Endre søk
Begrens søket
1234567 101 - 150 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.
  • 101.
    Augustsson, Louise
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion.
    Study and Analysis of Convolutional Neural Networks for Pedestrian Detection in Autonomous Vehicles2018Independent thesis Advanced level (professional degree), 20 poäng / 30 hpOppgave
    Abstract [en]

    The automotive industry is heading towards more automation. This puts high demands on many systems like Pedestrian Detection Systems. Such systems need to operate in real time with high accuracy and in embedded systems with limited power, memory resources and compute power. This in turn puts high demands on model size and model design. Lately Convolutional Neural Networks (ConvNets) have dominated the field of object detection and therefore it is reasonable to believe that they are suited for pedestrian detection as well. Therefore, this thesis investigates how ConvNets have been used for pedestrian detection and how such solutions can be implemented in embedded systems on FPGAs (Field Programmable Gate Arrays). The conclusions drawn are that ConvNets indeed perform well on pedestrian detection in terms of accuracy but to a cost of large model sizes and heavy computations. This thesis also comes up with a design proposal of a ConvNet for pedestrian detection with the implementation in an embedded system in mind. The proposed network performs well on pedestrian classification and the performance looks promising for detection as well, but further development is required.

  • 102.
    Aviles, Marcos
    et al.
    GMV, Spain.
    Siozios, Kostas
    School of ECE, National Technical University of Athens, Greece.
    Diamantopoulos, Dionysios
    School of ECE, National Technical University of Athens, Greece.
    Nalpantidis, Lazaros
    Production and Management Engineering Dept., Democritus University of Thrace, Greece.
    Kostavelis, Ioannis
    Production and Management Engineering Dept., Democritus University of Thrace, Greece.
    Boukas, Evangelos
    Production and Management Engineering Dept., Democritus University of Thrace, Greece.
    Soudris, Dimitrios
    School of ECE, National Technical University of Athens, Greece.
    Gasteratos, Antonios
    Production and Management Engineering Dept., Democritus University of Thrace, Greece.
    A co-design methodology for implementing computer vision algorithms for rover navigation onto reconfigurable hardware2011Inngår i: Proceedings of the FPL2011 Workshop on Computer Vision on Low-Power Reconfigurable Architectures, 2011, s. 9-10Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    Vision-based robotics applications have been widely studied in the last years. However, up to now solutions that have been proposed were affecting mostly software level. The SPARTAN project focuses in the tight and optimal implementation of computer vision algorithms targeting to rover navigation. For evaluation purposes, these algorithms will be implemented with a co-design methodology onto a Virtex-6 FPGA device.

  • 103.
    Axelsson, Emil
    et al.
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten.
    Costa, Jonathas
    NYU, NY 10003 USA.
    Silva, Claudio
    NYU, NY 10003 USA.
    Emmart, Carter
    Amer Museum Nat Hist, NY 10024 USA.
    Bock, Alexander
    Linköpings universitet, Institutionen för teknik och naturvetenskap. Linköpings universitet, Tekniska fakulteten.
    Ynnerman, Anders
    Linköpings universitet, Institutionen för teknik och naturvetenskap, Medie- och Informationsteknik. Linköpings universitet, Tekniska fakulteten. Linköpings universitet, Centrum för medicinsk bildvetenskap och visualisering, CMIV.
    Dynamic Scene Graph: Enabling Scaling, Positioning, and Navigation in the Universe2017Inngår i: Computer graphics forum (Print), ISSN 0167-7055, E-ISSN 1467-8659, Vol. 36, nr 3, s. 459-468Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    In this work, we address the challenge of seamlessly visualizing astronomical data exhibiting huge scale differences in distance, size, and resolution. One of the difficulties is accurate, fast, and dynamic positioning and navigation to enable scaling over orders of magnitude, far beyond the precision of floating point arithmetic. To this end we propose a method that utilizes a dynamically assigned frame of reference to provide the highest possible numerical precision for all salient objects in a scene graph. This makes it possible to smoothly navigate and interactively render, for example, surface structures on Mars and the Milky Way simultaneously. Our work is based on an analysis of tracking and quantification of the propagation of precision errors through the computer graphics pipeline using interval arithmetic. Furthermore, we identify sources of precision degradation, leading to incorrect object positions in screen-space and z-fighting. Our proposed method operates without near and far planes while maintaining high depth precision through the use of floating point depth buffers. By providing interoperability with order-independent transparency algorithms, direct volume rendering, and stereoscopy, our approach is well suited for scientific visualization. We provide the mathematical background, a thorough description of the method, and a reference implementation.

  • 104.
    Axelsson, Maria
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    An evaluation of scale and noise sensitivity of fibre orientation estimation in volume images2009Inngår i: Image Analysis and Processing - ICIAP 2009, Berlin: Springer , 2009, s. 975-984Konferansepaper (Fagfellevurdert)
  • 105.
    Axelsson, Maria
    et al.
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Svensson, Stina
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    3D pore structure characterisation of paper2010Inngår i: Pattern Analysis and Applications, ISSN 1433-7541, E-ISSN 1433-755X, Vol. 13, nr 2, s. 159-172Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Pore structure characterisation of paper, using automated image analysis methods, has previously been performed in two-dimensional images. Three dimensional (3D) images have become available and thereby new representations and corresponding measurements are needed for 3D pore structure characterisation. In this article, we present a new pore structure representation, the individual pore-based skeleton, and new quantitative measurements for individual pores in 3D, such as surface area, orientation, anisotropy, and size distributions. We also present measurements for network relations, like tortuosity and connectivity. The data used to illustrate the pore structure representations and corresponding measurements are high resolution X-ray microtomography volume images of a layered duplex board imaged at the European Synchrotron Radiation Facility (ESRF). Quantification of the pore structure is exemplified and the results show that differences in pore structure between the layers in the cardboard can be characterised using the presented methods.

  • 106.
    Axelsson, Maria
    et al.
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Svensson, Stina
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys.
    Borgefors, Gunilla
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys.
    Reduction of Ring Artifacts in High Resolution X-Ray Microtomography Images2006Inngår i: Pattern Recognition: 28th DAGM Symposium, Berlin, Germany, September 2006, Proceedings, 2006, s. 61-70Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Ring artifacts can occur in reconstructed images from X-ray microtomography as full or partial circles centred on the rotation axis. In this paper, a 2D method is proposed that reduces these ring artifacts in the reconstructed images. The method consists of two main parts. First, the artifacts are localised in the image using local orientation estimation of the image structures and filtering to find ring patterns in the orientation information. Second, the map of the located artifacts is used to calculate a correction image using normalised convolution. The method is evaluated on 2D images from volume data of paper fibre imaged at the European Synchrotron Radiation Facility (ESRF) with high resolution X-ray microtomography. The results show that the proposed method reduces the artifacts and restores the pixel values for all types of partial and complete ring artifacts where the signal is not completely saturated.

  • 107.
    Axelsson, Maria
    et al.
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Östlund, Catherine
    Vomhoff, Hannes
    Svensson, Stina
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys.
    Estimation of the pore volume at the interface between paper web and press felt2006Inngår i: Nordic Pulp & Paper Research Journal, ISSN 0283-2631, E-ISSN 2000-0669, Vol. 21, nr 3, s. 395-402Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    A method for determining the water content at the interface between a press felt and a paper web has been developed. The water content was obtained by subtracting the estimated volume of the indented fibre web from the measured felt surface porosity of the press felt. The felt surface porosity was calculated from a topography map that was imaged with a Confocal Laser Scanning Microscope (CLSM) method. Here, the press felt was compressed against a smooth surface using a stress in the range of 0 to 10 MPa. Artefacts in the CLSM images were reduced using an image analysis method. The indentation of paper webs into the measured felt surface pores at different applied pressures was estimated using another image analysis method, simulating a rolling ball, with different radii of curvature for the different pressures and grammages, rolling over the felt surface. The ball radii were determined for a low and a high grammage web using the STFI-Packforsk Dewatering model. The method was evaluated in a case study with four press felts that had batt fibre diameters in a range between 22 and 78 μm. The indentation was calculated for webs with a low (15 g/m2) and a high grammage (105 g/m2), respectively. The evaluation showed that a considerable amount of porespace is available at the interface between the web and the felt. In most cases, the volume of the water-filled pores accounted for approximately 50% of the total surface porosity of the felt. Assuming a complete water saturation of the web/felt interface, approximately 10 g/m2 of water for the finest felt surface up to 40 g/m2 for the coarsest felt surface, could be located at the interface between the press felt and the paper web at a load of 10 MPa. This implies that a considerable amount of water is available for separation rewetting.

  • 108.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Brun, Anders
    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.
    Document Binarization Combining with Graph Cuts and Deep Neural Networks2017Konferansepaper (Annet vitenskapelig)
  • 109.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Brun, Anders
    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.
    Historical document binarization combining semantic labeling and graph cuts2017Inngår i: Image Analysis: Part I, Springer, 2017, s. 386-396Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Most data mining applications on collections of historical documents require binarization of the digitized images as a pre-processing step. Historical documents are often subjected to degradations such as parchment aging, smudges and bleed through from the other side. The text is sometimes printed, but more often handwritten. Mathematical modeling of appearance of the text, background and all kinds of degradations, is challenging. In the current work we try to tackle binarization as pixel classification problem. We first apply semantic segmentation, using fully convolutional neural networks. In order to improve the sharpness of the result, we then apply a graph cut algorithm. The labels from the semantic segmentation are used as approximate estimates of the text and background, with the probability map of background used for pruning the edges in the graph cut. The results obtained show significant improvement over the state of the art approach.

  • 110.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Brun, Anders
    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.
    Semantic Labeling using Convolutional Networks coupled with Graph-Cuts for Document binarization2017Konferansepaper (Annet vitenskapelig)
  • 111.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Brun, Anders
    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.
    Topological clustering guided document binarization2015Rapport (Annet vitenskapelig)
    Abstract [en]

    The current approach for text binarization proposes a clustering algorithm as a preprocessing stage to an energy-based segmentation method. It uses a clustering algorithm to obtain a coarse estimate of the background (BG) and foreground (FG) pixels. These estimates are usedas a prior for the source and sink points of a graph cut implementation, which is used to efficiently find the minimum energy solution of an objective function to separate the BG and FG. The binary image thus obtained is used to refine the edge map that guides the graph cut algorithm. A final binary image is obtained by once again performing the graph cut guided by the refined edges on Laplacian of the image.

  • 112.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Malmberg, Filip
    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.
    Brun, Anders
    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.
    PDNet: Semantic segmentation integrated with a primal-dual network for document binarization2019Inngår i: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 121, s. 52-60Artikkel i tidsskrift (Fagfellevurdert)
    Fulltekst tilgjengelig fra 2020-05-17 16:13
  • 113.
    Ayyalasomayajula, Kalyan Ram
    et al.
    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.
    Nettelblad, Carl
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för beräkningsvetenskap.
    Brun, Anders
    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.
    Feature evaluation for handwritten character recognition with regressive and generative Hidden Markov Models2016Inngår i: Advances in Visual Computing: Part I, Springer, 2016, s. 278-287Konferansepaper (Fagfellevurdert)
  • 114.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Laptev, I.
    Object detection using strongly-supervised deformable part models2012Inngår i: Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I / [ed] Andrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, Cordelia Schmid, Springer, 2012, nr PART 1, s. 836-849Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Deformable part-based models [1, 2] achieve state-of-the-art performance for object detection, but rely on heuristic initialization during training due to the optimization of non-convex cost function. This paper investigates limitations of such an initialization and extends earlier methods using additional supervision. We explore strong supervision in terms of annotated object parts and use it to (i) improve model initialization, (ii) optimize model structure, and (iii) handle partial occlusions. Our method is able to deal with sub-optimal and incomplete annotations of object parts and is shown to benefit from semi-supervised learning setups where part-level annotation is provided for a fraction of positive examples only. Experimental results are reported for the detection of six animal classes in PASCAL VOC 2007 and 2010 datasets. We demonstrate significant improvements in detection performance compared to the LSVM [1] and the Poselet [3] object detectors.

  • 115.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Razavian, Ali Sharif
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Maki, Atsuto
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    From Generic to Specific Deep Representations for Visual Recognition2015Inngår i: Proceedings of CVPR 2015, IEEE conference proceedings, 2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Evidence is mounting that ConvNets are the best representation learning method for recognition. In the common scenario, a ConvNet is trained on a large labeled dataset and the feed-forward units activation, at a certain layer of the network, is used as a generic representation of an input image. Recent studies have shown this form of representation to be astoundingly effective for a wide range of recognition tasks. This paper thoroughly investigates the transferability of such representations w.r.t. several factors. It includes parameters for training the network such as its architecture and parameters of feature extraction. We further show that different visual recognition tasks can be categorically ordered based on their distance from the source task. We then show interesting results indicating a clear correlation between the performance of tasks and their distance from the source task conditioned on proposed factors. Furthermore, by optimizing these factors, we achieve stateof-the-art performances on 16 visual recognition tasks.

  • 116.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sharif Razavian, Ali
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Maki, Atsuto
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlssom, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Factors of Transferability for a Generic ConvNet Representation2016Inngår i: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 38, nr 9, s. 1790-1802, artikkel-id 7328311Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, by optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their similarity to the source task such that a correlation between the performance of tasks and their similarity to the source task w.r.t. the proposed factors is observed.

  • 117.
    Bacciu, Davide
    et al.
    Università di Pisa, Pisa, Italy.
    Di Rocco, Maurizio
    Örebro University, Örebro, Sweden.
    Dragone, Mauro
    Heriot-Watt University, Edinburgh, UK.
    Gallicchio, Claudio
    Università di Pisa, Pisa, Italy.
    Micheli, Alessio
    Università di Pisa, Pisa, Italy.
    Saffiotti, Alessandro
    Örebro universitet, Institutionen för naturvetenskap och teknik.
    An ambient intelligence approach for learning in smart robotic environmentsInngår i: Computational intelligence, ISSN 0824-7935, E-ISSN 1467-8640Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Smart robotic environments combine traditional (ambient) sensing devices and mobile robots. This combination extends the type of applications that can be considered, reduces their complexity, and enhances the individual values of the devices involved by enabling new services that cannot be performed by a single device. To reduce the amount of preparation and preprogramming required for their deployment in real-world applications, it is important to make these systems self-adapting. The solution presented in this paper is based upon a type of compositional adaptation where (possibly multiple) plans of actions are created through planning and involve the activation of pre-existing capabilities. All the devices in the smart environment participate in a pervasive learning infrastructure, which is exploited to recognize which plans of actions are most suited to the current situation. The system is evaluated in experiments run in a real domestic environment, showing its ability to proactively and smoothly adapt to subtle changes in the environment and in the habits and preferences of their user(s), in presence of appropriately defined performance measuring functions.

  • 118.
    Baisero, Andrea
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Pokorny, Florian T.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Kragic, Danica
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Ek, Carl Henrik
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    The Path Kernel2013Inngår i: ICPRAM 2013 - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods, 2013, s. 50-57Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Kernel methods have been used very successfully to classify data in various application domains. Traditionally, kernels have been constructed mainly for vectorial data defined on a specific vector space. Much less work has been addressing the development of kernel functions for non-vectorial data. In this paper, we present a new kernel for encoding sequential data. We present our results comparing the proposed kernel to the state of the art, showing a significant improvement in classification and a much improved robustness and interpretability.

  • 119.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    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. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Sladoje, Natasa
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Single image super-resolution reconstruction in presence of mixed Poisson-Gaussian noise2016Inngår i: 2016 SIXTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), IEEE, 2016Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Single image super-resolution (SR) reconstructionaims to estimate a noise-free and blur-free high resolution imagefrom a single blurred and noisy lower resolution observation.Most existing SR reconstruction methods assume that noise in theimage is white Gaussian. Noise resulting from photon countingdevices, as commonly used in image acquisition, is, however,better modelled with a mixed Poisson-Gaussian distribution. Inthis study we propose a single image SR reconstruction methodbased on energy minimization for images degraded by mixedPoisson-Gaussian noise.We evaluate performance of the proposedmethod on synthetic images, for different levels of blur andnoise, and compare it with recent methods for non-Gaussiannoise. Analysis shows that the appropriate treatment of signaldependentnoise, provided by our proposed method, leads tosignificant improvement in reconstruction performance.

  • 120.
    Bajic, Buda
    et al.
    Univ Novi Sad, Fac Tech Sci, Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sladoje, Natasa
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sparsity promoting super-resolution coverage segmentation by linear unmixing in presence of blur and noise2019Inngår i: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 28, nr 1, artikkel-id 013046Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    We present a segmentation method that estimates the relative coverage of each pixel in a sensed image by each image component. The proposed super-resolution blur-aware model (utilizes a priori knowledge of the image blur) for linear unmixing of image intensities relies on a sparsity promoting approach expressed by two main requirements: (i) minimization of Huberized total variation, providing smooth object boundaries and noise removal, and (ii) minimization of nonedge image fuzziness, responding to an assumption that imaged objects are crisp and that fuzziness is mainly due to the imaging and digitization process. Edge fuzziness due to partial coverage is allowed, enabling subpixel precise feature estimates. The segmentation is formulated as an energy minimization problem and solved by the spectral projected gradient method, utilizing a graduated nonconvexity scheme. Quantitative and qualitative evaluation on synthetic and real multichannel images confirms good performance, particularly relevant when subpixel precision in segmentation and subsequent analysis is a requirement. (C) 2019 SPIE and IS&T

  • 121.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    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. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sladoje, Nataša
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Blind restoration of images degraded with mixed poisson-Gaussian noise with application in transmission electron microscopy2016Inngår i: 2016 Ieee 13Th International Symposium On Biomedical Imaging (ISBI), IEEE, 2016, s. 123-127Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Noise and blur, present in images after acquisition, negatively affect their further analysis. For image enhancement when the Point Spread Function (PSF) is unknown, blind deblurring is suitable, where both the PSF and the original image are simultaneously reconstructed. In many realistic imaging conditions, noise is modelled as a mixture of Poisson (signal-dependent) and Gaussian (signal independent) noise. In this paper we propose a blind deconvolution method for images degraded by such mixed noise. The method is based on regularized energy minimization. We evaluate its performance on synthetic images, for different blur kernels and different levels of noise, and compare with non-blind restoration. We illustrate the performance of the method on Transmission Electron Microscopy images of cilia, used in clinical practice for diagnosis of a particular type of genetic disorders.

  • 122.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    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. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Sladoje, Nataša
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Bildanalys och människa-datorinteraktion. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för visuell information och interaktion. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Restoration of images degraded by signal-dependent noise based on energy minimization: an empirical study2016Inngår i: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 25, nr 4, artikkel-id 043020Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Most energy minimization-based restoration methods are developed for signal-independent Gaussian noise. The assumption of Gaussian noise distribution leads to a quadratic data fidelity term, which is appealing in optimization. When an image is acquired with a photon counting device, it contains signal-dependent Poisson or mixed Poisson–Gaussian noise. We quantify the loss in performance that occurs when a restoration method suited for Gaussian noise is utilized for mixed noise. Signal-dependent noise can be treated by methods based on either classical maximum a posteriori (MAP) probability approach or on a variance stabilization approach (VST). We compare performances of these approaches on a large image material and observe that VST-based methods outperform those based on MAP in both quality of restoration and in computational efficiency. We quantify improvement achieved by utilizing Huber regularization instead of classical total variation regularization. The conclusion from our study is a recommendation to utilize a VST-based approach combined with regularization by Huber potential for restoration of images degraded by blur and signal-dependent noise. This combination provides a robust and flexible method with good performance and high speed.

  • 123.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    A Simple Method to Measure Homogeneity of Fat Distribution in Meat2001Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Fat distribution is an important criterium for meat quality evaluation and

  • 124.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Detection and quantification of foveal avascular zone alterations in diabetic retinopathy2000Inngår i: 1st Int. Workshop on Computer Assisted Fundus Image Analysis (CAFIA), 2000Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this work a computational approach for detecting and quantifying diabetic

  • 125.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Determination of fat content in NMR images of meat2000Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper we present an application to food science of image processing

  • 126.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Determination of fat contents in NMR images of meat: preliminary results2000Inngår i: Symposium on Image Analysis - SSAB 2000, 2000, s. 79-82Konferansepaper (Annet vitenskapelig)
  • 127.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Genetic Snakes for Color Image Segmentation2001Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The world of meat faces a permanent need for new methods of meat quality

  • 128.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    How Do People Choose Meat?2001Inngår i: Swedish Society for Automated Image Analysis Symposium - SSAB 2001,ITN, Campus Norrköping, LinköpingUniversity, 2001, s. 119-122Konferansepaper (Annet vitenskapelig)
  • 129.
    Ballerini, L.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Image Analysis for the Food Industry: Digital Camera Photographs and Nuclear Magnetic Resonance Images2001Inngår i: Electronic Imaging, Vol. 11, nr 2, s. 7-Artikkel i tidsskrift (Fagfellevurdert)
  • 130.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Barone, L.T.
    Bianchetti, M.
    Monforti Ferrario, F.
    Sacca', F.
    Usai, C.
    Cervelli in fuga (Brains on the run - Stories of Italian researchers fled abroad)2001Bok (Annet vitenskapelig)
  • 131.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Bocchi, L.
    A Fractal Approach to Predict Fat Content in Meat Images2001Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Intramuscular fat content in meat influences some important meat quality

  • 132.
    Ballerini. L., Bocchi
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    L.,
    Segmentation of liver images by texture and genetic snakes2002Konferansepaper (Fagfellevurdert)
  • 133.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Bocchi, L.
    Hullberg, A.
    Determination of Pores in Pig Meat Images2002Inngår i: International Conference on Computer Vision and Graphics, Zakopane, Poland, 2002, s. 70-78Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper we present an image processing application for

  • 134.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Borgefors, G.
    Theory and Applications of Image Analysis at the Centre for Image Analysis2001Inngår i: 5th Korea-Germany JointWorkshop on Advanced Medical Image Processing, Seoul, Korea, 2001Konferansepaper (Annet vitenskapelig)
  • 135.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Hullberg, A.
    Determination of holes in pig meat images2002Inngår i: Proceedings SSAB'02 Symposium on Image Analysis, 2002, s. 53-56Konferansepaper (Annet vitenskapelig)
    Abstract [en]

    In this paper we present an image processing application for

  • 136.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Högberg, A.
    How Do People Choose Meat?2001Konferansepaper (Fagfellevurdert)
    Abstract [en]

    In this paper we present a survey carried out to understand the choice of

  • 137.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Högberg, A.
    Borgefors., G.
    Bylund, A.-C.
    Lindgård, A.
    Lundström, K.
    Rakotonirainy, O.
    Soussi, B.
    A Segmentation Technique to Determine Fat Content in NMR Images of Beef Meat2002Inngår i: IEEE Transactions on Nuclear Science, Vol. 49, nr 1, s. 195-199Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    The world of meat faces a permanent need for new methods of meat

  • 138.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Högberg, A.
    Borgefors, G.
    Bylund, A.-C.
    Lindgård, A.
    Lundström, K.
    Rakotonirainy, O.
    Soussi, B.
    Testing MRI and image analysis techniques for fat quantification in meat science2000Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The world of meat faces a permanent need for new methods of meat quality

  • 139.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Högberg, A.
    Lundström, K.
    Borgefors, G.
    Colour Image Analysis Technique for Measuring of Fat in Meat: An Application forthe Meat Industry2001Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Intramuscular fat content in meat influences some important meat quality

  • 140.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Piazza, E.
    A picture of doctoral studies in Italy2001Inngår i: Eurodoc 2001, European Conference of Doctoral Students, Uppsala, Sweden, 2001Konferansepaper (Annet vitenskapelig)
  • 141.
    Ballerini, L.
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Piazza, E.
    The future of Italian doctors2002Inngår i: Eurodoc 2002, European Conference of Doctoral Students, Girona, Spain, 2002Konferansepaper (Annet vitenskapelig)
  • 142. Barekatain, M.
    et al.
    Marti, Miquel
    KTH. Polytechnic University of Catalonia, Spain.
    Shih, H. -F
    Murray, Samuel
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Nakayama, K.
    Matsuo, Y.
    Prendinger, H.
    Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection2017Inngår i: 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, IEEE Computer Society, 2017, Vol. 2017, s. 2153-2160Konferansepaper (Fagfellevurdert)
    Abstract [en]

    Despite significant progress in the development of human action detection datasets and algorithms, no current dataset is representative of real-world aerial view scenarios. We present Okutama-Action, a new video dataset for aerial view concurrent human action detection. It consists of 43 minute-long fully-annotated sequences with 12 action classes. Okutama-Action features many challenges missing in current datasets, including dynamic transition of actions, significant changes in scale and aspect ratio, abrupt camera movement, as well as multi-labeled actors. As a result, our dataset is more challenging than existing ones, and will help push the field forward to enable real-world applications.

  • 143.
    Barkman, Richard Dan William
    Karlstads universitet, Fakulteten för hälsa, natur- och teknikvetenskap (from 2013).
    Object Tracking Achieved by Implementing Predictive Methods with Static Object Detectors Trained on the Single Shot Detector Inception V2 Network2019Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
    Abstract [en]

    In this work, the possibility of realising object tracking by implementing predictive methods with static object detectors is explored. The static object detectors are obtained as models trained on a machine learning algorithm, or in other words, a deep neural network. Specifically, it is the single shot detector inception v2 network that will be used to train such models. Predictive methods will be incorporated to the end of improving the obtained models’ precision, i.e. their performance with respect to accuracy. Namely, Lagrangian mechanics will be employed to derived equations of motion for three different scenarios in which the object is to be tracked. These equations of motion will be implemented as predictive methods by discretising and combining them with four different iterative formulae.

    In ch. 1, the fundamentals of supervised machine learning, neural networks, convolutional neural networks as well as the workings of the single shot detector algorithm, approaches to hyperparameter optimisation and other relevant theory is established. This includes derivations of the relevant equations of motion and the iterative formulae with which they were implemented. In ch. 2, the experimental set-up that was utilised during data collection, and the manner by which the acquired data was used to produce training, validation and test datasets is described. This is followed by a description of how the approach of random search was used to train 64 models on 300×300 datasets, and 32 models on 512×512 datasets. Consecutively, these models are evaluated based on their performance with respect to camera-to-object distance and object velocity. In ch. 3, the trained models were verified to possess multi-scale detection capabilities, as is characteristic of models trained on the single shot detector network. While the former is found to be true irrespective of the resolution-setting of the dataset that the model has been trained on, it is found that the performance with respect to varying object velocity is significantly more consistent for the lower resolution models as they operate at a higher detection rate.

    Ch. 3 continues with that the implemented predictive methods are evaluated. This is done by comparing the resulting deviations when they are let to predict the missing data points from a collected detection pattern, with varying sampling percentages. It is found that the best predictive methods are those that make use of the least amount of previous data points. This followed from that the data upon which evaluations were made contained an unreasonable amount of noise, considering that the iterative formulae implemented do not take noise into account. Moreover, the lower resolution models were found to benefit more than those trained on the higher resolution datasets because of the higher detection frequency they can employ.

    In ch. 4, it is argued that the concept of combining predictive methods with static object detectors to the end of obtaining an object tracker is promising. Moreover, the models obtained on the single shot detector network are concluded to be good candidates for such applications. However, the predictive methods studied in this thesis should be replaced with some method that can account for noise, or be extended to be able to account for it. A profound finding is that the single shot detector inception v2 models trained on a low-resolution dataset were found to outperform those trained on a high-resolution dataset in certain regards due to the higher detection rate possible on lower resolution frames. Namely, in performance with respect to object velocity and in that predictive methods performed better on the low-resolution models.

  • 144.
    Barnada, Marc
    et al.
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Goethe University of Frankfurt, Germany.
    Conrad, Christian
    Goethe University of Frankfurt, Germany.
    Bradler, Henry
    Goethe University of Frankfurt, Germany.
    Ochs, Matthias
    Goethe University of Frankfurt, Germany.
    Mester, Rudolf
    Linköpings universitet, Institutionen för systemteknik, Datorseende. Linköpings universitet, Tekniska fakulteten. Goethe University of Frankfurt, Germany.
    Estimation of Automotive Pitch, Yaw, and Roll using Enhanced Phase Correlation on Multiple Far-field Windows2015Inngår i: 2015 IEEE Intelligent Vehicles Symposium (IV), IEEE , 2015, s. 481-486Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The online-estimation of yaw, pitch, and roll of a moving vehicle is an important ingredient for systems which estimate egomotion, and 3D structure of the environment in a moving vehicle from video information. We present an approach to estimate these angular changes from monocular visual data, based on the fact that the motion of far distant points is not dependent on translation, but only on the current rotation of the camera. The presented approach does not require features (corners, edges,...) to be extracted. It allows to estimate in parallel also the illumination changes from frame to frame, and thus allows to largely stabilize the estimation of image correspondences and motion vectors, which are most often central entities needed for computating scene structure, distances, etc. The method is significantly less complex and much faster than a full egomotion computation from features, such as PTAM [6], but it can be used for providing motion priors and reduce search spaces for more complex methods which perform a complete analysis of egomotion and dynamic 3D structure of the scene in which a vehicle moves.

  • 145.
    Barnden, L
    et al.
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Kwiatek, R
    Lau, Y
    Hutton, B
    Thurfjell, L
    Pile, K
    Rowe, C
    Validation of fully automatic brain SPET to MR co-registration2000Inngår i: EUROPEAN JOURNAL OF NUCLEAR MEDICINE, ISSN 0340-6997, Vol. 27, nr 2, s. 147-154Artikkel i tidsskrift (Fagfellevurdert)
    Abstract [en]

    Fully automatic co-registration of functional to anatomical brain images using information intrinsic to the scans has been validated in a clinical setting for positron emission tomography (PET), but not for single-photon emission tomography (SPET). In thi

  • 146. Baroffio, L.
    et al.
    Cesana, M.
    Redondi, A.
    Tagliasacchi, M.
    Ascenso, J.
    Monteiro, P.
    Eriksson, Emil
    KTH, Skolan för elektro- och systemteknik (EES), Kommunikationsnät.
    Dan, G.
    Fodor, Viktoria
    KTH, Skolan för elektro- och systemteknik (EES), Kommunikationsnät.
    GreenEyes: Networked energy-aware visual analysis2015Inngår i: 2015 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2015, IEEE conference proceedings, 2015Konferansepaper (Fagfellevurdert)
    Abstract [en]

    The GreenEyes project aims at developing a comprehensive set of new methodologies, practical algorithms and protocols, to empower wireless sensor networks with vision capabilities. The key tenet of this research is that most visual analysis tasks can be carried out based on a succinct representation of the image, which entails both global and local features, while it disregards the underlying pixel-level representation. Specifically, GreenEyes will pursue the following goals: i) energy-constrained extraction of visual features; ii) rate-efficiency modelling and coding of visual feature; iii) networking streams of visual features. This will have a significant impact on several scenarios including, e.g., smart cities and environmental monitoring.

  • 147.
    Barrera Tony, Hast Anders, Bengtsson Ewert
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    A fast all-integer ellipse discretization algorithm2003Inngår i: Graphics Programming Methods, 2003, s. 121-131Kapittel i bok, del av antologi (Fagfellevurdert)
  • 148.
    Barrera Tony, Hast Anders, Bengtsson Ewert
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    A fast and simple all-integer parametric line2003Kapittel i bok, del av antologi (Fagfellevurdert)
  • 149. Barrera, Tony
    et al.
    Hast, Anders
    Creative Media Lab, University of Gävle.
    Bengtsson, Ewert
    Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Centrum för bildanalys. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    An alternative model for shading of diffuse light for rough materials2008Inngår i: Game Programming Gems 7 / [ed] Scott Jacobs, Boston: Charles River Media , 2008, 1, s. 373-380Kapittel i bok, del av antologi (Annet vitenskapelig)
  • 150.
    Barrera Tony, Hast Anders, Bengtsson Ewert
    Uppsala universitet, Fakultetsövergripande enheter, Centrum för bildanalys. Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Datoriserad bildanalys.
    Faster Shading by Equal Angle Interpolation of Vectors2004Inngår i: IEEE Transactions on Visualization and Computer Graphics, Vol. 10, nr 2, s. 217-223Artikkel i tidsskrift (Fagfellevurdert)
1234567 101 - 150 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