Video processing method, system and device and storage medium

The invention provides a video processing method, system and device and a storage medium, and the method comprises the steps: sequentially inputting each video frame image with continuous time in a to-be-processed video into a portrait matting model, the portrait matting model comprising a decoding part, the decoding part comprising at least one circulating decoding module connected in series, each cyclic decoding module is used for extracting hidden features from the current video frame image by using the hidden features extracted from the previous video frame image by the cyclic decoding module; acquiring a portrait mask of the current video frame image from the portrait matting model; and obtaining a processed image of the current video frame based on the portrait mask and the background image of the previous video frame. Through adoption of the method and the device, the portrait prediction continuity between the video frames is improved, and portrait flicker between the frames is reduced. 本申请提供了一种视频处理方法、