Endre søk
Begrens søket
3435363738 1801 - 1850 of 1863
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Treff pr side
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
  • Standard (Relevans)
  • Forfatter A-Ø
  • Forfatter Ø-A
  • Tittel A-Ø
  • Tittel Ø-A
  • Type publikasjon A-Ø
  • Type publikasjon Ø-A
  • Eldste først
  • Nyeste først
  • Skapad (Eldste først)
  • Skapad (Nyeste først)
  • Senast uppdaterad (Eldste først)
  • Senast uppdaterad (Nyeste først)
  • Disputationsdatum (tidligste først)
  • Disputationsdatum (siste først)
Merk
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1801.
    Zhang, Lichao
    et al.
    Univ Autonoma Barcelona, Spain.
    Gonzalez-Garcia, Abel
    Univ Autonoma Barcelona, Spain.
    van de Weijer, Joost
    Univ Autonoma Barcelona, Spain.
    Danelljan, Martin
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Khan, Fahad
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Incept Inst Artificial Intelligence, U Arab Emirates.
    Synthetic Data Generation for End-to-End Thermal Infrared Tracking2019Inngår i: IEEE Transactions on Image Processing, ISSN 1057-7149, E-ISSN 1941-0042, Vol. 28, nr 4, s. 1837-1850Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The usage of both off-the-shelf and end-to-end trained deep networks have significantly improved the performance of visual tracking on RGB videos. However, the lack of large labeled datasets hampers the usage of convolutional neural networks for tracking in thermal infrared (TIR) images. Therefore, most state-of-the-art methods on tracking for TIR data are still based on handcrafted features. To address this problem, we propose to use image-to-image translation models. These models allow us to translate the abundantly available labeled RGB data to synthetic TIR data. We explore both the usage of paired and unpaired image translation models for this purpose. These methods provide us with a large labeled dataset of synthetic TIR sequences, on which we can train end-to-end optimal features for tracking. To the best of our knowledge, we are the first to train end-to-end features for TIR tracking. We perform extensive experiments on the VOT-TIR2017 dataset. We show that a network trained on a large dataset of synthetic TIR data obtains better performance than one trained on the available real TIR data. Combining both data sources leads to further improvement. In addition, when we combine the network with motion features, we outperform the state of the art with a relative gain of over 10%, clearly showing the efficiency of using synthetic data to train end-to-end TIR trackers.

  • 1802.
    Zhang, Silun
    et al.
    KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Optimeringslära och systemteori.
    Ringh, Axel
    KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Optimeringslära och systemteori.
    Hu, Xiaoming
    KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Optimeringslära och systemteori.
    Karlsson, Johan
    KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Optimeringslära och systemteori.
    A moment-based approach to modeling collective behaviors2018Inngår i: 2018 IEEE Conference on Decision and Control (CDC), Institute of Electrical and Electronics Engineers (IEEE), 2018, s. 1681-1687, artikkel-id 8619389Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this work we introduce an approach for modeling and analyzing collective behavior of a group of agents using moments. We represent the occupation measure of the group of agents by their moments and show how the dynamics of the moments can be modeled. Then approximate trajectories of the moments can be computed and an inverse problem is solved to recover macro-scale properties of the group of agents. To illustrate the theory, a numerical example with interactions between the agents is given.

  • 1803.
    Zhao, Yuxin
    Linköpings universitet, Institutionen för systemteknik, Reglerteknik. Linköpings universitet, Tekniska fakulteten.
    Position Estimation in Uncertain Radio Environments and Trajectory Learning2017Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    To infer the hidden states from the noisy observations and make predictions based on a set of input states and output observations are two challenging problems in many research areas. Examples of applications many include position estimation from various measurable radio signals in indoor environments, self-navigation for autonomous cars, modeling and predicting of the traffic flows, and flow pattern analysis for crowds of people. In this thesis, we mainly use the Bayesian inference framework for position estimation in an indoor environment, where the radio propagation is uncertain. In Bayesian inference framework, it is usually hard to get analytical solutions. In such cases, we resort to Monte Carlo methods to solve the problem numerically. In addition, we apply Bayesian nonparametric modeling for trajectory learning in sport analytics.

    The main contribution of this thesis is to propose sequential Monte Carlo methods, namely particle filtering and smoothing, for a novel indoor positioning framework based on proximity reports. The experiment results have been further compared with theoretical bounds derived for this proximity based positioning system. To improve the performance, Bayesian non-parametric modeling, namely Gaussian process, has been applied to better indicate the radio propagation conditions. Then, the position estimates obtained sequentially using filtering and smoothing are further compared with a static solution, which is known as fingerprinting.

    Moreover, we propose a trajectory learning framework for flow estimation in sport analytics based on Gaussian processes. To mitigate the computation deficiency of Gaussian process, a grid-based on-line algorithm has been adopted for real-time applications. The resulting trajectory modeling for individual athlete can be used for many purposes, such as performance prediction and analysis, health condition monitoring, etc. Furthermore, we aim at modeling the flow of groups of athletes, which could be potentially used for flow pattern recognition, strategy planning, etc.

  • 1804.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Hedman, Anders
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    How Good Can a Face Identifier Be Without Learning2016Inngår i: Lecture Notes in Computer Science, ISSN 0302-9743, E-ISSN 1611-3349Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Constructing discriminative features is an essential issue in developing face recognition algorithms. There are two schools in how features are constructed: hand-crafted features and learned features from data. A clear trend in the face recognition community is to use learned features to replace hand-crafted ones for face recognition, due to the superb performance achieved by learned features through Deep Learning networks. Given the negative aspects of database-dependent solutions, we consider an alternative and demonstrate that, for good generalization performance, developing face recognition algorithms by using handcrafted features is surprisingly promising when the training dataset is small or medium sized. We show how to build such a face identifier with our Block Matching method which leverages the power of the Gabor phase in face images. Although no learning process is involved, empirical results show that the performance of this “designed” identifier is comparable (superior) to state-of-the-art identifiers and even close to Deep Learning approaches.

  • 1805.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Hedman, Anders
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    How good can a face identifier be without learning?2017Inngår i: 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2016, Springer, 2017, Vol. 693, s. 515-533Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Constructing discriminative features is an essential issue in developing face recognition algorithms. There are two schools in how features are constructed: hand-crafted features and learned features from data. A clear trend in the face recognition community is to use learned features to replace hand-crafted ones for face recognition, due to the superb performance achieved by learned features through Deep Learning networks. Given the negative aspects of database-dependent solutions, we consider an alternative and demonstrate that, for good generalization performance, developing face recognition algorithms by using hand-crafted features is surprisingly promising when the training dataset is small or medium sized. We show how to build such a face identifier with our Block Matching method which leverages the power of the Gabor phase in face images. Although no learning process is involved, empirical results show that the performance of this “designed” identifier is comparable (superior) to state-of-the-art identifiers and even close to Deep Learning approaches.

  • 1806. Zhong, Yang
    et al.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Is block matching an alternative tool to LBP for face recognition?2014Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper, we introduce the Block Matching (BM) as an alternative patch-based local matching approach for solving the face recognition problem. The Block Matching enables an image patch of the probe face image to search for its best matching from displaced positions in the gallery face image. This matching strategy is very effective for handling spatial shift between two images and it is radically different from that of the widely used LBP type patch-based local matching approaches. Our evaluations on the FERET and CMU-PIE databases show that the performance of this simple method is well comparable (superior) to that of the popular LBP approach. We argue that the Block Matching could provide face recognition a new approach with more flexible algorithm architecture. One can expect that it could lead to much higher performance when combining with other feature extraction techniques, like Gabor wavelet and deep learning.

  • 1807.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Leveraging Gabor Phase for Face Identification in Controlled Scenarios2016Inngår i: Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Science and Technology Publications,Lda , 2016, s. 49-58Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Gabor features have been widely employed in solving face recognition problems in controlled scenarios. To construct discriminative face features from the complex Gabor space, the amplitude information is commonly preferred, while the other one — the phase — is not well utilized due to its spatial shift sensitivity. In this paper, we address the problem of face recognition in controlled scenarios. Our focus is on the selection of a suitable signal representation and the development of a better strategy for face feature construction. We demonstrate that through our Block Matching scheme Gabor phase information is powerful enough to improve the performance of face identification. Compared to state of the art Gabor filtering based approaches, the proposed algorithm features much lower algorithmic complexity. This is mainly due to our Block Matching enables the employment of high definition Gabor phase. Thus, a single-scale Gabor frequency band is sufficient for discrimination. Furthermore, learning process is not involved in the facial feature construction, which avoids the risk of building a database-dependent algorithm. Benchmark evaluations show that the proposed learning-free algorith outperforms state-of-the-art Gabor approaches and is even comparable to Deep Learning solutions.

  • 1808.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Face Attribute Prediction Using Off-The-Shelf CNN Features2016Inngår i: 2016 International Conference on Biometrics, ICB 2016, Institute of Electrical and Electronics Engineers (IEEE), 2016, artikkel-id 7550092Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks — face localization, facial descriptor construction, and attribute classification — in a pipeline. As a typical classification problem, face attribute preiction has been addressed using deep learning. Current state-of-the-art performance was achieved by using two cascaded Convolutional Neural Networks (CNNs), which were specifically trained to learn face localization and attribute description. In this paper, we experiment with an alternative way of employing the power of deep representations from CNNs. Combining with conventional face localization techniques, we use off-the-shelf architectures trained for face recognition to build facial descriptors. Recognizing that the describable face attributes are diverse, our face descriptors are constructed from different levels of the CNNs for different attributes to best facilitate face attribute prediction. Experiments on two large datasets, LFWA and CelebA, show that our approach is entirely comparable to the state-of-the-art. Our findings not only demonstrate an efficient face attribute prediction approach, but also raise an important question: how to leverage the power of off-the-shelf CNN representations for novel tasks

  • 1809.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Robotik, perception och lärande, RPL.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Leveraging Mid-level Deep Representations for Prediction Face Attributes in the Wild2016Inngår i: 2016 IEEE International Conference on Image Processing (ICIP), Institute of Electrical and Electronics Engineers (IEEE), 2016Konferansepaper (Fagfellevurdert)
  • 1810.
    Zhong, Yang
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Li, Haibo
    KTH, Skolan för datavetenskap och kommunikation (CSC), Medieteknik och interaktionsdesign, MID.
    Transferring from Face Recognition to Face Attribute Prediction through Adaptive Selection of Off-the-shelf CNN RepresentationsManuskript (preprint) (Annet vitenskapelig)
  • 1811.
    Zhu, Biwen
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Kommunikationssystem, CoS, Radio Systems Laboratory (RS Lab).
    Visual Tracking with Deep Learning: Automatic tracking of farm animals2018Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    Automatic tracking and video of surveillance on a farm could help to support farm management. In this project, an automated detection system is used to detect sows in surveillance videos. This system is based upon deep learning and computer vision methods. In order to minimize disk storage and to meet the network requirements necessary to achieve the real-performance, tracking in compressed video streams is essential.

    The proposed system uses a Discriminative Correlation Filter (DCF) as a classifier to detect targets. The tracking model is updated by training the classifier with online learning methods. Compression technology encodes the video data, thus reducing both the bit rates at which video signals are transmitted and helping the video transmission better adapt to the limited network bandwidth. However, compression may reduce the image quality of the videos the precision of our tracking may decrease. Hence, we conducted a performance evaluation of existing visual tracking algorithms on video sequences with quality degradation due to various compression parameters (encoders, target bitrate, rate control model, and Group of Pictures (GOP) size). The ultimate goal of video compression is to realize a tracking system with equal performance, but requiring fewer network resources.

    The proposed tracking algorithm successfully tracks each sow in consecutive frames in most cases. The performance of our tracker was benchmarked against two state-of-art tracking algorithms: Siamese Fully-Convolutional (FC) and Efficient Convolution Operators (ECO). The performance evaluation result shows our proposed tracker has similar performance to both Siamese FC and ECO.

    In comparison with the original tracker, the proposed tracker achieved similar tracking performance, while requiring much less storage and generating a lower bitrate when the video was compressed with appropriate parameters. However, the system is far slower than needed for real-time tracking due to high computational complexity; therefore, more optimal methods to update the tracking model will be needed to achieve real-time tracking.

  • 1812.
    Zhu, Peter
    Linköpings universitet, Institutionen för teknik och naturvetenskap.
    Deblurring Algorithms for Out-of-focus Infrared Images2010Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
    Abstract [en]

    An image that has been subject to the out-of-focus phenomenon has reducedsharpness, contrast and level of detail depending on the amount of defocus. Torestore out-of-focused images is a complex task due to the information loss thatoccurs. However there exist many restoration algorithms that attempt to revertthis defocus by estimating a noise model and utilizing the point spread function.The purpose of this thesis, proposed by FLIR Systems, was to find a robustalgorithm that can restore focus and from the customer’s perspective be userfriendly. The thesis includes three implemented algorithms that have been com-pared to MATLABs built-in. Three image series were used to evaluate the limitsand performance of each algorithm, based on deblurring quality, implementationcomplexity, computation time and usability.Results show that the Alternating Direction Method for total variation de-convolution proposed by Tao et al. [29] together with its the modified discretecosines transform version restores the defocused images with the highest qual-ity. These two algorithms include features such as, fast computational time, fewparameters to tune and a powerful noise reduction.

  • 1813.
    Zins, Matthieu
    Linköpings universitet, Institutionen för systemteknik, Datorseende.
    Color Fusion and Super-Resolution for Time-of-Flight Cameras2017Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    The recent emergence of time-of-flight cameras has opened up new possibilities in the world of computer vision. These compact sensors, capable of recording the depth of a scene in real-time, are very advantageous in many applications, such as scene or object reconstruction. This thesis first addresses the problem of fusing depth data with color images. A complete process to combine a time-of-flight camera with a color camera is described and its accuracy is evaluated. The results show that a satisfying precision is reached and that the step of calibration is very important.

    The second part of the work consists of applying super-resolution techniques to the time-of-flight camera in order to improve its low resolution. Different types of super-resolution algorithms exist but this thesis focuses on the combination of multiple shifted depth maps. The proposed framework is made of two steps: registration and reconstruction. Different methods for each step are tested and compared according to the improvements reached in term of level of details, sharpness and noise reduction. The results obtained show that Lucas-Kanade performs the best for the registration and that a non-uniform interpolation gives the best results in term of reconstruction. Finally, a few suggestions are made about future work and extensions for our solutions.

  • 1814.
    Zitinski Elias, Paula
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Nyström, Daniel
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Gooran, Sasan
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Color separation for improved perceived image quality in terms of graininess and gamut2017Inngår i: Color Research and Application, ISSN 0361-2317, E-ISSN 1520-6378, Vol. 42, nr 4, s. 486-497Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Multi-channel printing employs additional inks to improve the perceived image quality by reducing the graininess and augmenting the printer gamut. It also requires a color separation that deals with the one-to-many mapping problem imposed when using more than three inks. The proposed separation model incorporates a multilevel halftoning algorithm, reducing the complexity of the print characterization by grouping inks of similar hues in the same channel. In addition, a cost function is proposed that weights selected factors influencing the print and perceived image quality, namely color accuracy, graininess and ink consumption. The graininess perception is qualitatively assessed using S-CIELAB, a spatial low-pass filtering mimicking the human visual system. By applying it to a large set of samples, a generalized prediction quantifying the perceived graininess is carried out and incorporated as a criterion in the color separation. The results of the proposed model are compared with the separation giving the best colorimetric match, showing improvements in the perceived image quality in terms of graininess at a small cost of color accuracy and ink consumption. (c) 2016 Wiley Periodicals, Inc.

  • 1815.
    Zobel, Valentin
    et al.
    Zuse Institue Berlin.
    Reininghaus, Jan
    Zuse Institue Berlin.
    Hotz, Ingrid
    Zuse Institue Berlin.
    Visualization of Two-Dimensional Symmetric Tensor Fields Using the Heat Kernel Signature2014Inngår i: Topological Methods in Data Analysis and Visualization: Theory, Algorithms, and Applications / [ed] Peer-Timo Bremer, Ingrid Hotz, Valerio Pascucci, Ronald Peikert, Springer, 2014, s. 249-262Kapittel i bok, del av antologi (Fagfellevurdert)
    Abstract [en]

    We propose a method for visualizing two-dimensional symmetric positive definite tensor fields using the Heat Kernel Signature (HKS). The HKS is derived from the heat kernel and was originally introduced as an isometry invariant shape signature. Each positive definite tensor field defines a Riemannian manifold by considering the tensor field as a Riemannian metric. On this Riemmanian manifold we can apply the definition of the HKS. The resulting scalar quantity is used for the visualization of tensor fields. The HKS is closely related to the Gaussian curvature of the Riemannian manifold and the time parameter of the heat kernel allows a multiscale analysis in a natural way. In this way, the HKS represents field related scale space properties, enabling a level of detail analysis of tensor fields. This makes the HKS an interesting new scalar quantity for tensor fields, which differs significantly from usual tensor invariants like the trace or the determinant. A method for visualization and a numerical realization of the HKS for tensor fields is proposed in this chapter. To validate the approach we apply it to some illustrating simple examples as isolated critical points and to a medical diffusion tensor data set.

  • 1816.
    Zobel, Valentin
    et al.
    Leipzig University, Leipzig, Germany.
    Reininghaus, Jan
    Institute of Science and Technology Austria, Klosterneuburg, Austria.
    Hotz, Ingrid
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Visualizing Symmetric Indefinite 2D Tensor Fields using the Heat Kernel Signature2015Inngår i: Visualization and Processing of Tensors and Higher Order Descriptors for Multi-Valued Data / [ed] Ingrid Hotz, Thomas Schultz, Cham: Springer, 2015, s. 257-267Kapittel i bok, del av antologi (Fagfellevurdert)
    Abstract [en]

    The Heat Kernel Signature (HKS) is a scalar quantity which is derived from the heat kernel of a given shape. Due to its robustness, isometry invariance, and multiscale nature, it has been successfully applied in many geometric applications. From a more general point of view, the HKS can be considered as a descriptor of the metric of a Riemannian manifold. Given a symmetric positive definite tensor field we may interpret it as the metric of some Riemannian manifold and thereby apply the HKS to visualize and analyze the given tensor data. In this paper, we propose a generalization of this approach that enables the treatment of indefinite tensor fields, like the stress tensor, by interpreting them as a generator of a positive definite tensor field. To investigate the usefulness of this approach we consider the stress tensor from the two-point-load model example and from a mechanical work piece.

  • 1817.
    Zografos, Vasileios
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Enhancing motion segmentation by combination of complementary affinities2012Inngår i: Proceedings of the 21st Internationa Conference on Pattern Recognition, 2012, s. 2198-2201Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    Complementary information, when combined in the right way, is capable of improving clustering and segmentation problems. In this paper, we show how it is possible to enhance motion segmentation accuracy with a very simple and inexpensive combination of complementary information, which comes from the column and row spaces of the same measurement matrix. We test our approach on the Hopkins155 dataset where it outperforms all other state-of-the-art methods.

  • 1818.
    Zografos, Vasileios
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Lenz, Reiner
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    The Weibull manifold in low-level image processing: an application to automatic image focusing.2013Inngår i: Image and Vision Computing, ISSN 0262-8856, E-ISSN 1872-8138, Vol. 31, nr 5, s. 401-417Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this paper, we introduce a novel framework for low-level image processing and analysis. First, we process images with very simple, difference-based filter functions. Second, we fit the 2-parameter Weibull distribution to the filtered output. This maps each image to the 2D Weibull manifold. Third, we exploit the information geometry of this manifold and solve low-level image processing tasks as minimisation problems on point sets. For a proof-of-concept example, we examine the image autofocusing task. We propose appropriate cost functions together with a simple implicitly-constrained manifold optimisation algorithm and show that our framework compares very favourably against common autofocus methods from literature. In particular, our approach exhibits the best overall performance in terms of combined speed and accuracy

  • 1819.
    Zukas, Paulius
    Linnéuniversitetet, Fakulteten för teknik (FTK), Institutionen för datavetenskap och medieteknik (DM).
    Raising Awareness of Computer Vision: How can a single purpose focused CV solution be improved?2018Independent thesis Basic level (degree of Bachelor), 10 poäng / 15 hpOppgave
    Abstract [en]

    The concept of Computer Vision is not new or fresh. On contrary ideas have been shared and worked on for almost 60 years. Many use cases have been found throughout the years and various systems developed, but there is always a place for improvement. An observation was made, that methods used today are generally focused on a single purpose and implement expensive technology, which could be improved. In this report, we are going to go through an extensive research to find out if a professionally sold, expensive software, can be replaced by an off the shelf, low-cost solution entirely designed and developed in-house. To do that we are going to look at the history of Computer Vision, examples of applications, algorithms, and find general scenarios or computer vision problems which can be solved. We are then going take a step further and define solid use cases for each of the scenarios found. Finally, a prototype solution is going to be designed and presented. After analysing the results gathered we are going to reach out to the reader convincing him/her that such application can be developed and work efficiently in various areas saving investments to businesses.

  • 1820.
    Zunic, Jovisa
    et al.
    Faculty of Technical Sciences, University of Novi Sad.
    Sladoje, Nataša
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys. Faculty of Technical Sciences, University of Novi Sad .
    A characterization of digital disks by discrete moments1997Inngår i: International Conference on Computer Analysis of Images and Patterns / [ed] Sommer G., Daniilidis K., Pauli J., Springer, 1997, s. 582-589Konferansepaper (Fagfellevurdert)
  • 1821.
    Zunic, Jovisa
    et al.
    Faculty of Technical Sciences, University of Novi Sad.
    Sladoje, Nataša
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys. Faculty of Technical Sciences, University of Novi Sad.
    Efficiency of Characterizing Ellipses and Ellipsoids by Discrete Moments2000Inngår i: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 22, nr 4, s. 407-414Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this paper, our studies are focused on ellipses and problems related to their representation and reconstruction from the data resulting from their digitization. The main result of the paper is that a finite number of discrete moments, corresponded to digital ellipses, is in one-to-one correspondence with digital ellipses, which enables coding of digital ellipses with an asymptotically optimal amount of memory. In addition, the problem of reconstruction, based on the same parameters, is considered. Since the digitization of real shapes causes an inherent loss of information about the original objects, the precision of the original shape estimation from the corresponding digital data is limited. We derive a sharp upper bound for the errors in reconstruction of the center position and half-axes of the ellipse, in function of the applied picture resolution (i.e., the number of pixels per unit). An extension of these results to the 3D case is also given

  • 1822.
    Ärleryd, Sebastian
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion.
    Realtime Virtual 3D Image of Kidney Using Pre-Operative CT Image for Geometry and Realtime US-Image for Tracking2014Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
    Abstract [en]

    In this thesis a method is presented to provide a 3D visualization of the human kidney and surrounding tissue during kidney surgery. The method takes advantage of the high detail of 3D X-Ray Computed Tomography (CT) and the high time resolution of Ultrasonography (US). By extracting the geometry from a single preoperative CT scan and animating the kidney by tracking its position in real time US images, a 3D visualization of the surgical volume can be created. The first part of the project consisted of building an imaging phantom as a simplified model of the human body around the kidney. It consists of three parts: the shell part representing surrounding tissue, the kidney part representing the kidney soft tissue and a kidney stone part embedded in the kidney part. The shell and soft tissue kidney parts was cast with a mixture of the synthetic polymer Polyvinyl Alchohol (PVA) and water. The kidney stone part was cast with epoxy glue. All three parts where designed to look like human tissue in CT and US images. The method is a pipeline of stages that starts with acquiring the CT image as a 3D matrix of intensity values. This matrix is then segmented, resulting in separate polygonal 3D models for the three phantom parts. A scan of the model is then performed using US, producing a sequence of US images. A computer program extracts easily recognizable image feature points from the images in the sequence. Knowing the spatial position and orientation of a new US image in which these features can be found again allows the position of the kidney to be calculated. The presented method is realized as a proof of concept implementation of the pipeline. The implementation displays an interactive visualization where the kidney is positioned according to a user-selected US image scanned for image features. Using the proof of concept implementation as a guide, the accuracy of the proposed method is estimated to be bounded by the acquired image data. For high resolution CT and US images, the accuracy can be in the order of a few millimeters. 

  • 1823.
    Åhlen, Julia
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Color correction of underwater images based on estimation of diffuse attenuation coefficients2003Inngår i: Proceedings of 3rd conference for the promotion of research in IT, 2003Konferansepaper (Annet vitenskapelig)
  • 1824.
    Åhlén, Julia
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys.
    Colour Correction of Underwater Images Using Spectral Data2005Doktoravhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    For marine sciences sometimes there is a need to perform underwater photography. Optical properties of light cause severe quality problems for underwater photography. Light of different energies is absorbed at highly different rates under water causing significant bluishness of the images. If the colour dependent attenuation under water can be properly estimated it should be possible to use computerised image processing to colour correct digital images using Beer’s Law.

    In this thesis we have developed such estimation and correction methods that have become progressively more complicated and more accurate giving successively better correction results. A process of estimation of downwelling attenuation coefficients from multi or hyper spectral data is a basis for automatic colour restoration of underwater taken images. The results indicate that for each diving site the unique and precise coefficients can be obtained.

    All standard digital cameras have built in white balancing and colour enhancement functions designed to make the images as aesthetically pleasing as possible. These functions can in most cameras not be switched off and the algorithms used are proprietary and undocumented. However, these enhancement functions can be estimated. Applying their reverse creates un-enhanced images and we show that our algorithms for underwater colour correction works significantly better when applied to such images.

    Finally, we have developed a method that uses point spectra from the spectrometer together with RGB colour images from a camera to generate pseudo-hyper-spectral images. Each of these can then be colour corrected. Finally, the images can be weighted together in the proportions needed to create new correct RGB images. This method is somewhat computationally demanding but gives very encouraging results.

    The algorithms and applications presented in this thesis show that automatic colour correction of underwater images can increase the credibility of data taken underwater for marine scientific purposes.

  • 1825. Åhlén, Julia
    et al.
    Seipel, Stefan
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.
    Automatic Water Body Extraction From Remote Sensing Images Using Entropy2015Inngår i: SGEM2015 Conference Proceedings, 2015, Vol. 2, s. 517-524Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This research focuses on automatic extraction of river banks and other inland waters from remote sensing images. There are no up to date accessible databases of rivers and most of other waters objects for modelling purposes. The main reason for that is that some regions are hard to access with the traditional ground through techniques and thus the boundary of river banks are uncertain in many geographical positions. The other reason is the limitations of widely applied method for extraction of water bodies called normalized-difference water index (NDWI). There is a novel approach to extract water bodies, which is based on pixel level variability or entropy, however, the methods work somewhat satisfactory on high spatial resolution images, there is no verification of the method performance on moderate or low resolution images. Problems encounter identification of mixed water pixels and e.g. roads, which are built in attachment to river banks and thus can be classified as rivers. In this work we propose an automatic extraction of river banks using image entropy, combined with NDWI identification. In this study only moderate spatial resolution Landsat TM are tested. Areas of interest include both major river banks and inland lakes. Calculating entropy on such poor spatial resolution images will lead to misinterpretation of water bodies, which all exhibits the same small variation of pixel values as e.g. some open or urban areas. Image entropy thus is calculated with the modification that involves the incorporation of local normalization index or variability coefficient. NDWI will produce an image where clear water exhibits large difference comparing to other land features. We are presenting an algorithm that uses an NDWI prior to entropy processing, so that bands used to calculate it, are chosen in clear connection to water body features that are clearly discernible.As a result we visualize a clear segmentation of the water bodies from the remote sensing images and verify the coordinates with a given geographic reference.

  • 1826.
    Åhlén, Julia
    et al.
    Högskolan i Gävle, Akademin för teknik och miljö, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, Samhällsbyggnad, GIS.
    Seipel, Stefan
    Högskolan i Gävle, Akademin för teknik och miljö, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, Datavetenskap. Uppsala University, Department of Information Technology, Sweden .
    Automatic water body extraction from remote sensing images using entropy2015Inngår i: Proceedings of the International Multidisciplinary Scientific GeoConference SGEM, 2015, Vol. 4, s. 517-524Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This research focuses on automatic extraction of river banks and other inland waters from remote sensing images. There are no up to date accessible databases of rivers and most of other waters objects for modelling purposes. The main reason for that is that some regions are hard to access with the traditional ground through techniques and thus the boundary of river banks are uncertain in many geographical positions. The other reason is the limitations of widely applied method for extraction of water bodies called normalized-difference water index (NDWI). There is a novel approach to extract water bodies, which is based on pixel level variability or entropy, however, the methods work somewhat satisfactory on high spatial resolution images, there is no verification of the method performance on moderate or low resolution images. Problems encounter identification of mixed water pixels and e.g. roads, which are built in attachment to river banks and thus can be classified as rivers. In this work we propose an automatic extraction of river banks using image entropy, combined with NDWI identification. In this study only moderate spatial resolution Landsat TM are tested. Areas of interest include both major river banks and inland lakes. Calculating entropy on such poor spatial resolution images will lead to misinterpretation of water bodies, which all exhibits the same small variation of pixel values as e.g. some open or urban areas. Image entropy thus is calculated with the modification that involves the incorporation of local normalization index or variability coefficient. NDWI will produce an image where clear water exhibits large difference comparing to other land features. We are presenting an algorithm that uses an NDWI prior to entropy processing, so that bands used to calculate it, are chosen in clear connection to water body features that are clearly discernible.As a result we visualize a clear segmentation of the water bodies from the remote sensing images and verify the coordinates with a given geographic reference.

  • 1827.
    Åhlén, Julia
    et al.
    Högskolan i Gävle, Akademin för teknik och miljö, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, Samhällsbyggnad/GIS-Institutet.
    Seipel, Stefan
    Högskolan i Gävle, Akademin för teknik och miljö, Avdelningen för Industriell utveckling, IT och Samhällsbyggnad, Datavetenskap.
    Early Recognition of Smoke in Digital Video2010Inngår i: Advances in Communications, Computers, Systems, Circuits and Devices: European Conference of Systems, ECS'10, European Conference of Circuits Technology and Devices, ECCTD'10, European Conference of Communications, ECCOM'10, ECCS'10 / [ed] Mladenov, V; Psarris, K; Mastorakis, N; Caballero, A; Vachtsevanos, G, Athens: World Scientific and Engineering Academy and Society, 2010, s. 301-306Konferansepaper (Fagfellevurdert)
    Abstract [en]

    This paper presents a method for direct smoke detection from video without enhancement pre-processing steps. Smoke is characterized by transparency, gray color and irregularities in motion, which are hard to describe with the basic image features. A method for robust smoke description using a color balancing algorithm and turbulence calculation is presented in this work. Background extraction is used as a first step in processing. All moving objects are candidates for smoke. We make use of Gray World algorithm and compare the results with the original video sequence in order to extract image features within some particular gray scale interval. As a last step we calculate shape complexity of turbulent phenomena and apply it to the incoming video stream. As a result we extract only smoke from the video. Features such shadows, illumination changes and people will not be mistaken for smoke by the algorithm. This method gives an early indication of smoke in the observed scene.

  • 1828.
    Åhlén, Julia
    et al.
    Högskolan i Gävle.
    Seipel, Stefan
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.
    Knowledge Based Single Building Extraction and Recognition2014Inngår i: Proceedings WSEAS International Conference on Computer Engineering and Applications, 2014, 2014, s. 29-35Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Building facade extraction is the primary step in the recognition process in outdoor scenes. It is also achallenging task since each building can be viewed from different angles or under different lighting conditions. Inoutdoor imagery, regions, such as sky, trees, pavement cause interference for a successful building facade recognition.In this paper we propose a knowledge based approach to automatically segment out the whole facade or majorparts of the facade from outdoor scene. The found building regions are then subjected to recognition process. Thesystem is composed of two modules: segmentation of building facades region module and facade recognition module.In the facade segmentation module, color processing and objects position coordinates are used. In the facaderecognition module, Chamfer metrics are applied. In real time recognition scenario, the image with a building isfirst analyzed in order to extract the facade region, which is then compared to a database with feature descriptors inorder to find a match. The results show that the recognition rate is dependent on a precision of building extractionpart, which in turn, depends on a homogeneity of colors of facades.

  • 1829.
    Åhlén, Julia
    et al.
    Högskolan i Gävle.
    Seipel, Stefan
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.
    TIME-SPACE VISUALISATION OF AMUR RIVER CHANNEL CHANGES DUE TO FLOODING DISASTER2014Inngår i: Proceedings of International Multidisciplinary Scientific GeoScience Conference (SGEM), 2014, 2014Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The analysis of flooding levels is a highly complex temporal and spatial assessment task that involves estimation of distances between references in geographical space as well as estimations of instances along the time-line that coincide with given spatial locations. This work has an aim to interactively explore changes of Amur River boundaries caused by the severe flooding in September 2013. In our analysis of river bank changes we use satellite imagery (Landsat 7) to extract parts belonging to Amur River. We use imagery from that covers time interval July 2003 until February 2014. Image data is pre-processed using low level image processing techniques prior to visualization. Pre-processing has a purpose to extract information about the boundaries of the river, and to transform it into a vectorized format, suitable as inputs subsequent visualization. We develop visualization tools to explore the spatial and temporal relationship in the change of river banks. In particular the visualization shall allow for exploring specific geographic locations and their proximity to the river/floods at arbitrary times. We propose a time space visualization that emanates from edge detection, morphological operations and boundary statistics on Landsat 2D imagery in order to extract the borders of Amur River. For the visualization we use the time-spacecube metaphor. It is based on a 3D rectilinear context, where the 2D geographical coordinate system is extended with a time-axis pointing along the 3rd Cartesian axis. Such visualization facilitates analysis of the channel shape of Amur River and thus enabling for a conclusion regarding the defined problem. As a result we demonstrate our time-space visualization for river Amur and using some amount of geographical point data as a reference we suggest an adequate method of interpolation or imputation that can be employed to estimate value at a given location and time.

  • 1830.
    Åhlén, Julia
    et al.
    Högskolan i Gävle.
    Seipel, Stefan
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.
    Liu, Fei
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion.
    Evaluation of the Automatic methods for Building Extraction2014Inngår i: International Journal of Computers and Communications, ISSN 2074-1294, Vol. 8, s. 171-176Artikkel i tidsskrift (Fagfellevurdert)
  • 1831.
    Åhlén Julia, Sundgren David
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Bottom Reflectance Influence on a Color Correction Algorithm for Underwater Images2003Inngår i: 13th Scandinavian Conference, SCIA 2003 Göteborg, Sweden, June 29-July 2, 2003, 2003, s. 922-926Konferansepaper (Fagfellevurdert)
  • 1832.
    Åhlén, Julia
    et al.
    Uppsala universitet.
    Sundgren, David
    Stockholms universitet.
    Bottom Reflectance Influence on a Color Correction Algorithm for Underwater Images2003Inngår i: Proceedings of the 13th Scandinavinan Conference on Image Analysis / [ed] Bigun, J., Gustavsson, T., Berlin: Springer , 2003, s. 922-926Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Diminishing the negative effects of water column introduced on digital underwater images is the aim of a color correction algorithm presented by the authors in a previous paper. The present paper describes an experimental result and set of calculations for determining the impact of bottom reflectance on the algorithm's performance. This concept is based on the estimation of the relative reflectance of various bottom types such as sand, bleached corals and algae. We describe the adverse effects of extremely low and high bottom reflectances on the algorithm.

  • 1833.
    Åhlén, Julia
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Sundgren, David
    KTH.
    Bengtsson, Ewert
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Pre-Processing of Underwater Images Taken in shallow Water for Color Reconstruction Purposes2005Inngår i: IASTED Proceeding (479): IASTED 7th Conference on Signal and Image Processing - 2005, 2005Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Coral reefs are monitored with different techniques in or der to examine their health. Digital cameras, which pro vide an economically defendable tool for marine scientists to collect underwater data, tend to produce bluish images due to severe absorption of light at longer wavelengths. In this paper we study the possibilities of correcting for this color distortion through image processing. The decrease of red light by depth can be predicted by Beer’s Law. An other parameter that has been taken into account is the image enhancement functions built into the camera. We use a spectrometer and a reflectance standard to obtain the data needed to approximate the joint effect of these func tions. This model is used to pre-process the underwater images taken by digital cameras so that the red, green and blue channels show correct values before the images are subjected to correction for the effects of the water column through application of Beer’s Law. This process is fully automatic and the amount of processed images is limited only by the speed of computer system. Experimental re sults show that the proposed method works well for cor recting images taken at different depths with two different cameras.

  • 1834.
    Åhlén, Julia
    et al.
    Högskolan i Gävle, Institutionen för matematik, natur- och datavetenskap, Ämnesavdelningen för datavetenskap.
    Sundgren, David
    Högskolan i Gävle, Institutionen för matematik, natur- och datavetenskap, Ämnesavdelningen för matematik och statistik.
    Bengtsson, Ewert
    Pre-Processing of Underwater Images Taken in Shallow Waters for Color Reconstruction Purposes2005Inngår i: Proceedings of the 7th IASTED International Conference on Signal and Image Processing, 2005Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Coral reefs are monitored with different techniques in order to examine their health. Digital cameras, which provide an economically defendable tool for marine scientists to collect underwater data, tend to produce bluish images due to severe absorption of light at longer wavelengths. In this paper we study the possibilities of correcting for this color distortion through image processing. The decrease of red light by depth can be predicted by Beer's law. Another parameter that has to be taken into account is the image enhancement functions built into the camera. We use a spectrometer and a reflectance standard to obtain the data needed to approximate the joint effect of these functions. This model is used to pre-process the underwater images taken by digital cameras so that the red, green and blue channels show correct values before the images are subjected to correction for the effects of water column through application of Beer's law. This process is fully automatic and the amount of processed images is limited only by the speed of computer system. Experimental results show that the proposed method works well for correcting images taken at different depths with two different cameras.

  • 1835.
    Åhlén, Julia
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Sundgren, David
    KTH.
    Lindell, Tommy
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Bengtsson, Ewert
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Dissolved Organic Matters Impact on Colour2005Inngår i: Image Analysis: 14th Scandinavian Conference, SCIA 2005, 2005, s. 1148-1156Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The natural properties of water column usually affect under-water

    imagery by suppressing high-energy light. In application such as

    color correction of underwater images estimation of water column parameters is crucial. Diffuse attenuation coefficients are estimated and used for further processing of underwater taken data. The coefficients will give information on how fast light of different wavelengths decreases with increasing depth. Based on the exact depth measurements and data from a spectrometer the calculation of downwelling irradiance will be done. Chlorophyll concentration and a yellow substance factor contribute to a great variety of values of attenuation coefficients at different depth. By taking advantage of variations in depth, a method is presented to

    estimate the in uence of dissolved organic matters and chlorophyll on color correction. Attenuation coefficients that depends on concentration of dissolved organic matters in water gives an indication on how well any spectral band is suited for color correction algorithm.

  • 1836.
    Åkerlind, Christina
    et al.
    Linköpings universitet, Institutionen för fysik, kemi och biologi. Linköpings universitet, Tekniska fakulteten. FOI, Linköping, Sweden.
    Fagerström, Jan
    FOI, Linköping, Sweden.
    Hallberg, Tomas
    FOI, Linköping, Sweden.
    Kariis, Hans
    FOI, Linköping, Sweden.
    Evaluation criteria for spectral design of camouflage2015Inngår i: Proc. SPIE 9653, Target and Background Signatures / [ed] Karin U. Stein; Ric H. M. A. Schleijpen, SPIE - International Society for Optical Engineering, 2015, Vol. 9653, s. Art.no: 9653-2-Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In development of visual (VIS) and infrared (IR) camouflage for signature management, the aim is the design of surface properties of an object to spectrally match or adapt to a background and thereby minimizing the contrast perceived by a threatening sensor. The so called 'ladder model" relates the requirements for task measure of effectiveness with surface structure properties through the steps signature effectiveness and object signature. It is intended to link materials properties via platform signature to military utility and vice versa. Spectral design of a surface intends to give it a desired wavelength dependent optical response to fit a specific application of interest. Six evaluation criteria were stated, with the aim to aid the process to put requirement on camouflage and for evaluation. The six criteria correspond to properties such as reflectance, gloss, emissivity, and degree of polarization as well as dynamic properties, and broadband or multispectral properties. These criteria have previously been exemplified on different kinds of materials and investigated separately. Anderson and Åkerlind further point out that the six criteria rarely were considered or described all together in one and same publication previously. The specific level of requirement of the different properties must be specified individually for each specific situation and environment to minimize the contrast between target and a background. The criteria or properties are not totally independent of one another. How they are correlated is part of the theme of this paper. However, prioritization has been made due to the limit of space. Therefore all of the interconnections between the six criteria will not be considered in the work of this report. The ladder step previous to digging into the different material composition possibilities and choice of suitable materials and structures (not covered here), includes the object signature and decision of what the spectral response should be, when intended for a specific environment. The chosen spectral response should give a low detection probability (DP). How detection probability connects to image analysis tools and implementation of the six criteria is part of this work.

  • 1837.
    Åkesson, Ulrik
    Mälardalens högskola, Akademin för innovation, design och teknik.
    Design of a multi-camera system for object identification, localisation, and visual servoing2019Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    In this thesis, the development of a stereo camera system for an intelligent tool is presented. The task of the system is to identify and localise objects so that the tool can guide a robot. Different approaches to object detection have been implemented and evaluated and the systems ability to localise objects has been tested. The results show that the system can achieve a localisation accuracy below 5 mm.

  • 1838.
    Åström, Freddie
    et al.
    Heidelberg University, Germany.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Baravdish, George
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Kommunikations- och transportsystem. Linköpings universitet, Tekniska fakulteten.
    Mapping-Based Image Diffusion2017Inngår i: Journal of Mathematical Imaging and Vision, ISSN 0924-9907, E-ISSN 1573-7683, Vol. 57, nr 3, s. 293-323Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this work, we introduce a novel tensor-based functional for targeted image enhancement and denoising. Via explicit regularization, our formulation incorporates application-dependent and contextual information using first principles. Few works in literature treat variational models that describe both application-dependent information and contextual knowledge of the denoising problem. We prove the existence of a minimizer and present results on tensor symmetry constraints, convexity, and geometric interpretation of the proposed functional. We show that our framework excels in applications where nonlinear functions are present such as in gamma correction and targeted value range filtering. We also study general denoising performance where we show comparable results to dedicated PDE-based state-of-the-art methods.

  • 1839.
    Åström, Freddie
    et al.
    Heidelberg Collaboratory for Image Processing Heidelberg University Heidelberg, Germany.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Scharr, Hanno
    BG-2: Plant Sciences Forschungszentrum Jülich 52425, Jülich, Germany.
    Adaptive sharpening of multimodal distributions2015Inngår i: Colour and Visual Computing Symposium (CVCS), 2015 / [ed] Marius Pedersen and Jean-Baptiste Thomas, IEEE , 2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this work we derive a novel framework rendering measured distributions into approximated distributions of their mean. This is achieved by exploiting constraints imposed by the Gauss-Markov theorem from estimation theory, being valid for mono-modal Gaussian distributions. It formulates the relation between the variance of measured samples and the so-called standard error, being the standard deviation of their mean. However, multi-modal distributions are present in numerous image processing scenarios, e.g. local gray value or color distributions at object edges, or orientation or displacement distributions at occlusion boundaries in motion estimation or stereo. Our method not only aims at estimating the modes of these distributions together with their standard error, but at describing the whole multi-modal distribution. We utilize the method of channel representation, a kind of soft histogram also known as population codes, to represent distributions in a non-parametric, generic fashion. Here we apply the proposed scheme to general mono- and multimodal Gaussian distributions to illustrate its effectiveness and compliance with the Gauss-Markov theorem.

  • 1840.
    Öfjäll, Kristoffer
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Adaptive Supervision Online Learning for Vision Based Autonomous Systems2016Doktoravhandling, monografi (Annet vitenskapelig)
    Abstract [en]

    Driver assistance systems in modern cars now show clear steps towards autonomous driving and improvements are presented in a steady pace. The total number of sensors has also decreased from the vehicles of the initial DARPA challenge, more resembling a pile of sensors with a car underneath. Still, anyone driving a tele-operated toy using a video link is a demonstration that a single camera provides enough information about the surronding world.  

    Most lane assist systems are developed for highway use and depend on visible lane markers. However, lane markers may not be visible due to snow or wear, and there are roads without lane markers. With a slightly different approach, autonomous road following can be obtained on almost any kind of road. Using realtime online machine learning, a human driver can demonstrate driving on a road type unknown to the system and after some training, the system can seamlessly take over. The demonstrator system presented in this work has shown capability of learning to follow different types of roads as well as learning to follow a person. The system is based solely on vision, mapping camera images directly to control signals.  

    Such systems need the ability to handle multiple-hypothesis outputs as there may be several plausible options in similar situations. If there is an obstacle in the middle of the road, the obstacle can be avoided by going on either side. However the average action, going straight ahead, is not a viable option. Similarly, at an intersection, the system should follow one road, not the average of all roads.  

    To this end, an online machine learning framework is presented where inputs and outputs are represented using the channel representation. The learning system is structurally simple and computationally light, based on neuropsychological ideas presented by Donald Hebb over 60 years ago. Nonetheless the system has shown a cabability to learn advanced tasks. Furthermore, the structure of the system permits a statistical interpretation where a non-parametric representation of the joint distribution of input and output is generated. Prediction generates the conditional distribution of the output, given the input.  

    The statistical interpretation motivates the introduction of priors. In cases with multiple options, such as at intersections, a prior can select one mode in the multimodal distribution of possible actions. In addition to the ability to learn from demonstration, a possibility for immediate reinforcement feedback is presented. This allows for a system where the teacher can choose the most appropriate way of training the system, at any time and at her own discretion.  

    The theoretical contributions include a deeper analysis of the channel representation. A geometrical analysis illustrates the cause of decoding bias commonly present in neurologically inspired representations, and measures to counteract it. Confidence values are analyzed and interpreted as evidence and coherence. Further, the use of the truncated cosine basis function is motivated.  

    Finally, a selection of applications is presented, such as autonomous road following by online learning and head pose estimation. A method founded on the same basic principles is used for visual tracking, where the probabilistic representation of target pixel values allows for changes in target appearance.

  • 1841.
    Öfjäll, Kristoffer
    Linköpings universitet, Institutionen för systemteknik, Bildbehandling. Linköpings universitet, Tekniska högskolan.
    LEAP, A Platform for Evaluation of Control Algorithms2010Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
    Abstract [en]

    Most people are familiar with the BRIO labyrinth game and the challenge of guiding the ball through the maze. The goal of this project was to use this game to create a platform for evaluation of control algorithms. The platform was used to evaluate a few different controlling algorithms, both traditional automatic control algorithms as well as algorithms based on online incremental learning.

    The game was fitted with servo actuators for tilting the maze. A camera together with computer vision algorithms were used to estimate the state of the game. The evaluated controlling algorithm had the task of calculating a proper control signal, given the estimated state of the game.

    The evaluated learning systems used traditional control algorithms to provide initial training data. After initial training, the systems learned from their own actions and after a while they outperformed the controller used to provide initial training.

  • 1842.
    Öfjäll, Kristoffer
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Online Learning for Robot Vision2014Licentiatavhandling, med artikler (Annet vitenskapelig)
    Abstract [en]

    In tele-operated robotics applications, the primary information channel from the robot to its human operator is a video stream. For autonomous robotic systems however, a much larger selection of sensors is employed, although the most relevant information for the operation of the robot is still available in a single video stream. The issue lies in autonomously interpreting the visual data and extracting the relevant information, something humans and animals perform strikingly well. On the other hand, humans have great diculty expressing what they are actually looking for on a low level, suitable for direct implementation on a machine. For instance objects tend to be already detected when the visual information reaches the conscious mind, with almost no clues remaining regarding how the object was identied in the rst place. This became apparent already when Seymour Papert gathered a group of summer workers to solve the computer vision problem 48 years ago [35].

    Articial learning systems can overcome this gap between the level of human visual reasoning and low-level machine vision processing. If a human teacher can provide examples of what to be extracted and if the learning system is able to extract the gist of these examples, the gap is bridged. There are however some special demands on a learning system for it to perform successfully in a visual context. First, low level visual input is often of high dimensionality such that the learning system needs to handle large inputs. Second, visual information is often ambiguous such that the learning system needs to be able to handle multi modal outputs, i.e. multiple hypotheses. Typically, the relations to be learned  are non-linear and there is an advantage if data can be processed at video rate, even after presenting many examples to the learning system. In general, there seems to be a lack of such methods.

    This thesis presents systems for learning perception-action mappings for robotic systems with visual input. A range of problems are discussed, such as vision based autonomous driving, inverse kinematics of a robotic manipulator and controlling a dynamical system. Operational systems demonstrating solutions to these problems are presented. Two dierent approaches for providing training data are explored, learning from demonstration (supervised learning) and explorative learning (self-supervised learning). A novel learning method fullling the stated demands is presented. The method, qHebb, is based on associative Hebbian learning on data in channel representation. Properties of the method are demonstrated on a vision-based autonomously driving vehicle, where the system learns to directly map low-level image features to control signals. After an initial training period, the system seamlessly continues autonomously. In a quantitative evaluation, the proposed online learning method performed comparably with state of the art batch learning methods.

  • 1843.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Biologically Inspired Online Learning of Visual Autonomous Driving2014Inngår i: Proceedings British Machine Vision Conference 2014 / [ed] Michel Valstar; Andrew French; Tony Pridmore, BMVA Press , 2014, s. 137-156Konferansepaper (Fagfellevurdert)
    Abstract [en]

    While autonomously driving systems accumulate more and more sensors as well as highly specialized visual features and engineered solutions, the human visual system provides evidence that visual input and simple low level image features are sufficient for successful driving. In this paper we propose extensions (non-linear update and coherence weighting) to one of the simplest biologically inspired learning schemes (Hebbian learning). We show that this is sufficient for online learning of visual autonomous driving, where the system learns to directly map low level image features to control signals. After the initial training period, the system seamlessly continues autonomously. This extended Hebbian algorithm, qHebb, has constant bounds on time and memory complexity for training and evaluation, independent of the number of training samples presented to the system. Further, the proposed algorithm compares favorably to state of the art engineered batch learning algorithms.

  • 1844.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Combining Vision, Machine Learning and Automatic Control to Play the Labyrinth Game2012Inngår i: Proceedings of SSBA, Swedish Symposium on Image Analysis, 2012, 2012Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    The labyrinth game is a simple yet challenging platform, not only for humans but also for control algorithms and systems. The game is easy to understand but still very hard to master. From a system point of view, the ball behavior is in general easy to model but close to the obstacles there are severe non-linearities. Additionally, the far from flat surface on which the ball rolls provides for changing dynamics depending on the ball position.

    The general dynamics of the system can easily be handled by traditional automatic control methods. Taking the obstacles and uneven surface into account would require very detailed models of the system. A simple deterministic control algorithm is combined with a learning control method. The simple control method provides initial training data. As thelearning method is trained, the system can learn from the results of its own actions and the performance improves well beyond the performance of the initial controller.

    A vision system and image analysis is used to estimate the ball position while a combination of a PID controller and a learning controller based on LWPR is used to learn to steer the ball through the maze.

  • 1845.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Integrating Learning and Optimization for Active Vision Inverse Kinematics2013Inngår i: Proceedings of SSBA, Swedish Symposium on Image Analysis, 2013, 2013Konferansepaper (Annet vitenskapelig)
  • 1846.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Online Learning and Mode Switching for Autonomous Driving from Demonstration2014Inngår i: Proceedings of SSBA, Swedish Symposium on Image Analysis, 2014, 2014Konferansepaper (Annet vitenskapelig)
  • 1847.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Online learning of autonomous driving using channel representations of multi-modal joint distributions2015Inngår i: Proceedings of SSBA, Swedish Symposium on Image Analysis, 2015, Swedish Society for automated image analysis , 2015Konferansepaper (Annet vitenskapelig)
  • 1848.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Online Learning of Vision-Based Robot Control during Autonomous Operation2015Inngår i: New Development in Robot Vision / [ed] Yu Sun, Aman Behal and Chi-Kit Ronald Chung, Springer Berlin/Heidelberg, 2015, s. 137-156Kapittel i bok, del av antologi (Fagfellevurdert)
    Abstract [en]

    Online learning of vision-based robot control requires appropriate activation strategies during operation. In this chapter we present such a learning approach with applications to two areas of vision-based robot control. In the first setting, selfevaluation is possible for the learning system and the system autonomously switches to learning mode for producing the necessary training data by exploration. The other application is in a setting where external information is required for determining the correctness of an action. Therefore, an operator provides training data when required, leading to an automatic mode switch to online learning from demonstration. In experiments for the first setting, the system is able to autonomously learn the inverse kinematics of a robotic arm. We propose improvements producing more informative training data compared to random exploration. This reduces training time and limits learning to regions where the learnt mapping is used. The learnt region is extended autonomously on demand. In experiments for the second setting, we present an autonomous driving system learning a mapping from visual input to control signals, which is trained by manually steering the robot. After the initial training period, the system seamlessly continues autonomously. Manual control can be taken back at any time for providing additional training.

  • 1849.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska högskolan. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Weighted Update and Comparison for Channel-Based Distribution Field Tracking2015Inngår i: COMPUTER VISION - ECCV 2014 WORKSHOPS, PT II, Springer, 2015, Vol. 8926, s. 218-231Konferansepaper (Fagfellevurdert)
    Abstract [en]

    There are three major issues for visual object trackers: modelrepresentation, search and model update. In this paper we address thelast two issues for a specic model representation, grid based distributionmodels by means of channel-based distribution elds. Particularly weaddress the comparison part of searching. Previous work in the areahas used standard methods for comparison and update, not exploitingall the possibilities of the representation. In this work we propose twocomparison schemes and one update scheme adapted to the distributionmodel. The proposed schemes signicantly improve the accuracy androbustness on the Visual Object Tracking (VOT) 2014 Challenge dataset.

  • 1850.
    Öfjäll, Kristoffer
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Felsberg, Michael
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Robinson, Andreas
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten.
    Visual Autonomous Road Following by Symbiotic Online Learning2016Inngår i: Intelligent Vehicles Symposium (IV), 2016 IEEE, 2016, s. 136-143Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Recent years have shown great progress in driving assistance systems, approaching autonomous driving step by step. Many approaches rely on lane markers however, which limits the system to larger paved roads and poses problems during winter. In this work we explore an alternative approach to visual road following based on online learning. The system learns the current visual appearance of the road while the vehicle is operated by a human. When driving onto a new type of road, the human driver will drive for a minute while the system learns. After training, the human driver can let go of the controls. The present work proposes a novel approach to online perception-action learning for the specific problem of road following, which makes interchangeably use of supervised learning (by demonstration), instantaneous reinforcement learning, and unsupervised learning (self-reinforcement learning). The proposed method, symbiotic online learning of associations and regression (SOLAR), extends previous work on qHebb-learning in three ways: priors are introduced to enforce mode selection and to drive learning towards particular goals, the qHebb-learning methods is complemented with a reinforcement variant, and a self-assessment method based on predictive coding is proposed. The SOLAR algorithm is compared to qHebb-learning and deep learning for the task of road following, implemented on a model RC-car. The system demonstrates an ability to learn to follow paved and gravel roads outdoors. Further, the system is evaluated in a controlled indoor environment which provides quantifiable results. The experiments show that the SOLAR algorithm results in autonomous capabilities that go beyond those of existing methods with respect to speed, accuracy, and functionality. 

3435363738 1801 - 1850 of 1863
RefereraExporteraLink til resultatlisten
Permanent link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf