Video Object Segmentation With Robust Reference Frame Generation

In this paper, a video object segmentation algorithm with robust reference frame generation has been proposed. This algorithm uses a robust approach for obtaining a reference background frame in order to improve the results of change detection and also solves the problems of dis-occluded regions appearing as part of the segmented moving objects. In addition, a change detection process with adaptive threshold estimation has been adopted here. Also, the use of specially detected “moving” edgels and a graph-based edge-linking method that employs both gradient-based and edge-based constraints have also been applied to refine the object segmentation mask. The proposed work has shown a reasonably fast and good video object segmentation technique that operates in real-time and can be applied in applications such as MPEG-4's content-based video coding and home/office/warehouse security. Key-Words: video object segmentation, change detection, reference frame, disoccluded regions, edgelinking