Tracking and segmentation using min-cut with consecutive shape priors

• Main Authors: Wang Junqiu, Yagi Yasushi
• Format: Article
• Language: English
• Published: De Gruyter 2010-03-01
• Series: Paladyn: Journal of Behavioral Robotics
• Subjects: tracking; segmentation; mean-shift; min-cut; shape priors; consecutive shape matching
• Online Access: https://doi.org/10.2478/s13230-010-0008-y

Tracking and segmentation find a wide range of applications such as intelligent sensing of robots, human-computer interaction, and video surveillance. Tracking and segmentation, however, are challenging for many reasons, e.g., complicated object shapes, cluttered background. We propose a tracking and segmentation algorithm that employs shape priors in a consecutive way. We found that shape information obtained using the Min-Cut algorithm can be applied in segmenting the consecutive frames. In our algorithm, the tracking and segmentation are carried out consecutively. We use an adaptive tracker that employs color and shape features. The target is modeled based on discriminative features selected using foreground/background contrast analysis. Tracking provides overall motion of the target for the segmentation module. Based on the overall motion, we segment object out using the effective min-cut algorithm. Markov Random Fields, which are the foundation of the min-cut algorithm, provide poor priors for specific shapes. It is necessary to embed shape priors into the min-cut algorithm to achieve reasonable segmentation results. Object shapes obtained by segmentation are employed as shape priors to improve segmentation in next frame. We have verified the proposed approach and got positive results on challenging video sequences.§