Density-aware person detection and tracking in crowds

Mikel Rodriguez (1, 2) , Ivan Laptev (1) , Josef Sivic (1) , Jean-Yves Audibert (1, 3, 4)

1 WILLOW - Models of visual object recognition and scene understanding
2 ENS-PSL - École normale supérieure - Paris
3 imagine [Marne-la-Vallée]
4 LIGM - Laboratoire d'Informatique Gaspard-Monge

We address the problem of person detection and tracking in crowded video scenes. While the detection of individual objects has been improved significantly over the recent years, crowd scenes remain particularly challenging for the detection and tracking tasks due to heavy occlusions, high person densities and significant variation in people's appearance. To address these challenges, we propose to leverage information on the global structure of the scene and to resolve all detections jointly. In particular, we explore constraints imposed by the crowd density and formulate person detection as the optimization of a joint energy function combining crowd density estimation and the localization of individual people. We demonstrate how the optimization of such an energy function significantly improves person detection and tracking in crowds. We validate our approach on a challenging video dataset of crowded scenes.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Mikel Rodriguez, Ivan Laptev, Josef Sivic, Jean-Yves Audibert. Density-aware person detection and tracking in crowds. ICCV 2011 - 13th International Conference on Computer Vision, Nov 2011, Barcelona, Spain. 8 p. ⟨hal-00654266⟩