Continuous multi-views tracking using tensor voting

The paper presents a new approach for continuous tracking of moving objects observed by multiple fixed cameras. The continuous tracking of moving objects in each view is realized using a tensor voting based approach. We infer objects' trajectories by performing a perceptual grouping in 2D+t using tensor voting. Also, a multi-scale approach to bridge gaps in object trajectories is presented The trajectories obtained from the multiple cameras are registered in space and time, allowing a synchronization of the video streams and a continuous tracking of objects across multiple views. We demonstrate the performance of the system on several real video surveillance sequences.