Real-time object detection using an evolutionary boosting strategy

Authors:
Xavier Baro;Jordi Vitria
Affiliations:
Centre de Visió per Computador;Centre de Visió per Computador and Dept. de Ciències de la Computació UAB, Edifici O -Campus UAB, 08193 Bellaterra, Barcelona, Catalonia, Spain {xbaro,jordi}@cvc.uab.es
Venue:
Proceedings of the 2006 conference on Artificial Intelligence Research and Development
Year:
2006

Citing 2
Cited 2

Robust Real-Time Face Detection

International Journal of Computer Vision
Feature Selection with Non-Parametric Mutual Information for Adaboost Learning

Proceedings of the 2005 conference on Artificial Intelligence Research and Development

Weighted Dissociated Dipoles for Evolutive Learning

Proceedings of the 2007 conference on Artificial Intelligence Research and Development
Weighted dissociated dipoles: an extended visual feature set

ICVS'08 Proceedings of the 6th international conference on Computer vision systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a brief introduction to the nowadays most used object detection scheme. From this scheme, we highlight the two critical points of this scheme in terms of training time, and present a variant of this scheme that solves one of these points. Our proposal is to replace the WeakLearner in the Adaboost algorithm by a genetic algorithm. In addition, this approach allows us to work with high dimensional feature spaces which can not be used in the traditional scheme. In this paper we also use the dissociated dipoles, a generalized version of the Haarlike features used on the detection scheme. This type of features is an example of high dimensional feature space, moreover, when we extend it to color spaces.