Extracting video object's motion trajectory by velocity voting

Abstract

Video object extraction is an important issue in video content analysis. In this paper, a novel approach to motion trajectory extraction is proposed, which may effectively facilitate video object extraction. A motion trajectory in this approach is defined as a trail of image regions with coherent velocities in an image sequence. The regions with color and texture coherence are extracted first. Then, the region velocity is estimated through the relationships between itself and its adjacent regions in the consecutive frames. This process is called velocity voting. After that, the genetic algorithm is applied to establish the 2D+t motion trajectories based on the region velocities. Finally, some short motion trajectories are concatenated along the time axis. In the spatial plane, the regions are merged by grouping the similar motion trajectories. Experimental results show that the proposed approach effectively suppresses some challenging issues in video object extraction, such as over-segmentation and losing track of objects.