Counting Crowded Moving Objects

In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably with occlusions and therefore with crowding. When the objects are constrained to be of the same kind, however, partitioning of densely crowded semi-rigid objects can be accomplished by means of clustering tracked feature points. We base our approach on a highly parallelized version of the KLT tracker in order to process the video into a set of feature trajectories. While such a set of trajectories provides a substrate for motion analysis, their unequal lengths and fragmented nature present difficulties for subsequent processing. To address this, we propose a simple means of spatially and temporally conditioning the trajectories. Given this representation, we integrate it with a learned object descriptor to achieve a segmentation of the constituent motions. We present experimental results for the problem of esti...

• Type: Conference
• Year: 2006
• Where: CVPR
• Authors: Vincent Rabaud, Serge Belongie
• Keywords: Computer Vision, Crowded Objects Necessitates, CVPR 2006, Feature Trajectories, Motion Analysis, Nature Present Difficulties, Semi-rigid Objects