toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Idoia Ruiz; Joan Serrat edit   pdf
url  doi
openurl 
  Title Rank-based ordinal classification Type Conference Article
  Year 2020 Publication 25th International Conference on Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 8069-8076  
  Keywords  
  Abstract Differently from the regular classification task, in ordinal classification there is an order in the classes. As a consequence not all classification errors matter the same: a predicted class close to the groundtruth one is better than predicting a farther away class. To account for this, most previous works employ loss functions based on the absolute difference between the predicted and groundtruth class labels. We argue that there are many cases in ordinal classification where label values are arbitrary (for instance 1. . . C, being C the number of classes) and thus such loss functions may not be the best choice. We instead propose a network architecture that produces not a single class prediction but an ordered vector, or ranking, of all the possible classes from most to least likely. This is thanks to a loss function that compares groundtruth and predicted rankings of these class labels, not the labels themselves. Another advantage of this new formulation is that we can enforce consistency in the predictions, namely, predicted rankings come from some unimodal vector of scores with mode at the groundtruth class. We compare with the state of the art ordinal classification methods, showing
that ours attains equal or better performance, as measured by common ordinal classification metrics, on three benchmark datasets. Furthermore, it is also suitable for a new task on image aesthetics assessment, i.e. most voted score prediction. Finally, we also apply it to building damage assessment from satellite images, providing an analysis of its performance depending on the degree of imbalance of the dataset.
 
  Address Virtual; January 2021  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language (up) Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICPR  
  Notes ADAS; 600.118; 600.124 Approved no  
  Call Number Admin @ si @ RuS2020 Serial 3549  
Permanent link to this record
 

 
Author Gemma Rotger; Francesc Moreno-Noguer; Felipe Lumbreras; Antonio Agudo edit  doi
openurl 
  Title Single view facial hair 3D reconstruction Type Conference Article
  Year 2019 Publication 9th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal  
  Volume 11867 Issue Pages 423-436  
  Keywords 3D Vision; Shape Reconstruction; Facial Hair Modeling  
  Abstract n this work, we introduce a novel energy-based framework that addresses the challenging problem of 3D reconstruction of facial hair from a single RGB image. To this end, we identify hair pixels over the image via texture analysis and then determine individual hair fibers that are modeled by means of a parametric hair model based on 3D helixes. We propose to minimize an energy composed of several terms, in order to adapt the hair parameters that better fit the image detections. The final hairs respond to the resulting fibers after a post-processing step where we encourage further realism. The resulting approach generates realistic facial hair fibers from solely an RGB image without assuming any training data nor user interaction. We provide an experimental evaluation on real-world pictures where several facial hair styles and image conditions are observed, showing consistent results and establishing a comparison with respect to competing approaches.  
  Address Madrid; July 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language (up) Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IbPRIA  
  Notes ADAS; 600.086; 600.130; 600.122 Approved no  
  Call Number Admin @ si @ Serial 3707  
Permanent link to this record
 

 
Author Yi Xiao; Felipe Codevilla; Diego Porres; Antonio Lopez edit  url
openurl 
  Title Scaling Vision-Based End-to-End Autonomous Driving with Multi-View Attention Learning Type Conference Article
  Year 2023 Publication International Conference on Intelligent Robots and Systems Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract On end-to-end driving, human driving demonstrations are used to train perception-based driving models by imitation learning. This process is supervised on vehicle signals (e.g., steering angle, acceleration) but does not require extra costly supervision (human labeling of sensor data). As a representative of such vision-based end-to-end driving models, CILRS is commonly used as a baseline to compare with new driving models. So far, some latest models achieve better performance than CILRS by using expensive sensor suites and/or by using large amounts of human-labeled data for training. Given the difference in performance, one may think that it is not worth pursuing vision-based pure end-to-end driving. However, we argue that this approach still has great value and potential considering cost and maintenance. In this paper, we present CIL++, which improves on CILRS by both processing higher-resolution images using a human-inspired HFOV as an inductive bias and incorporating a proper attention mechanism. CIL++ achieves competitive performance compared to models which are more costly to develop. We propose to replace CILRS with CIL++ as a strong vision-based pure end-to-end driving baseline supervised by only vehicle signals and trained by conditional imitation learning.  
  Address Detroit; USA; October 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language (up) Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference IROS  
  Notes ADAS Approved no  
  Call Number Admin @ si @ XCP2023 Serial 3930  
Permanent link to this record
 

 
Author Muhammad Anwer Rao; David Vazquez; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Opponent Colors for Human Detection Type Conference Article
  Year 2011 Publication 5th Iberian Conference on Pattern Recognition and Image Analysis Abbreviated Journal  
  Volume 6669 Issue Pages 363-370  
  Keywords Pedestrian Detection; Color; Part Based Models  
  Abstract Human detection is a key component in fields such as advanced driving assistance and video surveillance. However, even detecting non-occluded standing humans remains a challenge of intensive research. Finding good features to build human models for further detection is probably one of the most important issues to face. Currently, shape, texture and motion features have deserve extensive attention in the literature. However, color-based features, which are important in other domains (e.g., image categorization), have received much less attention. In fact, the use of RGB color space has become a kind of choice by default. The focus has been put in developing first and second order features on top of RGB space (e.g., HOG and co-occurrence matrices, resp.). In this paper we evaluate the opponent colors (OPP) space as a biologically inspired alternative for human detection. In particular, by feeding OPP space in the baseline framework of Dalal et al. for human detection (based on RGB, HOG and linear SVM), we will obtain better detection performance than by using RGB space. This is a relevant result since, up to the best of our knowledge, OPP space has not been previously used for human detection. This suggests that in the future it could be worth to compute co-occurrence matrices, self-similarity features, etc., also on top of OPP space, i.e., as we have done with HOG in this paper.  
  Address Las Palmas de Gran Canaria. Spain  
  Corporate Author Thesis  
  Publisher Springer Place of Publication Berlin Heidelberg Editor J. Vitria; J.M. Sanches; M. Hernandez  
  Language (up) English Summary Language English Original Title Opponent Colors for Human Detection  
  Series Editor Series Title Lecture Notes on Computer Science Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-21256-7 Medium  
  Area Expedition Conference IbPRIA  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ RVL2011a Serial 1666  
Permanent link to this record
 

 
Author Javier Marin; David Vazquez; David Geronimo; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Learning Appearance in Virtual Scenarios for Pedestrian Detection Type Conference Article
  Year 2010 Publication 23rd IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal  
  Volume Issue Pages 137–144  
  Keywords Pedestrian Detection; Domain Adaptation  
  Abstract Detecting pedestrians in images is a key functionality to avoid vehicle-to-pedestrian collisions. The most promising detectors rely on appearance-based pedestrian classifiers trained with labelled samples. This paper addresses the following question: can a pedestrian appearance model learnt in virtual scenarios work successfully for pedestrian detection in real images? (Fig. 1). Our experiments suggest a positive answer, which is a new and relevant conclusion for research in pedestrian detection. More specifically, we record training sequences in virtual scenarios and then appearance-based pedestrian classifiers are learnt using HOG and linear SVM. We test such classifiers in a publicly available dataset provided by Daimler AG for pedestrian detection benchmarking. This dataset contains real world images acquired from a moving car. The obtained result is compared with the one given by a classifier learnt using samples coming from real images. The comparison reveals that, although virtual samples were not specially selected, both virtual and real based training give rise to classifiers of similar performance.  
  Address San Francisco; CA; USA; June 2010  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language (up) English Summary Language English Original Title Learning Appearance in Virtual Scenarios for Pedestrian Detection  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1063-6919 ISBN 978-1-4244-6984-0 Medium  
  Area Expedition Conference CVPR  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ MVG2010 Serial 1304  
Permanent link to this record
 

 
Author Muhammad Anwer Rao; David Vazquez; Antonio Lopez edit   pdf
doi  isbn
openurl 
  Title Color Contribution to Part-Based Person Detection in Different Types of Scenarios Type Conference Article
  Year 2011 Publication 14th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 6855 Issue II Pages 463-470  
  Keywords Pedestrian Detection; Color  
  Abstract Camera-based person detection is of paramount interest due to its potential applications. The task is diffcult because the great variety of backgrounds (scenarios, illumination) in which persons are present, as well as their intra-class variability (pose, clothe, occlusion). In fact, the class person is one of the included in the popular PASCAL visual object classes (VOC) challenge. A breakthrough for this challenge, regarding person detection, is due to Felzenszwalb et al. These authors proposed a part-based detector that relies on histograms of oriented gradients (HOG) and latent support vector machines (LatSVM) to learn a model of the whole human body and its constitutive parts, as well as their relative position. Since the approach of Felzenszwalb et al. appeared new variants have been proposed, usually giving rise to more complex models. In this paper, we focus on an issue that has not attracted suficient interest up to now. In particular, we refer to the fact that HOG is usually computed from RGB color space, but other possibilities exist and deserve the corresponding investigation. In this paper we challenge RGB space with the opponent color space (OPP), which is inspired in the human vision system.We will compute the HOG on top of OPP, then we train and test the part-based human classifer by Felzenszwalb et al. using PASCAL VOC challenge protocols and person database. Our experiments demonstrate that OPP outperforms RGB. We also investigate possible differences among types of scenarios: indoor, urban and countryside. Interestingly, our experiments suggest that the beneficts of OPP with respect to RGB mainly come for indoor and countryside scenarios, those in which the human visual system was designed by evolution.  
  Address Seville, Spain  
  Corporate Author Thesis  
  Publisher Springer Place of Publication Berlin Heidelberg Editor P. Real, D. Diaz, H. Molina, A. Berciano, W. Kropatsch  
  Language (up) English Summary Language english Original Title Color Contribution to Part-Based Person Detection in Different Types of Scenarios  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0302-9743 ISBN 978-3-642-23677-8 Medium  
  Area Expedition Conference CAIP  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ RVL2011b Serial 1665  
Permanent link to this record
 

 
Author Patricia Marquez; Debora Gil; Aura Hernandez-Sabate edit   pdf
url  doi
openurl 
  Title A Confidence Measure for Assessing Optical Flow Accuracy in the Absence of Ground Truth Type Conference Article
  Year 2011 Publication IEEE International Conference on Computer Vision – Workshops Abbreviated Journal  
  Volume Issue Pages 2042-2049  
  Keywords IEEE International Conference on Computer Vision – Workshops  
  Abstract Optical flow is a valuable tool for motion analysis in autonomous navigation systems. A reliable application requires determining the accuracy of the computed optical flow. This is a main challenge given the absence of ground truth in real world sequences. This paper introduces a measure of optical flow accuracy for Lucas-Kanade based flows in terms of the numerical stability of the data-term. We call this measure optical flow condition number. A statistical analysis over ground-truth data show a good statistical correlation between the condition number and optical flow error. Experiments on driving sequences illustrate its potential for autonomous navigation systems.  
  Address  
  Corporate Author Thesis  
  Publisher IEEE Place of Publication Barcelona (Spain) Editor  
  Language (up) English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCVW  
  Notes IAM; ADAS Approved no  
  Call Number IAM @ iam @ MGH2011 Serial 1682  
Permanent link to this record
 

 
Author David Vazquez; Antonio Lopez; Daniel Ponsa; Javier Marin edit   pdf
doi  isbn
openurl 
  Title Virtual Worlds and Active Learning for Human Detection Type Conference Article
  Year 2011 Publication 13th International Conference on Multimodal Interaction Abbreviated Journal  
  Volume Issue Pages 393-400  
  Keywords Pedestrian Detection; Human detection; Virtual; Domain Adaptation; Active Learning  
  Abstract Image based human detection is of paramount interest due to its potential applications in fields such as advanced driving assistance, surveillance and media analysis. However, even detecting non-occluded standing humans remains a challenge of intensive research. The most promising human detectors rely on classifiers developed in the discriminative paradigm, i.e., trained with labelled samples. However, labeling is a manual intensive step, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, some authors have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of rendered images, i.e., using realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera, or similar ones. Accordingly, in this paper we address the challenge of using a virtual world for gathering (while playing a videogame) a large amount of automatically labelled samples (virtual humans and background) and then training a classifier that performs equal, in real-world images, than the one obtained by equally training from manually labelled real-world samples. For doing that, we cast the problem as one of domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we propose a non-standard active learning technique. Therefore, ultimately our human model is learnt by the combination of virtual and real world labelled samples (Fig. 1), which has not been done before. We present quantitative results showing that this approach is valid.  
  Address Alicante, Spain  
  Corporate Author Thesis  
  Publisher ACM DL Place of Publication New York, NY, USA, USA Editor  
  Language (up) English Summary Language English Original Title Virtual Worlds and Active Learning for Human Detection  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-1-4503-0641-6 Medium  
  Area Expedition Conference ICMI  
  Notes ADAS Approved yes  
  Call Number ADAS @ adas @ VLP2011a Serial 1683  
Permanent link to this record
 

 
Author David Vazquez; Antonio Lopez; Daniel Ponsa; Javier Marin edit   pdf
openurl 
  Title Cool world: domain adaptation of virtual and real worlds for human detection using active learning Type Conference Article
  Year 2011 Publication NIPS Domain Adaptation Workshop: Theory and Application Abbreviated Journal NIPS-DA  
  Volume Issue Pages  
  Keywords Pedestrian Detection; Virtual; Domain Adaptation; Active Learning  
  Abstract Image based human detection is of paramount interest for different applications. The most promising human detectors rely on discriminatively learnt classifiers, i.e., trained with labelled samples. However, labelling is a manual intensive task, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, in Marin et al. we have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera and the same type of scenario. Accordingly, in Vazquez et al. we cast the problem as one of supervised domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we use an active learning technique. Thus, ultimately our human model is learnt by the combination of virtual- and real-world labelled samples which, to the best of our knowledge, was not done before. Here, we term such combined space cool world. In this extended abstract we summarize our proposal, and include quantitative results from Vazquez et al. showing its validity.  
  Address Granada, Spain  
  Corporate Author Thesis  
  Publisher Place of Publication Granada, Spain Editor  
  Language (up) English Summary Language English Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference DA-NIPS  
  Notes ADAS Approved no  
  Call Number ADAS @ adas @ VLP2011b Serial 1756  
Permanent link to this record
 

 
Author Yainuvis Socarras; Sebastian Ramos; David Vazquez; Antonio Lopez; Theo Gevers edit   pdf
openurl 
  Title Adapting Pedestrian Detection from Synthetic to Far Infrared Images Type Conference Article
  Year 2013 Publication ICCV Workshop on Visual Domain Adaptation and Dataset Bias Abbreviated Journal  
  Volume Issue Pages  
  Keywords Domain Adaptation; Far Infrared; Pedestrian Detection  
  Abstract We present different techniques to adapt a pedestrian classifier trained with synthetic images and the corresponding automatically generated annotations to operate with far infrared (FIR) images. The information contained in this kind of images allow us to develop a robust pedestrian detector invariant to extreme illumination changes.  
  Address Sydney; Australia; December 2013  
  Corporate Author Thesis  
  Publisher Place of Publication Sydney, Australy Editor  
  Language (up) English Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCVW-VisDA  
  Notes ADAS; 600.054; 600.055; 600.057; 601.217;ISE Approved no  
  Call Number ADAS @ adas @ SRV2013 Serial 2334  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: