Page de Frédéric SUARD

Aller au contenu | Aller au menu | Aller à la recherche

Tag - svm

Fil des billets

dimanche, septembre 30 2007

A Pedestrian Detector Using Histograms of Oriented Gradients and a Support Vector Machine Classificator

Par Frédéric Suard le dimanche, septembre 30 2007, 10:01 - Publications

IEEE Intelligent Transportation Systems Conference 2007 30 septembre - 3 octobre 2007, Seattle, USA http://ewh.ieee.org/tc/its/itsc2007/

Abstract This paper details filtering subsystem for a tetravision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. This list is furtherly refined using symmetry-based assumptions. Then, this results is fed to a number of independent validators that evaluate the presence of human shapes inside the areas of attention. Histogram of oriented gradients and Support Vector Machines are used as a filter and demonstrated to be able to successfully classify up to 91% of pedestrians in the areas of attention.

2 annexes

mercredi, juin 13 2007

Model selection in pedestrian detection using multiple kernel learning

Par Frédéric Suard le mercredi, juin 13 2007, 18:22 - Publications

Intelligent Vehicle Symposium 13-15 June 2007, Istanbul, Turkey http://www.iv2007.itu.edu.tr/

Abstract This paper presents a pedestrian detection method based on the multiple kernel framework. This approach enables us to select and combine different kinds of image representations. The combination is done through a linear combination of kernels, weighted according to the relevance of kernels. After having presented some descriptors and detailed the multiple kernel framework, we propose three different applications concerning combination of representations, automatic parameters setting and feature selection. We then show that the MKL framework enable us to apply a model selection and improve the performance.

2 annexes

mardi, juin 13 2006

Pedestrian Detection using Infrared images and Histograms of Oriented Gradients

Par Frédéric Suard le mardi, juin 13 2006, 13:00 - Publications

Intelligent Vehicles Symposium 13-15 juin 2006, Tokyo, Japon http://www.cvl.iis.u-tokyo.ac.jp/iv2006/

Abstract This paper presents a complete method for pedestrian detection applied to infrared images. First, we study an image descriptor based on histograms of oriented gradients (HOG), associated with a Support Vector Machine (SVM) classifier and evaluate its efficiency. After having tuned the HOG descriptor and the classifier, we include this method in a complete system, which deals with stereo infrared images. This approach gives good results for window classification, and a preliminary test applied on a video sequence proves that this approach is very promising.

@inproceedings{fsuardiv06,
author = {Frédéric Suard and Alain Rakotomamonjy and Abdelaziz Bensrhair and Alberto Broggi},
title = {Pedestrian Detection using Infrared images and Histograms of Oriented Gradients},
booktitle = {Intelligent Vehicles Symposium, Tokyo, Japan},
year = {2006},
month = {June},
pages = {206--212},}

2 annexes

lundi, juin 6 2005

Pedestrian Detection using Stereo-vision and Graph Kernels

Par Frédéric Suard le lundi, juin 6 2005, 12:58 - Publications

Intelligent Vehicles Symposium 6-8 juin 2005, Las Vegas, Nevada, Etats-Unis. http://www.ieeeiv.org/

Abstract This paper presents a method for pedestrian detection with stereovision and graph comparison. Images are segmented thanks to the NCut method applied on a single image, and the disparity is computed from a pair of images. This segmentation enables us to keep only shapes of potential obstacles, by eliminating the background. The comparison between two graphs is accomplished with a inner product for graph, and then the recognition stage is performed learning is done among several pedestrian and non-pedestrian graphs with SVM method. The results that are depicted are preliminary results but they show that this approach is very promising since it clearly demonstrates that our graph representation is able to deal with the variability of pedestrian pose.

@inproceedings{fsuardiv05,
author = {Frédéric Suard and Vincent Guigue and Alain Rakotomamonjy and Abdelaziz Bensrhair},
 title = {Pedestrian Detection using Stereo-vision and Graph Kernels},
 booktitle = {Intelligent Vehicles Symposium, Las Vegas, Nevada},
 year = {2005},
 month = {June},
 pages = {267--272},}

2 annexes