Human Detection with a Multi-sensors Stereovision System

Abstract : In this paper, we propose a human detection process using Far-Infrared (FIR) and daylight cameras mounted on a stereovision setup. Although daylight or FIR cameras have long been used to detect pedestrians, they nonetheless suffer from known limitations. In this paper, we present how both can collaborate inside a stereovision setup to reduce the false positive rate inherent to their individual use. Our detection method is based on two distinctive steps. First, human positions are detected in both FIR and daylight images using a cascade of boosted classifiers. Then, both results are fused based on the geometric information of the sterovision system. In this paper, we present how human positions are localized in images, and how the decisions taken by each camera are fused together. In order to gauge performances, a quantitative evaluation based on an annotated dataset is presented.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download
Contributor : Morgan Barbier <>
Submitted on : Tuesday, October 16, 2012 - 3:19:17 PM
Last modification on : Thursday, February 7, 2019 - 5:38:32 PM
Document(s) archivé(s) le : Thursday, January 17, 2013 - 2:40:10 AM


Files produced by the author(s)



Yannick Benezeth, Pierre-Marc Jodoin, Bruno Emile, Hélène Laurent, Christophe Rosenberger. Human Detection with a Multi-sensors Stereovision System. International Conference on Image and Signal Processing, Jul 2010, Trois-Rivières, Canada. pp.228-235, ⟨10.1007/978-3-642-13681-8_27⟩. ⟨inria-00545510⟩



Record views


Files downloads