Key frame extraction method based on inter-frame difference and color histogram difference

Abstract

The invention discloses a key frame extraction method based on inter-frame difference and color histogram difference. The method comprises the steps: in the first stage, detecting a moving target in amonitoring video based on inter-frame difference, dividing the monitoring video into a video sequence only containing the moving target, and obtaining candidate key frames; and in the second stage, calculating the color histogram difference value of two adjacent frames in the candidate key frames, setting a threshold value, removing similar image frames, and obtaining a final key frame set. Compared with other key frame extraction technologies, the method has the advantages that the time required for key frame extraction is remarkably shortened, the real-time requirement is met and redundantinformation in the set is reduced as much as possible while relatively high representativeness of the content of the key frame set is ensured, so that the number of key frame frames is relatively small, and thus, the time complexity of task algorithms such as subsequent target identification and pedestrian quantity statistics is reduced.

Description

technical field [0001] The invention belongs to the technical field of video detection, and in particular relates to a key frame extraction method based on inter-frame difference and color histogram difference. Background technique [0002] With the rapid development of technologies such as smart terminals and the Internet of Things, video data is growing explosively, and video analysis methods that rely on manual screening can no longer meet actual needs. On the one hand, the speed is slow, and it is difficult for manual screening methods to process a large amount of video data in real time; on the other hand, the cost is high, and massive video analysis brings huge labor costs. How to use computer resources to extract the content we are interested in from massive video data, and provide more effective data for target recognition, people flow statistics and other technologies has become a problem that needs to be solved at present. [0003] At present, the typical key fram...

AI Technical Summary

Problems solved by technology

This type of method is simple, but it is easy to select more redundant frames

[0004] Most of the current research is based on the video of camera switching, and there is less research on the video of fixed camera

Secondly, it does not take into account the key frame extraction requirements of subsequent tasks such as target recognition

In addition, the above research methods such as clustering and streamer method have complex calculations, and there are redundant frames in the key frames extracted by methods such as sampling and image features.

Images