An edge-texture based moving object detection for video content based application

This paper presents a moving-object segmentation algorithm using texture information along the edge segment. The proposed method is developed to address challenges due to variations in ambient lighting and background contents. We investigated the suitability of the proposed algorithm in comparison with the traditional edge-pixel-based and edge-segment-based detection methods. In our method, edges are extracted from each frame of a video sequence and are represented as segments using an efficiently designed edge class. In addition we maintain the underlying texture information with a newly proposed texture descriptor Local Directional Pattern (LDP). LDP feature is generated by comparing a pixel's edge response in eight directions. LDP texture extracted along the edge region to identify moving edge segment using three most recent frames. This fusion of texture and edge segment information helps to obtain the geometric information of edge in the case of edge matching. Detected moving edges are utilized along with watershed algorithm for extracting video object plane with more accurate boundary. Experiment results with real image sequence reflect that the proposed method is suitable than other existing approaches.