Visual Attention Based Motion Object Detection and Trajectory

Publisher:
Springer
Publication Type:
Chapter
Citation:
Lecture Notes in Computer Science 6298 - Advances in Multimedia Information Processing - PCM 2010, 2010, 1, pp. 462 - 470
Issue Date:
2010-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2009007465OK.pdf651.58 kB
Adobe PDF
A motion trajectory tracking method using a novel visual attention model and kernel density estimation is proposed in this paper. As a crucial step, moving objects detection is based on visual attention. The visual attention model is built by combination of the static and motion feature attention map and a Karhunen-Loeve transform (KLT) distribution map. Since the visual attention analysis is conducted on object level instead of pixel level, the proposed method can detect any kinds of motion objects provided saliency without the affection of objects appearance and surrounding circumstance. After locating the region of moving object, the kernel density is estimated for trajectory tracking. The experimental results show that the proposed method is promising for moving objects detection and trajectory tracking.
Please use this identifier to cite or link to this item: