toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author (down) Daniel Marczak; Grzegorz Rypesc; Sebastian Cygert; Tomasz Trzcinski; Bartłomiej Twardowski edit   pdf
url  openurl
  Title Generalized Continual Category Discovery Type Miscellaneous
  Year 2023 Publication arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Most of Continual Learning (CL) methods push the limit of supervised learning settings, where an agent is expected to learn new labeled tasks and not forget previous knowledge. However, these settings are not well aligned with real-life scenarios, where a learning agent has access to a vast amount of unlabeled data encompassing both novel (entirely unlabeled) classes and examples from known classes. Drawing inspiration from Generalized Category Discovery (GCD), we introduce a novel framework that relaxes this assumption. Precisely, in any task, we allow for the existence of novel and known classes, and one must use continual version of unsupervised learning methods to discover them. We call this setting Generalized Continual Category Discovery (GCCD). It unifies CL and GCD, bridging the gap between synthetic benchmarks and real-life scenarios. With a series of experiments, we present that existing methods fail to accumulate knowledge from subsequent tasks in which unlabeled samples of novel classes are present. In light of these limitations, we propose a method that incorporates both supervised and unsupervised signals and mitigates the forgetting through the use of centroid adaptation. Our method surpasses strong CL methods adopted for GCD techniques and presents a superior representation learning performance.  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes LAMP Approved no  
  Call Number Admin @ si @ MRC2023 Serial 3985  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Lukas Schneider; P. Cebrian; A. Espinosa; David Vazquez; Antonio Lopez; Uwe Franke; Marc Pollefeys; Juan Carlos Moure edit   pdf
url  openurl
  Title Slanted Stixels: A way to represent steep streets Type Journal Article
  Year 2019 Publication International Journal of Computer Vision Abbreviated Journal IJCV  
  Volume 127 Issue Pages 1643–1658  
  Keywords  
  Abstract This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced in order to significantly reduce the computational complexity of the Stixel algorithm, and then achieve real-time computation capabilities. The idea is to first perform an over-segmentation of the image, discarding the unlikely Stixel cuts, and apply the algorithm only on the remaining Stixel cuts. This work presents a novel over-segmentation strategy based on a fully convolutional network, which outperforms an approach based on using local extrema of the disparity map. We evaluate the proposed methods in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.118; 600.124 Approved no  
  Call Number Admin @ si @ HSC2019 Serial 3304  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Lukas Schneider; Antonio Espinosa; David Vazquez; Antonio Lopez; Uwe Franke; Marc Pollefeys; Juan C. Moure edit   pdf
openurl 
  Title Slanted Stixels: Representing San Francisco's Steepest Streets} Type Conference Article
  Year 2017 Publication 28th British Machine Vision Conference Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract In this work we present a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced that uses an extremely efficient over-segmentation. In doing so, the computational complexity of the Stixel inference algorithm is reduced significantly, achieving real-time computation capabilities with only a slight drop in accuracy. We evaluate the proposed approach in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.  
  Address London; uk; September 2017  
  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 ISBN Medium  
  Area Expedition Conference BMVC  
  Notes ADAS; 600.118 Approved no  
  Call Number ADAS @ adas @ HSE2017a Serial 2945  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Juan Carlos Moure; Toni Espinosa; Alejandro Chacon; David Vazquez; Antonio Lopez edit   pdf
openurl 
  Title Real-time 3D Reconstruction for Autonomous Driving via Semi-Global Matching Type Conference Article
  Year 2016 Publication GPU Technology Conference Abbreviated Journal  
  Volume Issue Pages  
  Keywords Stereo; Autonomous Driving; GPU; 3d reconstruction  
  Abstract Robust and dense computation of depth information from stereo-camera systems is a computationally demanding requirement for real-time autonomous driving. Semi-Global Matching (SGM) [1] approximates heavy-computation global algorithms results but with lower computational complexity, therefore it is a good candidate for a real-time implementation. SGM minimizes energy along several 1D paths across the image. The aim of this work is to provide a real-time system producing reliable results on energy-efficient hardware. Our design runs on a NVIDIA Titan X GPU at 104.62 FPS and on a NVIDIA Drive PX at 6.7 FPS, promising for real-time platforms  
  Address Silicon Valley; San Francisco; USA; April 2016  
  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 ISBN Medium  
  Area Expedition Conference GTC  
  Notes ADAS; 600.085; 600.082; 600.076 Approved no  
  Call Number ADAS @ adas @ HME2016 Serial 2738  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan Carlos Moure edit   pdf
url  doi
openurl 
  Title GPU-accelerated real-time stixel computation Type Conference Article
  Year 2017 Publication IEEE Winter Conference on Applications of Computer Vision Abbreviated Journal  
  Volume Issue Pages 1054-1062  
  Keywords Autonomous Driving; GPU; Stixel  
  Abstract The Stixel World is a medium-level, compact representation of road scenes that abstracts millions of disparity pixels into hundreds or thousands of stixels. The goal of this work is to implement and evaluate a complete multi-stixel estimation pipeline on an embedded, energyefficient, GPU-accelerated device. This work presents a full GPU-accelerated implementation of stixel estimation that produces reliable results at 26 frames per second (real-time) on the Tegra X1 for disparity images of 1024×440 pixels and stixel widths of 5 pixels, and achieves more than 400 frames per second on a high-end Titan X GPU card.  
  Address Santa Rosa; CA; USA; March 2017  
  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 ISBN Medium  
  Area Expedition Conference WACV  
  Notes ADAS; 600.118 Approved no  
  Call Number ADAS @ adas @ HEV2017b Serial 2812  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan Carlos Moure edit   pdf
openurl 
  Title Embedded Real-time Stixel Computation Type Conference Article
  Year 2017 Publication GPU Technology Conference Abbreviated Journal  
  Volume Issue Pages  
  Keywords GPU; CUDA; Stixels; Autonomous Driving  
  Abstract  
  Address Silicon Valley; USA; May 2017  
  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 ISBN Medium  
  Area Expedition Conference GTC  
  Notes ADAS; 600.118 Approved no  
  Call Number ADAS @ adas @ HEV2017a Serial 2879  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Antonio Espinosa; David Vazquez; Antonio Lopez; Juan C. Moure edit   pdf
url  doi
openurl 
  Title 3D Perception With Slanted Stixels on GPU Type Journal Article
  Year 2021 Publication IEEE Transactions on Parallel and Distributed Systems Abbreviated Journal TPDS  
  Volume 32 Issue 10 Pages 2434-2447  
  Keywords Daniel Hernandez-Juarez; Antonio Espinosa; David Vazquez; Antonio M. Lopez; Juan C. Moure  
  Abstract This article presents a GPU-accelerated software design of the recently proposed model of Slanted Stixels, which represents the geometric and semantic information of a scene in a compact and accurate way. We reformulate the measurement depth model to reduce the computational complexity of the algorithm, relying on the confidence of the depth estimation and the identification of invalid values to handle outliers. The proposed massively parallel scheme and data layout for the irregular computation pattern that corresponds to a Dynamic Programming paradigm is described and carefully analyzed in performance terms. Performance is shown to scale gracefully on current generation embedded GPUs. We assess the proposed methods in terms of semantic and geometric accuracy as well as run-time performance on three publicly available benchmark datasets. Our approach achieves real-time performance with high accuracy for 2048 × 1024 image sizes and 4 × 4 Stixel resolution on the low-power embedded GPU of an NVIDIA Tegra Xavier.  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ HEV2021 Serial 3561  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Alejandro Chacon; Antonio Espinosa; David Vazquez; Juan Carlos Moure; Antonio Lopez edit   pdf
url  openurl
  Title Embedded real-time stereo estimation via Semi-Global Matching on the GPU Type Conference Article
  Year 2016 Publication 16th International Conference on Computational Science Abbreviated Journal  
  Volume 80 Issue Pages 143-153  
  Keywords Autonomous Driving; Stereo; CUDA; 3d reconstruction  
  Abstract Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 41 frames per second for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.  
  Address San Diego; CA; USA; June 2016  
  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 ISBN Medium  
  Area Expedition Conference ICCS  
  Notes ADAS; 600.085; 600.082; 600.076 Approved no  
  Call Number ADAS @ adas @ HCE2016a Serial 2740  
Permanent link to this record
 

 
Author (down) Daniel Hernandez; Alejandro Chacon; Antonio Espinosa; David Vazquez; Juan Carlos Moure; Antonio Lopez edit   pdf
openurl 
  Title Stereo Matching using SGM on the GPU Type Report
  Year 2016 Publication Programming and Tuning Massively Parallel Systems Abbreviated Journal PUMPS  
  Volume Issue Pages  
  Keywords CUDA; Stereo; Autonomous Vehicle  
  Abstract Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy efficient GPU devices. Our design runs on a Tegra X1 at 42 frames per second (fps) for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.  
  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 ISBN Medium  
  Area Expedition Conference PUMPS  
  Notes ADAS; 600.085; 600.087; 600.076 Approved no  
  Call Number ADAS @ adas @ HCE2016b Serial 2776  
Permanent link to this record
 

 
Author (down) Dani Rowe; Jordi Gonzalez; Marco Pedersoli; Juan J. Villanueva edit   pdf
doi  openurl
  Title On Tracking Inside Groups Type Journal Article
  Year 2010 Publication Machine Vision and Applications Abbreviated Journal MVA  
  Volume 21 Issue 2 Pages 113–127  
  Keywords  
  Abstract This work develops a new architecture for multiple-target tracking in unconstrained dynamic scenes, which consists of a detection level which feeds a two-stage tracking system. A remarkable characteristic of the system is its ability to track several targets while they group and split, without using 3D information. Thus, special attention is given to the feature-selection and appearance-computation modules, and to those modules involved in tracking through groups. The system aims to work as a stand-alone application in complex and dynamic scenarios. No a-priori knowledge about either the scene or the targets, based on a previous training period, is used. Hence, the scenario is completely unknown beforehand. Successful tracking has been demonstrated in well-known databases of both indoor and outdoor scenarios. Accurate and robust localisations have been yielded during long-term target merging and occlusions.  
  Address  
  Corporate Author Thesis  
  Publisher Springer-Verlag Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 0932-8092 ISBN Medium  
  Area Expedition Conference  
  Notes ISE Approved no  
  Call Number ISE @ ise @ RGP2010 Serial 1158  
Permanent link to this record
 

 
Author (down) Dani Rowe; Jordi Gonzalez; Ivan Huerta; Juan J. Villanueva edit  openurl
  Title On Reasoning over Tracking Events Type Conference Article
  Year 2007 Publication 15th Scandinavian Conference on Image Analysis Abbreviated Journal  
  Volume 4522 Issue Pages 502–511  
  Keywords  
  Abstract  
  Address Aalborg (Denmark)  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference SCIA´07  
  Notes ISE Approved no  
  Call Number ISE @ ise @ RGH2007 Serial 784  
Permanent link to this record
 

 
Author (down) Dani Rowe; Ivan Huerta; Jordi Gonzalez; Juan J. Villanueva edit  openurl
  Title Robust Multiple-People Tracking Using Colour-Based Particle Filters Type Book Chapter
  Year 2007 Publication 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA 2007), J. Marti et al. (Eds.) LNCS 4477:113–120 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Girona (Spain)  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number ISE @ ise @ RHG2007 Serial 782  
Permanent link to this record
 

 
Author (down) Dani Rowe; Ignasi Rius; Jordi Gonzalez; Xavier Roca; Juan J. Villanueva edit  url
openurl 
  Title Probabilistic Image-Based Tracking: Improving Particle Filtering Type Book Chapter
  Year 2005 Publication Pattern Recognition and Image Analysis (IbPRIA 2005), LNCS 3522: 85–92 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Estoril (Portugal)  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes ISE Approved no  
  Call Number ISE @ ise @ RRG2005a Serial 545  
Permanent link to this record
 

 
Author (down) Dani Rowe; Ignasi Rius; Jordi Gonzalez; Juan J. Villanueva edit  openurl
  Title Robust Particle Filtering for Object Tracking Type Miscellaneous
  Year 2005 Publication 13th International Conference on Image Analysis and Processing (ICIAP’2005), LNCS 3617: 1158–1165, ISBN 3–540–28869–4 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Cagliary (Italy)  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number ISE @ ise @ RRG2005e Serial 577  
Permanent link to this record
 

 
Author (down) Dani Rowe; Ignasi Rius; Jordi Gonzalez; Juan J. Villanueva edit  openurl
  Title Improving Tracking by Handling Occlusions Type Miscellaneous
  Year 2005 Publication 3rd International Conference on Advances in Pattern Recognition (ICAPR’2005), Pattern Recognition and Image Analysis, LNCS 3687: 146–154, ISBN 978–3–540–28833–6 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Bath (United Kingdom)  
  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 ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number ISE @ ise @ RRG2005d Serial 619  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: