Video category identification method and related device

Abstract

The invention belongs to the technical field of video processing, and discloses a video category recognition method and a related device, and the device comprises an image receiving module, a key frame extraction module, an image noise reduction module, a feature information recognition module, a video library module, a feature information comparison module, and a recognition result output module.And the tTypes of the key frames in the identified video data are counted, and the types of the video data are determined according to a statistical result, so that the identification of the video types is realized. According to the technical scheme, the category of the video does not need to be manually recognized, the labor cost of video category recognition in video monitoring is reduced, andin addition, the speed of reading the video data from the video file is much higher than that of manually watching the video, so that the efficiency of video category recognition in video monitoring is further improved. According to the invention, nNoise reduction processing is carried out on the extracted video key frame, the definition of the key frame image is enhanced, and the accuracy of video identification and classification is improved.

Description

technical field [0001] The invention belongs to the technical field of video processing, and in particular, relates to a method and related device for video category identification. Background technique [0002] At present, with the continuous upgrading of computer hardware technology and software technology, various types of digital camera equipment emerge in an endless stream, communication technology has repeatedly developed breakthroughs, the number and dissemination speed of video is increasing rapidly, and content video has become a major trend in the development of the Internet. Therefore, the recognition technology for video classification is particularly important. In the prior art, when identifying and classifying a video, after recording and storing the corresponding video, it is necessary to manually identify the category of the video by playing back the video, and finally perform processing according to the identified category of the video. Since the existing t...

AI Technical Summary

Problems solved by technology

In the prior art, the category of the video is manually identified by playing back the video, so a large number of monitoring personnel need to be hired, and the labor cost is high. At the same time, since the monitoring personnel need to watch the video content from beginning to end when playing back the video, the efficiency is relatively high. Low

[0003] Through the above analysis, the existing problems and defects of the prior art are: in the prior art, the category of the video is manually identified by playing back the video, so it is necessary to employ a large number of monitoring personnel, and the labor cost is relatively high. The monitoring personnel are required to watch the video content from beginning to end, so the efficiency is low

Images