A superpixel segmentation algorithm with region correlation saliency analysis for video pedestrian detection
Dawei Yang, Lin Mao, Mengting Ji, Rubo Zhang · 2017
Most pedestrian detection algorithms only provide the object region instead of the actual body segmentation in video. For reducing the large number of redundant information and extracting a clear contour and texture feature of an up-right person, a superpixel segmentation algorithm with region correlation saliency analysis is proposed from coarse to fine cutting without any prior information. This algorithm cuts single pedestrian target automatically and obtains strict features of human object regardless of whether or not the camera is moving. It exploits saliency analysis to find location and compute region energy in superpixel image to achieve a body segmentation. Experimental results indicate that the proposed approach detects pedestrian efficiently in the complex background environment in both indoor and outdoor videos with precise object cutting boundaries.