Digitala Vetenskapliga Arkivet

Change search
Refine search result
1234567 151 - 200 of 3114
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 151.
    Asmussen, Edvin
    Mälardalen University, School of Innovation, Design and Engineering.
    OMNIDIRECTIONAL OBJECT DETECTION AND TRACKING, FOR AN AUTONOMOUS SAILBOAT2023Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    MDU, in collaboration with several other universities, plans to join the World Robotic Sailing Championship (WRSC), where in certain sub-challenges some object detection is necessary. Such as for detecting objects such as boats, buoys, and possibly other items. Utilizing a camera system could significantly aid in these tasks, and in this research, an omnidirectional camera is proposed. This is a camera that offers a wide field of view of 360 degrees and could provide comprehensive information about the boat’s surroundings. However, these images use a spherical camera model, which projects the image on a sphere and, when saved to a 2D format, becomes very distorted. To be able to use state-of-the-art vision algorithms for object detection and tracking, this research proposes to project these images to other formats. As such, four systems using object detection and tracking are made that uses different image representation projected from the spherical images. One system uses spherical images and is used as a baseline, while the three remaining systems use some form of projection. The first is cubemap projection, which projects the spherical image to a cube and unfolds this image on a 2D plane. The two other image representations used perspective projections, which are when the spherical image is projected to small sub-images. The two image representations that used perspective projections had 4 and 8 perspective images. None of the systems ultimately performed very well but did have some advantages and disadvantages.

    Download full text (pdf)
    fulltext
  • 152.
    Aspers, Patrik
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Sociology.
    Fuehrer, Paul
    Stockholm University, Faculty of Social Sciences, Department of Sociology.
    Sverrisson, Árni
    Stockholm University, Faculty of Social Sciences, Department of Sociology.
    Introduktion2004In: Bild och samhälle: visuell analys som vetenskaplig metod / [ed] Patrik Aspers, Paul Fuehrer, Árni Sverrisson, Lund: Studentlitteratur, 2004, p. 9-36Chapter in book (Other academic)
  • 153.
    Assabie Lake, Yaregal
    Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), Halmstad Embedded and Intelligent Systems Research (EIS).
    Multifont recognition System for Ethiopic Script2006Licentiate thesis, comprehensive summary (Other academic)
    Abstract [en]

    In this thesis, we present a general framework for multi-font, multi-size and multi-style Ethiopic character recognition system. We propose structural and syntactic techniques for recognition of Ethiopic characters where the graphically comnplex characters are represented by less complex primitive structures and their spatial interrelationships. For each Ethiopic character, the primitive structures and their spatial interrelationships form a unique set of patterns.

    The interrelationships of primitives are represented by a special tree structure which resembles a binary search tree in the sense that it groups child nodes as left and right, and keeps the spatial position of primitives in orderly manner. For a better computational efficiency, the primitive tree is converted into string pattern using in-order traversal, which generates a base of the alphabet that stores possibly occuring string patterns for each character. The recognition of characters is then achieved by matching the generated patterns with each pattern in a stored knowledge base of characters.

    Structural features are extracted using direction field tensor, which is also used for character segmentation. In general, the recognition system does not need size normalization, thinning or other preprocessing procedures. The only parameter that needs to be adjusted during the recognition process is the size of Gaussian window which should be chosen optimally in relation to font sizes. We also constructed an Ethiopic Document Image Database (EDIDB) from real life documents and the recognition system is tested with respect to variations in font type, size, style, document skewness and document type. Experimental results are reported.

  • 154.
    Assabie, Yaregal
    et al.
    Addis Ababa University, Department of Computer Science, Addis Ababa, Ethiopia .
    Bigun, Josef
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    A Hybrid System for Robust Recognition of Ethiopic Script2007In: Ninth International Conference on Document Analysis and Recognition: proceedings : Curtiba, Paraná, Brazil, September 23-26, 2007 / [ed] IEEE Computer Society, Los Alamitos, Calif.: IEEE Computer Society, 2007, p. 556-560Conference paper (Refereed)
    Abstract [en]

    In real life, documents contain several font types, styles, and sizes. However, many character recognition systems show good results for specific type of documents and fail to produce satisfactory results for others. Over the past decades, various pattern recognition techniques have been applied with the aim to develop recognition systems insensitive to variations in the characteristics of documents. In this paper, we present a robust recognition system for Ethiopic script using a hybrid of classifiers. The complex structures of Ethiopic characters are structurally and syntactically analyzed, and represented as a pattern of simpler graphical units called primitives. The pattern is used for classification of characters using similarity-based matching and neural network classifier. The classification result is further refined by using template matching. A pair of directional filters is used for creating templates and extracting structural features. The recognition system is tested by real life documents and experimental results are reported.

    Download full text (pdf)
    FULLTEXT01
  • 155.
    Astaraki, Mehdi
    et al.
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging. Karolinska Inst, Dept Oncol Pathol, Stockholm, Sweden..
    Yang, Guang
    Royal Brompton Hosp, Cardiovasc Res Ctr, London, England.;Imperial Coll London, Natl Heart & Lung Inst, London, England..
    Zakko, Yousuf
    Karolinska Univ Hosp, Dept Radiol Imaging & Funct, Solna, Sweden..
    Toma-Dasu, Iuliana
    Karolinska Inst, Dept Oncol Pathol, Stockholm, Sweden.;Stockholm Univ, Dept Phys, Stockholm, Sweden..
    Smedby, Örjan
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    Wang, Chunliang
    KTH, School of Engineering Sciences in Chemistry, Biotechnology and Health (CBH), Biomedical Engineering and Health Systems, Medical Imaging.
    A Comparative Study of Radiomics and Deep-Learning Based Methods for Pulmonary Nodule Malignancy Prediction in Low Dose CT Images2021In: Frontiers in Oncology, E-ISSN 2234-943X, Vol. 11, article id 737368Article in journal (Refereed)
    Abstract [en]

    ObjectivesBoth radiomics and deep learning methods have shown great promise in predicting lesion malignancy in various image-based oncology studies. However, it is still unclear which method to choose for a specific clinical problem given the access to the same amount of training data. In this study, we try to compare the performance of a series of carefully selected conventional radiomics methods, end-to-end deep learning models, and deep-feature based radiomics pipelines for pulmonary nodule malignancy prediction on an open database that consists of 1297 manually delineated lung nodules. MethodsConventional radiomics analysis was conducted by extracting standard handcrafted features from target nodule images. Several end-to-end deep classifier networks, including VGG, ResNet, DenseNet, and EfficientNet were employed to identify lung nodule malignancy as well. In addition to the baseline implementations, we also investigated the importance of feature selection and class balancing, as well as separating the features learned in the nodule target region and the background/context region. By pooling the radiomics and deep features together in a hybrid feature set, we investigated the compatibility of these two sets with respect to malignancy prediction. ResultsThe best baseline conventional radiomics model, deep learning model, and deep-feature based radiomics model achieved AUROC values (mean +/- standard deviations) of 0.792 +/- 0.025, 0.801 +/- 0.018, and 0.817 +/- 0.032, respectively through 5-fold cross-validation analyses. However, after trying out several optimization techniques, such as feature selection and data balancing, as well as adding context features, the corresponding best radiomics, end-to-end deep learning, and deep-feature based models achieved AUROC values of 0.921 +/- 0.010, 0.824 +/- 0.021, and 0.936 +/- 0.011, respectively. We achieved the best prediction accuracy from the hybrid feature set (AUROC: 0.938 +/- 0.010). ConclusionThe end-to-end deep-learning model outperforms conventional radiomics out of the box without much fine-tuning. On the other hand, fine-tuning the models lead to significant improvements in the prediction performance where the conventional and deep-feature based radiomics models achieved comparable results. The hybrid radiomics method seems to be the most promising model for lung nodule malignancy prediction in this comparative study.

  • 156. Astruc, Marine
    et al.
    Malm, Patrik
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Kumar, Rajesh
    Bengtsson, Ewert
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Cluster detection and field-of-view quality rating: Applied to automated Pap-smear analysis2013In: Proc. 2nd International Conference on Pattern Recognition Applications and Methods, SciTePress, 2013, p. 355-364Conference paper (Refereed)
    Abstract [en]

    Automated cervical cancer screening systems require high resolution analysis of a large number of epithelial cells, involving complex algorithms, mainly analysing the shape and texture of cell nuclei. This can be a very time consuming process. An initial selection of relevant fields-of-view in low resolution images could limit the number of fields to be further analysed at a high resolution. In particular, the detection of cell clusters is of interest for nuclei segmentation improvement, and for diagnostic purpose, malignant and endometrial cells being more prone to stick together in clusters than other cells. In this paper, we propose methods aiming at evaluating the quality of fields-of-view in bright-field microscope images of cervical cells. The approach consists in the construction of neighbourhood graphs using the nuclei as the set of vertices. Transformations are then applied on such graphs in order to highlight the main structures in the image. The methods result in the delineation of regions with varying cell density and the identification of cell clusters. Clustering methods are evaluated using a dataset of manually delineated clusters and compared to a related work.

    Download full text (pdf)
    fulltext
  • 157.
    Auer, Cornelia
    et al.
    Zuse Institute Berlin, Berlin, Germany.
    Nair, Jaya
    IIIT – Bangalore, Electronics City, Hosur Road, Bangalore, India.
    Zobel, Valentin
    Zuse Institue Berlin, Berlin, Germany.
    Hotz, Ingrid
    Zuse Institue Berlin, Berlin, Germany.
    2D Tensor Field Segmentation2011In: Dagstuhl Follow-Ups, E-ISSN 1868-8977, Vol. 2, p. 17-35Article in journal (Refereed)
    Abstract [en]

    We present a topology-based segmentation as means for visualizing 2D symmetric tensor fields. The segmentation uses directional as well as eigenvalue characteristics of the underlying field to delineate cells of similar (or dissimilar) behavior in the tensor field. A special feature of the resulting cells is that their shape expresses the tensor behavior inside the cells and thus also can be considered as a kind of glyph representation. This allows a qualitative comprehension of important structures of the field. The resulting higher-level abstraction of the field provides valuable analysis. The extraction of the integral topological skeleton using both major and minor eigenvector fields serves as a structural pre-segmentation and renders all directional structures in the field. The resulting curvilinear cells are bounded by tensorlines and already delineate regions of equivalent eigenvector behavior. This pre-segmentation is further adaptively refined to achieve a segmentation reflecting regions of similar eigenvalue and eigenvector characteristics. Cell refinement involves both subdivision and merging of cells achieving a predetermined resolution, accuracy and uniformity of the segmentation. The buildingblocks of the approach can be intuitively customized to meet the demands or different applications. Application to tensor fields from numerical stress simulations demonstrates the effectiveness of our method.

  • 158.
    Augustsson, Louise
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction.
    Study and Analysis of Convolutional Neural Networks for Pedestrian Detection in Autonomous Vehicles2018Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
    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.

    Download full text (pdf)
    fulltext
  • 159.
    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 hardware2011In: Proceedings of the FPL2011 Workshop on Computer Vision on Low-Power Reconfigurable Architectures, 2011, p. 9-10Conference paper (Other academic)
    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.

  • 160.
    Axelsson, Emil
    et al.
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering.
    Costa, Jonathas
    NYU, NY 10003 USA.
    Silva, Claudio
    NYU, NY 10003 USA.
    Emmart, Carter
    Amer Museum Nat Hist, NY 10024 USA.
    Bock, Alexander
    Linköping University, Department of Science and Technology. Linköping University, Faculty of Science & Engineering.
    Ynnerman, Anders
    Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Dynamic Scene Graph: Enabling Scaling, Positioning, and Navigation in the Universe2017In: Computer graphics forum (Print), ISSN 0167-7055, E-ISSN 1467-8659, Vol. 36, no 3, p. 459-468Article in journal (Refereed)
    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.

    Download full text (pdf)
    fulltext
  • 161.
    Axelsson, Maria
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    An evaluation of scale and noise sensitivity of fibre orientation estimation in volume images2009In: Image Analysis and Processing - ICIAP 2009, Berlin: Springer , 2009, p. 975-984Conference paper (Refereed)
  • 162.
    Axelsson, Maria
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Svensson, Stina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    3D pore structure characterisation of paper2010In: Pattern Analysis and Applications, ISSN 1433-7541, E-ISSN 1433-755X, Vol. 13, no 2, p. 159-172Article in journal (Refereed)
    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.

  • 163.
    Axelsson, Maria
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Svensson, Stina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis.
    Borgefors, Gunilla
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis.
    Reduction of Ring Artifacts in High Resolution X-Ray Microtomography Images2006In: Pattern Recognition: 28th DAGM Symposium, Berlin, Germany, September 2006, Proceedings, 2006, p. 61-70Conference paper (Refereed)
    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.

  • 164.
    Axelsson, Maria
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Östlund, Catherine
    Vomhoff, Hannes
    Svensson, Stina
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Centre for Image Analysis.
    Estimation of the pore volume at the interface between paper web and press felt2006In: Nordic Pulp & Paper Research Journal, ISSN 0283-2631, E-ISSN 2000-0669, Vol. 21, no 3, p. 395-402Article in journal (Refereed)
    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.

  • 165.
    Axelsson, Nils
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Skantze, Gabriel
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Modelling Adaptive Presentations in Human-Robot Interaction using Behaviour Trees2019In: 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue: Proceedings of the Conference / [ed] Satoshi Nakamura, Stroudsburg, PA: Association for Computational Linguistics (ACL) , 2019, p. 345-352Conference paper (Refereed)
    Abstract [en]

    In dialogue, speakers continuously adapt their speech to accommodate the listener, based on the feedback they receive. In this paper, we explore the modelling of such behaviours in the context of a robot presenting a painting. A Behaviour Tree is used to organise the behaviour on different levels, and allow the robot to adapt its behaviour in real-time; the tree organises engagement, joint attention, turn-taking, feedback and incremental speech processing. An initial implementation of the model is presented, and the system is evaluated in a user study, where the adaptive robot presenter is compared to a non-adaptive version. The adaptive version is found to be more engaging by the users, although no effects are found on the retention of the presented material.

  • 166.
    Axelsson, Nils
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Skantze, Gabriel
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Speech, Music and Hearing, TMH.
    Using knowledge graphs and behaviour trees for feedback-aware presentation agents2020In: Proceedings of Intelligent Virtual Agents 2020, Association for Computing Machinery (ACM) , 2020Conference paper (Refereed)
    Abstract [en]

    In this paper, we address the problem of how an interactive agent (such as a robot) can present information to an audience and adaptthe presentation according to the feedback it receives. We extend a previous behaviour tree-based model to generate the presentation from a knowledge graph (Wikidata), which allows the agent to handle feedback incrementally, and adapt accordingly. Our main contribution is using this knowledge graph not just for generating the system’s dialogue, but also as the structure through which short-term user modelling happens. In an experiment using simulated users and third-party observers, we show that referring expressions generated by the system are rated more highly when they adapt to the type of feedback given by the user, and when they are based on previously grounded information as opposed to new information.

  • 167.
    Ayele, Workneh Y.
    et al.
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Akram, Imran
    Stockholm University, Faculty of Social Sciences, Department of Computer and Systems Sciences.
    Identifying Emerging Trends and Temporal Patterns About Self-driving Cars in Scientific Literature2020In: Advances in Computer Vision: Proceedings of the 2019 Computer Vision Conference (CVC) / [ed] Kohei Arai, Supriya Kapoor, Springer, 2020, Vol. 2, p. 355-372Conference paper (Refereed)
    Abstract [en]

    Self-driving is an emerging technology which has several benefits such as improved quality of life, crash reductions, and fuel efficiency. There are however concerns regarding the utilization of self-driving technology such as affordability, safety, control, and liabilities. There is an increased effort in research centers, academia, and the industry to advance every sphere of science and technology yet it is getting harder to find innovative ideas. However, there is untapped potential to analyze the increasing research results using visual analytics, scientometrics, and machine learning. In this paper, we used scientific literature database, Scopus to collect relevant dataset and applied a visual analytics tool, CiteSpace, to conduct co-citation clustering, term burst detection, time series analysis to identify emerging trends, and analysis of global impacts and collaboration. Also, we applied unsupervised topic modeling, Latent Dirichlet Allocation (LDA) to identify hidden topics for gaining more insight about topics regarding self-driving technology. The results show emerging trends relevant to self-driving technology and global and regional collaboration between countries. Moreover, the result form the LDA shows that standard topic modeling reveals hidden topics without trend information. We believe that the result of this study indicates key technological areas and research domains which are the hot spots of the technology. For the future, we plan to include dynamic topic modeling to identify trends.

    Download full text (pdf)
    fulltext
  • 168.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Document Binarization Combining with Graph Cuts and Deep Neural Networks2017Conference paper (Other academic)
    Download full text (pdf)
    fulltext
  • 169.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Historical document binarization combining semantic labeling and graph cuts2017In: Image Analysis: Part I, Springer, 2017, p. 386-396Conference paper (Refereed)
    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.

    Download full text (pdf)
    fulltext
  • 170.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Semantic Labeling using Convolutional Networks coupled with Graph-Cuts for Document binarization2017Conference paper (Other academic)
    Download full text (pdf)
    fulltext
  • 171.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Topological clustering guided document binarization2015Report (Other academic)
    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.

    Download full text (pdf)
    fulltext
  • 172.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Malmberg, Filip
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    PDNet: Semantic segmentation integrated with a primal-dual network for document binarization2019In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 121, p. 52-60Article in journal (Refereed)
    Download full text (pdf)
    fulltext
  • 173.
    Ayyalasomayajula, Kalyan Ram
    et al.
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Nettelblad, Carl
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Scientific Computing.
    Brun, Anders
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction.
    Feature evaluation for handwritten character recognition with regressive and generative Hidden Markov Models2016In: Advances in Visual Computing: Part I, Springer, 2016, p. 278-287Conference paper (Refereed)
    Download full text (pdf)
    fulltext
  • 174.
    Azizpour, Hossein
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Laptev, I.
    Object detection using strongly-supervised deformable part models2012In: 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, no PART 1, p. 836-849Conference paper (Refereed)
    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.

  • 175.
    Azizpour, Hossein
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Razavian, Ali Sharif
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Sullivan, Josephine
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Maki, Atsuto
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlsson, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    From Generic to Specific Deep Representations for Visual Recognition2015In: Proceedings of CVPR 2015, IEEE conference proceedings, 2015Conference paper (Refereed)
    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.

    Download full text (pdf)
    fulltext
  • 176.
    Azizpour, Hossein
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Sharif Razavian, Ali
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Sullivan, Josephine
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Maki, Atsuto
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Carlssom, Stefan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Factors of Transferability for a Generic ConvNet Representation2016In: IEEE Transactions on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 38, no 9, p. 1790-1802, article id 7328311Article in journal (Refereed)
    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.

  • 177.
    Baaz, Hampus
    Mälardalen University, School of Innovation, Design and Engineering.
    NAVIGATION AND PLANNED MOVEMENT OF AN UNMANNED BICYCLE2020Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
    Abstract [en]

    A conventional bicycle is a stable system given adequate forward velocity. However, the velocity region of stability is limited and depends on the geometric parameters of the bicycle. An autonomous bicycle is just not about maintaining the balance but also controlling where the bicycle is heading. Following paths has been accomplished with bicycles and motorcycles in simulation for a while. Car-like vehicles have followed paths in the real world but few bicycles or motorcycles have done so. The goal of this work is to follow a planned path using a physical bicycle without overcoming the dynamic limitations of the bicycle. Using an iterative design process, controllers for direction and position are developed and improved. Kinematic models are also compared in their ability to simulate the bicycle movement and how controllers in simulation translate to outdoors driving. The result shows that the bicycle can follow a turning path on a residential road without human interaction and that some simulation behaviours do not translate to the real world.

    Download full text (pdf)
    fulltext
  • 178.
    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 University, School of Science and Technology.
    An ambient intelligence approach for learning in smart robotic environments2019In: Computational intelligence, ISSN 0824-7935, E-ISSN 1467-8640, Vol. 35, no 4, p. 1060-1087Article in journal (Refereed)
    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.

  • 179.
    Baerveldt, Albert-Jan
    Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Intelligent systems (IS-lab).
    A vision system for object verification and localization based on local features2001In: Robotics and Autonomous Systems, ISSN 0921-8890, E-ISSN 1872-793X, Vol. 34, no 2-3, p. 83-92Article in journal (Refereed)
    Abstract [en]

    An object verification and localization system should answer the question whether an expected object is present in an image or not, i.e. verification, and if present where it is located. Such a system would be very useful for mobile robots, e.g. for landmark recognition or for the fulfilment of certain tasks. In this paper, we present an object verification and localization system specially adapted to the needs of mobile robots. The object model is based on a collection of local features derived from a small neighbourhood around automatically detected interest points. The learned representation of the object is then matched with the image under consideration. The tests, based on 81 images, showed a very satisfying tolerance to scale changes of up to 50%, to viewpoint variations of 20, to occlusion of up to 80% and to major background changes as well as to local and global illumination changes. The tests also showed that the verification capabilities are very good and that similar objects did not trigger any false verification.

  • 180.
    Bai, Yifan
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Kanellakis, Christoforos
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Nikolakopoulos, George
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    SA-reCBS: Multi-robot task assignment with integrated reactive path generation2023In: 22nd IFAC World Congress: Yokohama, Japan, July 9-14, 2023, Proceedings / [ed] Hideaki Ishii; Yoshio Ebihara; Jun-ichi Imura; Masaki Yamakita, Elsevier, 2023, p. 7032-7037Conference paper (Refereed)
    Abstract [en]

    In this paper, we study the multi-robot task assignment and path-finding problem (MRTAPF), where a number of robots are required to visit all given tasks while avoiding collisions with each other. We propose a novel two-layer algorithm SA-reCBS that cascades the simulated annealing algorithm and conflict-based search to solve this problem. Compared to other approaches in the field of MRTAPF, the advantage of SA-reCBS is that without requiring a pre-bundle of tasks to groups with the same number of groups as the number of robots, it enables a part of robots needed to visit all tasks in collision-free paths. We test the algorithm in various simulation instances and compare it with state-of-the-art algorithms. The result shows that SA-reCBS has a better performance with a higher success rate, less computational time, and better objective values.

    Download full text (pdf)
    fulltext
  • 181.
    Bai, Yifan
    et al.
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Lindqvist, Björn
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Karlsson, Samuel
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Kanellakis, Christoforos
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Nikolakopoulos, George
    Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
    Multi-Robot Task Allocation Framework with Integrated Risk-Aware 3D Path Planning2022In: 2022 30th Mediterranean Conference on Control and Automation (MED), IEEE, 2022, p. 481-486Conference paper (Refereed)
    Abstract [en]

    This article presents an overall system architecture for multi-robot coordination in a known environment. The proposed framework is structured around a task allocation mechanism that performs unlabeled multi-robot path assignment informed by 3D path planning, while using a nonlinear model predictive control(NMPC) for each unmanned aerial vehicle (UAV) to navigate along its assigned path. More specifically, at first a risk aware 3D path planner D∗+ is applied to calculate cost between each UAV agent and each target point. Then the cost matrix related to the computed trajectories to each goal is fed into the Hungarian Algorithm that solves the assignment problem and generates the minimum total cost. NMPC is implemented to control the UAV while satisfying path following and input constraints. We evaluate the proposed architecture in Gazebo simulation framework and the result indicates UAVs are capable of approaching their assigned target whilst avoiding collisions.

    Download full text (pdf)
    fulltext
  • 182.
    Baisero, Andrea
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Pokorny, Florian T.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Kragic, Danica
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Ek, Carl Henrik
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    The Path Kernel2013In: ICPRAM 2013 - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods, 2013, p. 50-57Conference paper (Refereed)
    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.

  • 183.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Sladoje, Natasa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Single image super-resolution reconstruction in presence of mixed Poisson-Gaussian noise2016In: 2016 SIXTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), IEEE, 2016Conference paper (Refereed)
    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.

  • 184.
    Bajic, Buda
    et al.
    Univ Novi Sad, Fac Tech Sci, Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sladoje, Natasa
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sparsity promoting super-resolution coverage segmentation by linear unmixing in presence of blur and noise2019In: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 28, no 1, article id 013046Article in journal (Refereed)
    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

  • 185.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Serbian Acad Arts & Sci, Math Inst, Belgrade, Serbia.
    Blind restoration of images degraded with mixed poisson-Gaussian noise with application in transmission electron microscopy2016In: 2016 Ieee 13Th International Symposium On Biomedical Imaging (ISBI), IEEE, 2016, p. 123-127Conference paper (Refereed)
    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.

  • 186.
    Bajic, Buda
    et al.
    Faculty of Technical Sciences, University of Novi Sad, Serbia.
    Lindblad, Joakim
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Sladoje, Nataša
    Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. Mathematical Institute, Serbian Academy of Sciences and Arts, Belgrade, Serbia.
    Restoration of images degraded by signal-dependent noise based on energy minimization: an empirical study2016In: Journal of Electronic Imaging (JEI), ISSN 1017-9909, E-ISSN 1560-229X, Vol. 25, no 4, article id 043020Article in journal (Refereed)
    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.

    Download full text (pdf)
    fulltext
  • 187.
    Baldassarre, Federico
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Structured Representations for Explainable Deep Learning2023Doctoral thesis, comprehensive summary (Other academic)
    Abstract [en]

    Deep learning has revolutionized scientific research and is being used to take decisions in increasingly complex scenarios. With growing power comes a growing demand for transparency and interpretability. The field of Explainable AI aims to provide explanations for the predictions of AI systems. The state of the art of AI explainability, however, is far from satisfactory. For example, in Computer Vision, the most prominent post-hoc explanation methods produce pixel-wise heatmaps over the input domain, which are meant to visualize the importance of individual pixels of an image or video. We argue that such dense attribution maps are poorly interpretable to non-expert users because of the domain in which explanations are formed - we may recognize shapes in a heatmap but they are just blobs of pixels. In fact, the input domain is closer to the raw data of digital cameras than to the interpretable structures that humans use to communicate, e.g. objects or concepts. In this thesis, we propose to move beyond dense feature attributions by adopting structured internal representations as a more interpretable explanation domain. Conceptually, our approach splits a Deep Learning model in two: the perception step that takes as input dense representations and the reasoning step that learns to perform the task at hand. At the interface between the two are structured representations that correspond to well-defined objects, entities, and concepts. These representations serve as the interpretable domain for explaining the predictions of the model, allowing us to move towards more meaningful and informative explanations. The proposed approach introduces several challenges, such as how to obtain structured representations, how to use them for downstream tasks, and how to evaluate the resulting explanations. The works included in this thesis address these questions, validating the approach and providing concrete contributions to the field. For the perception step, we investigate how to obtain structured representations from dense representations, whether by manually designing them using domain knowledge or by learning them from data without supervision. For the reasoning step, we investigate how to use structured representations for downstream tasks, from Biology to Computer Vision, and how to evaluate the learned representations. For the explanation step, we investigate how to explain the predictions of models that operate in a structured domain, and how to evaluate the resulting explanations. Overall, we hope that this work inspires further research in Explainable AI and helps bridge the gap between high-performing Deep Learning models and the need for transparency and interpretability in real-world applications.

    Download full text (pdf)
    kappa
  • 188.
    Baldassarre, Federico
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Azizpour, Hossein
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Explainability Techniques for Graph Convolutional Networks2019Conference paper (Refereed)
    Abstract [en]

    Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Our study sets the ground for future development as well as application to real-world problems.

    Download full text (pdf)
    fulltext
  • 189.
    Baldassarre, Federico
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Azizpour, Hossein
    Towards Self-Supervised Learning of Global and Object-Centric Representations2022Conference paper (Refereed)
    Abstract [en]

    Self-supervision allows learning meaningful representations of natural images, which usually contain one central object. How well does it transfer to multi-entity scenes? We discuss key aspects of learning structured object-centric representations with self-supervision and validate our insights through several experiments on the CLEVR dataset. Regarding the architecture, we confirm the importance of competition for attention-based object discovery, where each image patch is exclusively attended by one object. For training, we show that contrastive losses equipped with matching can be applied directly in a latent space, avoiding pixel-based reconstruction. However, such an optimization objective is sensitive to false negatives (recurring objects) and false positives (matching errors). Careful consideration is thus required around data augmentation and negative sample selection.

  • 190.
    Baldassarre, Federico
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    Debard, Quentin
    Pontiveros, Gonzalo Fiz
    Wijaya, Tri Kurniawan
    Quantitative Metrics for Evaluating Explanations of Video DeepFake Detectors2022Conference paper (Refereed)
    Abstract [en]

    The proliferation of DeepFake technology is a rising challenge in today’s society, owing to more powerful and accessible generation methods. To counter this, the research community has developed detectors of ever-increasing accuracy. However, the ability to explain the decisions of such models to users lags behind performance and is considered an accessory in large-scale benchmarks, despite being a crucial requirement for the correct deployment of automated tools for moderation and censorship. We attribute the issue to the reliance on qualitative comparisons and the lack of established metrics. We describe a simple set of metrics to evaluate the visual quality and informativeness of explanations of video DeepFake classifiers from a human-centric perspective. With these metrics, we compare common approaches to improve explanation quality and discuss their effect on both classification and explanation performance on the recent DFDC and DFD datasets.

  • 191.
    Baldassarre, Federico
    et al.
    KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
    El-Nouby, Alaaeldin
    Jégou, Hervé
    Variable Rate Allocation for Vector-Quantized Autoencoders2023In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Institute of Electrical and Electronics Engineers (IEEE) , 2023Conference paper (Refereed)
    Abstract [en]

    Vector-quantized autoencoders have recently gained interest in image compression, generation and self-supervised learning. However, as a neural compression method, they lack the possibility to allocate a variable number of bits to each image location, e.g. according to the semantic content or local saliency. In this paper, we address this limitation in a simple yet effective way. We adopt a product quantizer (PQ) that produces a set of discrete codes for each image patch rather than a single index. This PQ-autoencoder is trained end-to-end with a structured dropout that selectively masks a variable number of codes at each location. These mechanisms force the decoder to reconstruct the original image based on partial information and allow us to control the local rate. The resulting model can compress images on a wide range of operating points of the rate-distortion curve and can be paired with any external method for saliency estimation to control the compression rate at a local level. We demonstrate the effectiveness of our approach on the popular Kodak and ImageNet datasets by measuring both distortion and perceptual quality metrics.

  • 192.
    Balkan, Büsra Atamer
    et al.
    Middle East Technical University, Turkey.
    Nicolaidis, Andreas
    RISE Research Institutes of Sweden, Built Environment, Energy and Resources.
    Odoemena, Kelechi
    Ag-AIM Solutions, Nigeria.
    Lamb, Robert
    Foundation for Inclusion, US.
    Tiongco, Monique Ann
    Ateneo de Manila University, Philippines.
    Gupta, Stueti
    BlueKei Solutions, India.
    Peteru, Arpitha
    Foundation for Inclusion, US.
    Menendez, Hector Manuel
    South Dakota State University, US.
    Understanding the Impact of COVID-19 on Agriculture and Food Supply Chains: System Dynamics Modeling for the Resilience of Smallholder Farmers2022In: International Journal on Food System Dynamics, E-ISSN 1869-6945, Vol. 12, no 3, p. 255-270Article in journal (Refereed)
    Abstract [en]

    COVID-19 has caused severe agriculture and food supply chain disruptions, significantly affecting smallholder farmers who supply most of the world’s food, specifically their changes in vulnerability, resilience, and food loss and waste. Therefore, the objective of this study was to understand the complex causal and feedback relationships for this system by developing a dynamic hypothesis and causal loop diagrams utilizing the System Dynamics methodology. Results provide a roadmap for dialogue and a framework for case-specific model development and help to guide policy decisions for smallholder farmers’ survival during health crises. 

  • 193.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    A Simple Method to Measure Homogeneity of Fat Distribution in Meat2001Conference paper (Refereed)
    Abstract [en]

    Fat distribution is an important criterium for meat quality evaluation and

  • 194.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Detection and quantification of foveal avascular zone alterations in diabetic retinopathy2000In: 1st Int. Workshop on Computer Assisted Fundus Image Analysis (CAFIA), 2000Conference paper (Refereed)
    Abstract [en]

    In this work a computational approach for detecting and quantifying diabetic

  • 195.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Determination of fat content in NMR images of meat2000Conference paper (Refereed)
    Abstract [en]

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

  • 196.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Determination of fat contents in NMR images of meat: preliminary results2000In: Symposium on Image Analysis - SSAB 2000, 2000, p. 79-82Conference paper (Other scientific)
  • 197.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Genetic Snakes for Color Image Segmentation2001Conference paper (Refereed)
    Abstract [en]

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

  • 198.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    How Do People Choose Meat?2001In: Swedish Society for Automated Image Analysis Symposium - SSAB 2001,ITN, Campus Norrköping, LinköpingUniversity, 2001, p. 119-122Conference paper (Other scientific)
  • 199.
    Ballerini, L.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    Image Analysis for the Food Industry: Digital Camera Photographs and Nuclear Magnetic Resonance Images2001In: Electronic Imaging, Vol. 11, no 2, p. 7-Article in journal (Refereed)
  • 200.
    Ballerini, L.
    et al.
    Uppsala University, Interfaculty Units, Centre for Image Analysis. Teknisk-naturvetenskapliga vetenskapsområdet, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis.
    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)2001Book (Other scientific)
1234567 151 - 200 of 3114
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf