Moving Object Tracking from Videos based on Enhanced Space-Time-Range Mean Shift and Motion Consistency
Paper i proceeding, 2007

Video surveillance and object tracking have drawn increased interests in recent years. This paper addresses the problem of moving object tracking from image sequences captured from stationary cameras. Based on our previous work on video segmentation using joint space-time-range mean shift, we extend the scheme to enable the tracking of moving objects. Large displacements of pdf modes in consecutive image frames are exploited for tracking. We also improve the above mean shift-based video segmentation by introducing edge-guided merging of over-segmented regions. This can be viewed as an extension of the enhanced mean shift 2D image segmentation to the enhanced space-time-range mean shift video segmentation. Experiments have been conducted on several indoor and outdoor videos. Our preliminary results and performance evaluation have indicated the effectiveness of the proposed scheme.

video segmentation

motion field

multiple object tracking

joint space-time-range mean shift

Författare

Irene Yu-Hua Gu

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Andrew Backhouse

Chalmers, Signaler och system

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Pengfei Shi

IEEE International Conference on Multimedia & Expo (ICME '07), 2007

Ämneskategorier

Signalbehandling

Datorseende och robotik (autonoma system)