An Improved Algorithm for Video Abstract.

In this paper, we study the foreground object extraction, the trajectory extraction, the trajectory combination optimization and other key technologies of the surveillance video abstract generation technology. Put forward a kind of improved algorithm, through the pre-processing based on Focus Stacking, foreground object extraction of the foreground object shadow removal, the trajectory synthesis optimization. As a result, the foreground extraction accuracy rate was increased by 2.78%; because of shadow removal of the foreground object, the collision rate of the foreground object in the synthesized video is reduced by 15.77%; The use of Semi-Transparent Handling Collision (STHC) makes the trajectory of the foreground object is not interrupted, the video frame information is not lose and the compression rate is increased by about 10%. The algorithm is applied in this paper, and the optimization effect is observed through the whole system test. As a result, the clarity of the synthesized video is increased, the integrity of the video’s information is enhanced, and the compression rate of the video is improved.