Records |
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Jordi Vitria |
Title |
Mobile monitoring system using an agent-oriented approach |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceedings of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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;OR;MV |
Approved |
no |
Call Number |
ADAS @ adas @ DaV1999 |
Serial |
21 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Joan Serrat; Antonio Lopez |
Title |
On-board image-based vehicle detection and tracking |
Type |
Journal Article |
Year |
2011 |
Publication |
Transactions of the Institute of Measurement and Control |
Abbreviated Journal |
TIM |
Volume |
33 |
Issue |
7 |
Pages |
783-805 |
Keywords |
vehicle detection |
Abstract |
In this paper we present a computer vision system for daytime vehicle detection and localization, an essential step in the development of several types of advanced driver assistance systems. It has a reduced processing time and high accuracy thanks to the combination of vehicle detection with lane-markings estimation and temporal tracking of both vehicles and lane markings. Concerning vehicle detection, our main contribution is a frame scanning process that inspects images according to the geometry of image formation, and with an Adaboost-based detector that is robust to the variability in the different vehicle types (car, van, truck) and lighting conditions. In addition, we propose a new method to estimate the most likely three-dimensional locations of vehicles on the road ahead. With regards to the lane-markings estimation component, we have two main contributions. First, we employ a different image feature to the other commonly used edges: we use ridges, which are better suited to this problem. Second, we adapt RANSAC, a generic robust estimation method, to fit a parametric model of a pair of lane markings to the image features. We qualitatively assess our vehicle detection system in sequences captured on several road types and under very different lighting conditions. The processed videos are available on a web page associated with this paper. A quantitative evaluation of the system has shown quite accurate results (a low number of false positives and negatives) at a reasonable computation time. |
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 |
Approved |
no |
Call Number |
ADAS @ adas @ PSL2011 |
Serial |
1413 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez; Joan Serrat; Felipe Lumbreras; T. Graf |
Title |
Multiple Vehicle 3D Tracking Using an Unscented Kalman Filter |
Type |
Miscellaneous |
Year |
2005 |
Publication |
Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, 1108–1113, ISBN:0–7803–9216–7 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
vehicle detection |
Abstract |
|
Address |
Vienna (Austria) |
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 |
Approved |
no |
Call Number |
ADAS @ adas @ PLS2005 |
Serial |
615 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez; Felipe Lumbreras; Joan Serrat; T. Graf |
Title |
3D Vehicle Sensor based on Monocular Vision |
Type |
Miscellaneous |
Year |
2005 |
Publication |
Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, 1096–1101, ISBN:0–7803–9216–7 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Vienna (Austria) |
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 |
Approved |
no |
Call Number |
ADAS @ adas @ PLL2005 |
Serial |
614 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez |
Title |
Vehicle Trajectory Estimation based on Monocular Vision |
Type |
Conference Article |
Year |
2007 |
Publication |
3rd Iberian Conference on Pattern Recognition and Image Analysis, LNCS 4477 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
587-594 |
Keywords |
vehicle detection |
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 |
ADAS |
Approved |
no |
Call Number |
ADAS @ adas @ PoL2007a |
Serial |
785 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez |
Title |
Feature Selection Based on a New Formulation of the Minimal-Redundancy-Maximal-Relevance Criterion |
Type |
Conference Article |
Year |
2007 |
Publication |
3rd Iberian Conference on Pattern Recognition and Image Analysis, LNCS 4477 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
47-54 |
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 |
ADAS |
Approved |
no |
Call Number |
ADAS @ adas @ PoL2007b |
Serial |
787 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez |
Title |
Cascade of Classifiers for Vehicle Detection |
Type |
Conference Article |
Year |
2007 |
Publication |
Advanced Concepts for Intelligent Vision Systems, LNCS 4678, volume 1, pp. 980–989 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
vehicle detection |
Abstract |
|
Address |
Delft (Netherlands) |
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 |
Approved |
no |
Call Number |
ADAS @ adas @ PoL2007c |
Serial |
935 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez |
Title |
Variance reduction techniques in particle-based visual contour Tracking |
Type |
Journal Article |
Year |
2009 |
Publication |
Pattern Recognition |
Abbreviated Journal |
PR |
Volume |
42 |
Issue |
11 |
Pages |
2372–2391 |
Keywords |
Contour tracking; Active shape models; Kalman filter; Particle filter; Importance sampling; Unscented particle filter; Rao-Blackwellization; Partitioned sampling |
Abstract |
This paper presents a comparative study of three different strategies to improve the performance of particle filters, in the context of visual contour tracking: the unscented particle filter, the Rao-Blackwellized particle filter, and the partitioned sampling technique. The tracking problem analyzed is the joint estimation of the global and local transformation of the outline of a given target, represented following the active shape model approach. The main contributions of the paper are the novel adaptations of the considered techniques on this generic problem, and the quantitative assessment of their performance in extensive experimental work done. |
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 |
Approved |
no |
Call Number |
ADAS @ adas @ PoL2009a |
Serial |
1168 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; Antonio Lopez |
Title |
Seguimiento Visual de Contornos Computerizado |
Type |
Miscellaneous |
Year |
2009 |
Publication |
UAB Divulga, Revista de divulgacion cientifica |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
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 |
spreading;ADAS |
Approved |
no |
Call Number |
ADAS @ adas @ PoL2009b |
Serial |
1270 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; A.F. Sole; Antonio Lopez; Cristina Cañero; Petia Radeva; Jordi Vitria |
Title |
Regularized EM |
Type |
Miscellaneous |
Year |
1999 |
Publication |
Proceedings of the VIII Symposium Nacional de Reconocimiento de Formas y Analisis de Imagenes |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
Bilbao |
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 |
invisible;ADAS;OR;MILAB;MV |
Approved |
no |
Call Number |
ADAS @ adas @ PSL1999 |
Serial |
4 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa; A.F. Sole; Antonio Lopez; Cristina Cañero; Petia Radeva; Jordi Vitria |
Title |
Regularized EM. |
Type |
Miscellaneous |
Year |
2000 |
Publication |
Pattern Recognition and Applications, IOS Press, 69–77. |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
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 |
invisible;ADAS;OR;MILAB;MV |
Approved |
no |
Call Number |
ADAS @ adas @ PSL2000 |
Serial |
336 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa |
Title |
A model based pedestrian tracking review |
Type |
Report |
Year |
2001 |
Publication |
CVC Technical Report #69 |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
|
Address |
CVC (UAB) |
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 |
invisible;ADAS |
Approved |
no |
Call Number |
ADAS @ adas @ Pon2001 |
Serial |
522 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Ponsa |
Title |
Model-Based Visual Localisation of Contours and Vehicles |
Type |
Book Whole |
Year |
2007 |
Publication |
PhD Thesis, Universitat Autonoma de Barcelona-CVC |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
Phd Thesis |
Abstract |
|
Address |
|
Corporate Author |
|
Thesis |
Ph.D. thesis |
Publisher |
Ediciones Graficas Rey |
Place of Publication |
|
Editor |
Antonio Lopez;Xavier Roca |
Language |
|
Summary Language |
|
Original Title |
|
Series Editor |
|
Series Title |
|
Abbreviated Series Title |
|
Series Volume |
|
Series Issue |
|
Edition |
|
ISSN |
|
ISBN |
978-84-935251-3-2 |
Medium |
|
Area |
|
Expedition |
|
Conference |
|
Notes |
ADAS |
Approved |
no |
Call Number |
ADAS @ adas @ Pon2007 |
Serial |
1107 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Marczak; Sebastian Cygert; Tomasz Trzcinski; Bartlomiej Twardowski |
Title |
Revisiting Supervision for Continual Representation Learning |
Type |
Miscellaneous |
Year |
2023 |
Publication |
Arxiv |
Abbreviated Journal |
|
Volume |
|
Issue |
|
Pages |
|
Keywords |
|
Abstract |
In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, recent studies have highlighted the strengths of self-supervised continual representation learning. The improved transferability of representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning. |
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 |
xxx |
Approved |
no |
Call Number |
Admin @ si @ MCT2023 |
Serial |
4013 |
Permanent link to this record |
|
|
|
Author ![sorted by Author field, descending order (down)](img/sort_desc.gif) |
Daniel Marczak; Grzegorz Rypesc; Sebastian Cygert; Tomasz Trzcinski; Bartłomiej Twardowski |
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 |