论文信息 - On Occlusion-Handling for People Detection Fusion in Multi-camera Networks

On Occlusion-Handling for People Detection Fusion in Multi-camera Networks

In this paper a system for people detection by means of Track-To-Track fusion of multiple cameras is presented. The main contribution of this paper is the evaluation of the fusion algorithm based on real image data. Before the fusion of the tracks an occlusion handling resolves implausible assignments.

Anton Kummert | Mirko Meuter | Christian Nunn | Anselm Haselhoff | Lars Hoehmann

[1] Stephan Matzka,et al. A comparison of track-to-track fusion algorithms for automotive sensor fusion , 2008, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[2] Rudolph van der Merwe,et al. Sigma-point kalman filters for probabilistic inference in dynamic state-space models , 2004 .

[3] Yaakov Bar-Shalom,et al. Multitarget-Multisensor Tracking: Applications and Advances , 1992 .

[4] J. Munkres. ALGORITHMS FOR THE ASSIGNMENT AND TRANSIORTATION tROBLEMS* , 1957 .

[5] Mirko Meuter,et al. Multi-camera Pedestrian Detection by Means of Track-To-Track Fusion and Car2Car Communication , 2011, VISAPP.

[6] Sameer Singh,et al. Approaches to Multisensor Data Fusion in Target Tracking: A Survey , 2006, IEEE Transactions on Knowledge and Data Engineering.