Search For:

Displaying 1-6 out of 6 total
Learning appearance in virtual scenarios for pedestrian detection
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Javier Marin, David Vazquez, David Geronimo, Antonio M. Lopez
Issue Date:June 2010
pp. 137-144
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...
 
Virtual and Real World Adaptation for Pedestrian Detection
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By David Vazquez,Antonio M. Lopez,Javier Marin,Daniel Ponsa,David Geronimo
Issue Date:April 2014
pp. 797-809
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 ...
 
Domain Adaptation of Deformable Part-Based Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Jiaolong Xu,Sebastian Ramos,David Vazquez,Antonio M. Lopez
Issue Date:December 2014
pp. 1-1
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 pa...
 
Random Forests of Local Experts for Pedestrian Detection
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Javier Marin,David Vazquez,Antonio M. Lopez,Jaume Amores,Bastian Leibe
Issue Date:December 2013
pp. 2592-2599
Pedestrian detection is one of the most challenging tasks in computer vision, and has received a lot of attention in the last years. Recently, some authors have shown the advantages of using combinations of part/patch-based detectors in order to cope with ...
 
Prefilter design for forensic resampling estimation
Found in: Information Forensics and Security, IEEE International Workshop on
By David Vazquez-Padin,Fernando Perez-Gonzalez
Issue Date:December 2011
pp. 1-6
Starting from a theoretical analysis of the resampling estimation problem for image tampering detection, this work presents a study, based on cyclostationarity theory, about the use of prefilters to improve the estimation accuracy of the resampling factor....
 
Virtual worlds and active learning for human detection
Found in: Proceedings of the 13th international conference on multimodal interfaces (ICMI '11)
By Antonio M. Lopez, Daniel Ponsa, David Vazquez, Javier Marin
Issue Date:November 2011
pp. 393-400
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 res...
     
 1