Video frame coding method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a video frame coding method and device, electronic equipment and a storage medium. The method comprises: performing high and low frequency splitting on a privacy ROI region in a video frame coding block coefficient, wherein a base layer comprises a low-frequency coefficient of the ROI region and a complete coefficient of a non-ROI region, and an enhancement layer comprises a high-frequency coefficient of the ROI region; decoding the code stream of the base layer to obtain a low-frequency coefficient comprising the ROI region in the base layer and complete coefficients of other regions except the ROI region, so that the ROI region subjected to privacy processing and a clear non-ROI region can be obtained, and since the enhancement layer code stream comprises the high-frequency coefficient of the ROI region, the clear ROI region can be obtained through decoding by using the enhancement layer code stream and the base layer code stream, so that the recoverability of the privacy region can be realized. In addition, the coefficients of the non-ROI region in the enhancement layer are all preset numerical values, coding resources can be saved, the data size after coding is small, and therefore bandwidth resources are saved.

Description

technical field [0001] The present application relates to the technical field of video coding, in particular to a video frame coding method, device, electronic equipment and storage medium. Background technique [0002] With the development of science and technology and the improvement of people's safety awareness, there are more and more monitoring equipment in public places, and intelligent detection technology is also more and more used in monitoring scenarios. In addition, people are paying more and more attention to personal privacy protection under surveillance equipment, and the demand for video privacy protection technology is also increasing. Video privacy protection, that is, by coding, blocking, or scrambling the partial privacy area in the video image, the image in the privacy area cannot be recognized, while other areas retain the original content and are normally visible. However, the image processing of video privacy protection has the characteristic that the...

AI Technical Summary

Problems solved by technology

[0004] However, using the above method, the two video streams are encoded separately, which wastes encoding resources, and the transmission of the two video streams also wastes network bandwidth resources. In addition, the privacy area of ​​the video stream after privacy protection processing cannot be restored, and subsequent evidence collection is difficult.

Images