An evidential framework for pedestrian detection in high-density crowds

Jennifer Vandoni (1, 2) , Emanuel Aldea (1, 2) , Sylvie Le Hégarat-Mascle (1, 2)

1 SATIE-MOSS - Méthodes et Outils pour les Signaux et Systèmes
2 UP11 - Université Paris-Sud - Paris 11

This paper addresses the problem of pedestrian detection in high-density crowd images, characterized by strong homogeneity and clutter. We propose an evidential fusion algorithm which is able to exploit multiple detectors based on different gradient, texture and orientation descriptors. The evidential framework allows us to model the spatial im-precision arising from each of the detectors. A first result of our study is that the fusion results underline clearly the good complementarity among the four descriptors we considered for this specific context. Moreover, the proposed algorithm outperforms a fusion solution based on Multiple Kernel Learning on difficult high-density crowd images acquired at Makkah at the height of the Muslim pilgrimage.

Domaines: Traitement du signal et de l'image [eess.SP]

Jennifer Vandoni, Emanuel Aldea, Sylvie Le Hégarat-Mascle. An evidential framework for pedestrian detection in high-density crowds. 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), Aug 2017, Lecce, Italy. ⟨10.1109/AVSS.2017.8078498⟩. ⟨hal-01690895⟩