Key-frame retrieval method based on optical flow and entropy statistic for blooming video

The original video of flower growth process contains large amount of data and plenty of redundance information. In order to obtain the video of flower growth process to facilitate the researchers, which is endowed with high compression ratio, small amount of data, rich growth details information and natural fluency, a key frame extraction method was introduced to process the original video. According to the characteristics of flower growing process, he motion detection algorithm was chosen to take tests on them. Through the simulation analysis of frame difference method, this paper proposed a new key frame extraction method based on optical flow and direction information entropy. Experiment showed that in the case of extracting the same number of key frames, this method can perform details of the flower movement better, which is superior to the frame difference method.