toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Sudeep Katakol; Basem Elbarashy; Luis Herranz; Joost van de Weijer; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Distributed Learning and Inference with Compressed Images Type Journal Article
  Year 2020 Publication IEEE Transactions on Image Processing Abbreviated Journal TIP  
  Volume 30 Issue Pages 3069 - 3083  
  Keywords  
  Abstract arXiv:2004.10497
Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.
 
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) ISBN Medium  
  Area Expedition Conference  
  Notes LAMP; ADAS; 600.120; 600.118 Approved no  
  Call Number Admin @ si @ KEH2020 Serial 3543  
Permanent link to this record
 

 
Author Jaume Amores edit   pdf
doi  openurl
  Title Multiple Instance Classification: review, taxonomy and comparative study Type Journal Article
  Year 2013 Publication Artificial Intelligence Abbreviated Journal AI  
  Volume 201 Issue Pages 81-105  
  Keywords Multi-instance learning; Codebook; Bag-of-Words  
  Abstract Multiple Instance Learning (MIL) has become an important topic in the pattern recognition community, and many solutions to this problemhave been proposed until now. Despite this fact, there is a lack of comparative studies that shed light into the characteristics and behavior of the different methods. In this work we provide such an analysis focused on the classification task (i.e.,leaving out other learning tasks such as regression). In order to perform our study, we implemented
fourteen methods grouped into three different families. We analyze the performance of the approaches across a variety of well-known databases, and we also study their behavior in synthetic scenarios in order to highlight their characteristics. As a result of this analysis, we conclude that methods that extract global bag-level information show a clearly superior performance in general. In this sense, the analysis permits us to understand why some types of methods are more successful than others, and it permits us to establish guidelines in the design of new MIL
methods.
 
  Address  
  Corporate Author Thesis  
  Publisher Elsevier Science Publishers Ltd. Essex, UK Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0004-3702 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 601.042; 600.057 Approved no  
  Call Number Admin @ si @ Amo2013 Serial 2273  
Permanent link to this record
 

 
Author David Geronimo; Joan Serrat; Antonio Lopez; Ramon Baldrich edit   pdf
doi  openurl
  Title Traffic sign recognition for computer vision project-based learning Type Journal Article
  Year 2013 Publication IEEE Transactions on Education Abbreviated Journal T-EDUC  
  Volume 56 Issue 3 Pages 364-371  
  Keywords traffic signs  
  Abstract This paper presents a graduate course project on computer vision. The aim of the project is to detect and recognize traffic signs in video sequences recorded by an on-board vehicle camera. This is a demanding problem, given that traffic sign recognition is one of the most challenging problems for driving assistance systems. Equally, it is motivating for the students given that it is a real-life problem. Furthermore, it gives them the opportunity to appreciate the difficulty of real-world vision problems and to assess the extent to which this problem can be solved by modern computer vision and pattern classification techniques taught in the classroom. The learning objectives of the course are introduced, as are the constraints imposed on its design, such as the diversity of students' background and the amount of time they and their instructors dedicate to the course. The paper also describes the course contents, schedule, and how the project-based learning approach is applied. The outcomes of the course are discussed, including both the students' marks and their personal feedback.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0018-9359 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; CIC Approved no  
  Call Number Admin @ si @ GSL2013; ADAS @ adas @ Serial 2160  
Permanent link to this record
 

 
Author Debora Gil; Aura Hernandez-Sabate; Mireia Brunat;Steven Jansen; Jordi Martinez-Vilalta edit   pdf
doi  openurl
  Title Structure-preserving smoothing of biomedical images Type Journal Article
  Year 2011 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 44 Issue 9 Pages 1842-1851  
  Keywords Non-linear smoothing; Differential geometry; Anatomical structures; segmentation; Cardiac magnetic resonance; Computerized tomography  
  Abstract Smoothing of biomedical images should preserve gray-level transitions between adjacent tissues, while restoring contours consistent with anatomical structures. Anisotropic diffusion operators are based on image appearance discontinuities (either local or contextual) and might fail at weak inter-tissue transitions. Meanwhile, the output of block-wise and morphological operations is prone to present a block structure due to the shape and size of the considered pixel neighborhood. In this contribution, we use differential geometry concepts to define a diffusion operator that restricts to image consistent level-sets. In this manner, the final state is a non-uniform intensity image presenting homogeneous inter-tissue transitions along anatomical structures, while smoothing intra-structure texture. Experiments on different types of medical images (magnetic resonance, computerized tomography) illustrate its benefit on a further process (such as segmentation) of images.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes IAM; ADAS Approved no  
  Call Number IAM @ iam @ GHB2011 Serial 1526  
Permanent link to this record
 

 
Author Oscar Argudo; Marc Comino; Antonio Chica; Carlos Andujar; Felipe Lumbreras edit  url
openurl 
  Title Segmentation of aerial images for plausible detail synthesis Type Journal Article
  Year 2018 Publication Computers & Graphics Abbreviated Journal CG  
  Volume 71 Issue Pages 23-34  
  Keywords Terrain editing; Detail synthesis; Vegetation synthesis; Terrain rendering; Image segmentation  
  Abstract The visual enrichment of digital terrain models with plausible synthetic detail requires the segmentation of aerial images into a suitable collection of categories. In this paper we present a complete pipeline for segmenting high-resolution aerial images into a user-defined set of categories distinguishing e.g. terrain, sand, snow, water, and different types of vegetation. This segmentation-for-synthesis problem implies that per-pixel categories must be established according to the algorithms chosen for rendering the synthetic detail. This precludes the definition of a universal set of labels and hinders the construction of large training sets. Since artists might choose to add new categories on the fly, the whole pipeline must be robust against unbalanced datasets, and fast on both training and inference. Under these constraints, we analyze the contribution of common per-pixel descriptors, and compare the performance of state-of-the-art supervised learning algorithms. We report the findings of two user studies. The first one was conducted to analyze human accuracy when manually labeling aerial images. The second user study compares detailed terrains built using different segmentation strategies, including official land cover maps. These studies demonstrate that our approach can be used to turn digital elevation models into fully-featured, detailed terrains with minimal authoring efforts.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0097-8493 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.086; 600.118 Approved no  
  Call Number Admin @ si @ ACC2018 Serial 3147  
Permanent link to this record
 

 
Author Jiaolong Xu; Sebastian Ramos; David Vazquez; Antonio Lopez edit   pdf
doi  openurl
  Title Domain Adaptation of Deformable Part-Based Models Type Journal Article
  Year 2014 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 36 Issue 12 Pages 2367-2380  
  Keywords Domain Adaptation; Pedestrian Detection  
  Abstract The accuracy of object classifiers can significantly drop when the training data (source domain) and the application scenario (target domain) have inherent differences. Therefore, adapting the classifiers to the scenario in which they must operate is of paramount importance. We present novel domain adaptation (DA) methods for object detection. As proof of concept, we focus on adapting the state-of-the-art deformable part-based model (DPM) for pedestrian detection. We introduce an adaptive structural SVM (A-SSVM) that adapts a pre-learned classifier between different domains. By taking into account the inherent structure in feature space (e.g., the parts in a DPM), we propose a structure-aware A-SSVM (SA-SSVM). Neither A-SSVM nor SA-SSVM needs to revisit the source-domain training data to perform the adaptation. Rather, a low number of target-domain training examples (e.g., pedestrians) are used. To address the scenario where there are no target-domain annotated samples, we propose a self-adaptive DPM based on a self-paced learning (SPL) strategy and a Gaussian Process Regression (GPR). Two types of adaptation tasks are assessed: from both synthetic pedestrians and general persons (PASCAL VOC) to pedestrians imaged from an on-board camera. Results show that our proposals avoid accuracy drops as high as 15 points when comparing adapted and non-adapted detectors.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0162-8828 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.057; 600.054; 601.217; 600.076 Approved no  
  Call Number ADAS @ adas @ XRV2014b Serial 2436  
Permanent link to this record
 

 
Author David Geronimo; Antonio Lopez; Angel Sappa; Thorsten Graf edit   pdf
url  doi
openurl 
  Title Survey on Pedestrian Detection for Advanced Driver Assistance Systems Type Journal Article
  Year 2010 Publication IEEE Transaction on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 32 Issue 7 Pages 1239–1258  
  Keywords ADAS, pedestrian detection, on-board vision, survey  
  Abstract Advanced driver assistance systems (ADASs), and particularly pedestrian protection systems (PPSs), have become an active research area aimed at improving traffic safety. The major challenge of PPSs is the development of reliable on-board pedestrian detection systems. Due to the varying appearance of pedestrians (e.g., different clothes, changing size, aspect ratio, and dynamic shape) and the unstructured environment, it is very difficult to cope with the demanded robustness of this kind of system. Two problems arising in this research area are the lack of public benchmarks and the difficulty in reproducing many of the proposed methods, which makes it difficult to compare the approaches. As a result, surveying the literature by enumerating the proposals one-after-another is not the most useful way to provide a comparative point of view. Accordingly, we present a more convenient strategy to survey the different approaches. We divide the problem of detecting pedestrians from images into different processing steps, each with attached responsibilities. Then, the different proposed methods are analyzed and classified with respect to each processing stage, favoring a comparative viewpoint. Finally, discussion of the important topics is presented, putting special emphasis on the future needs and challenges.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0162-8828 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ GLS2010 Serial 1340  
Permanent link to this record
 

 
Author David Vazquez; Javier Marin; Antonio Lopez; Daniel Ponsa; David Geronimo edit   pdf
doi  openurl
  Title Virtual and Real World Adaptation for Pedestrian Detection Type Journal Article
  Year 2014 Publication IEEE Transactions on Pattern Analysis and Machine Intelligence Abbreviated Journal TPAMI  
  Volume 36 Issue 4 Pages 797-809  
  Keywords Domain Adaptation; Pedestrian Detection  
  Abstract Pedestrian detection is of paramount interest for many applications. Most promising detectors rely on discriminatively learnt classifiers, i.e., trained with annotated samples. However, the annotation step is a human intensive and subjective task worth to be minimized. By using virtual worlds we can automatically obtain precise and rich annotations. Thus, we face the question: can a pedestrian appearance model learnt in realistic virtual worlds work successfully for pedestrian detection in realworld images?. Conducted experiments show that virtual-world based training can provide excellent testing accuracy in real world, but it can also suffer the dataset shift problem as real-world based training does. Accordingly, we have designed a domain adaptation framework, V-AYLA, in which we have tested different techniques to collect a few pedestrian samples from the target domain (real world) and combine them with the many examples of the source domain (virtual world) in order to train a domain adapted pedestrian classifier that will operate in the target domain. V-AYLA reports the same detection accuracy than when training with many human-provided pedestrian annotations and testing with real-world images of the same domain. To the best of our knowledge, this is the first work demonstrating adaptation of virtual and real worlds for developing an object detector.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0162-8828 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.057; 600.054; 600.076 Approved no  
  Call Number ADAS @ adas @ VML2014 Serial 2275  
Permanent link to this record
 

 
Author Fadi Dornaika; Angel Sappa edit  doi
openurl 
  Title Instantaneous 3D motion from image derivatives using the Least Trimmed Square Regression Type Journal Article
  Year 2009 Publication Pattern Recognition Letters Abbreviated Journal PRL  
  Volume 30 Issue 5 Pages 535–543  
  Keywords  
  Abstract This paper presents a new technique to the instantaneous 3D motion estimation. The main contributions are as follows. First, we show that the 3D camera or scene velocity can be retrieved from image derivatives only assuming that the scene contains a dominant plane. Second, we propose a new robust algorithm that simultaneously provides the Least Trimmed Square solution and the percentage of inliers-the non-contaminated data. Experiments on both synthetic and real image sequences demonstrated the effectiveness of the developed method. Those experiments show that the new robust approach can outperform classical robust schemes.  
  Address  
  Corporate Author Thesis  
  Publisher Elsevier Science Inc. Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0167-8655 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ DoS2009a Serial 1115  
Permanent link to this record
 

 
Author Jaume Amores edit   pdf
doi  openurl
  Title MILDE: multiple instance learning by discriminative embedding Type Journal Article
  Year 2015 Publication Knowledge and Information Systems Abbreviated Journal KAIS  
  Volume 42 Issue 2 Pages 381-407  
  Keywords Multi-instance learning; Codebook; Bag of words  
  Abstract While the objective of the standard supervised learning problem is to classify feature vectors, in the multiple instance learning problem, the objective is to classify bags, where each bag contains multiple feature vectors. This represents a generalization of the standard problem, and this generalization becomes necessary in many real applications such as drug activity prediction, content-based image retrieval, and others. While the existing paradigms are based on learning the discriminant information either at the instance level or at the bag level, we propose to incorporate both levels of information. This is done by defining a discriminative embedding of the original space based on the responses of cluster-adapted instance classifiers. Results clearly show the advantage of the proposed method over the state of the art, where we tested the performance through a variety of well-known databases that come from real problems, and we also included an analysis of the performance using synthetically generated data.  
  Address  
  Corporate Author Thesis  
  Publisher Springer London Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN (up) 0219-1377 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 601.042; 600.057; 600.076 Approved no  
  Call Number Admin @ si @ Amo2015 Serial 2383  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: