Video key frame extraction method based on adaptive grouping and feature map information entropy

The invention discloses a video key frame extraction method based on adaptive grouping and feature map information entropy. The method comprises the following steps: firstly, segmenting a selected video into a video frame sequence according to the frame rate of the video; then, calculating the structural similarity between two adjacent frames in the video frame sequence so as to obtain a similarity sequence of the current video; calculating a self-adaptive threshold value by using the similarity sequence, and grouping the video frame sequence according to the self-adaptive threshold value to obtain a plurality of image groups of the current video; and finally, in combination with the information entropy of the feature map, respectively extracting key frames of each image group, thereby obtaining all key frames of the current video, and completing extraction of the video key frames. According to the method, the accuracy of key frame extraction is greatly improved by adopting the method of combining the SSIM an