Video synopsis algorithm based on two-stage target tubes grouping

Video synopsis generates a concentrated video that can be browsed quickly. With the increase of condensation ratio, more pseudo collisions between target tubes will occur. To solve this problem, paper proposed algorithm based on two-stage grouping. In first stage, using hypergraph to analyze collision relationship tubes, and are grouped according hyper-edges. second clustering equal distance nearest neighbor sampling is group tubes. Then, selecting selection principle quantity priority groups length within (QPB-LPG) . Finally, these rearranged generate videos with smaller collisions. The experimental results show significantly reduce without reducing frame ratio compact rate compared existing concentration algorithms, feasibility method fully verified.