System and method for collecting and analyzing moving image

Abstract

The invention discloses a method for collecting and analyzing a moving image. The method comprises the following steps: S100, extracting a video stream to be processed, and carrying out framing processing to obtain a plurality of frames of images; respectively capturing different scenery information in the plurality of frames of images and integrating the information with respective scenery; s200, performing fragment division on the to-be-processed video stream based on the scene integration information; s300, target scenery discrimination is carried out on each image frame, and expected image selection is carried out on a plurality of segments of video sequences; step S400, carrying out target scenery motion condition identification and adjustment on the part of the expected image; step S500, pushing the finally selected expected image to the user, wherein the user can select the image based on own willingness; in order to better realize the method, the invention also provides a mobile image acquisition and analysis system. When the picture scene in the video is a character or a chart, the recognition of the picture scene can correspond to the information recognition of the character and the chart.

Description

technical field [0001] The invention relates to the technical field of collecting and processing video stream content, in particular to a system and method for collecting and analyzing moving images. Background technique [0002] For a video stream, if the user wants to obtain a part of the scene in a video stream, he usually adopts the method of self-screenshot, but the moment of self-screenshot is likely to be the transition between the film frame and the frame, it is possible The interception of the desired image is not accurate, and if there is a dynamic scene in the video stream, it is even more difficult to collect a photo with an excellent viewing effect of the dynamic scene; at the same time, the video stream includes many If the image is only collected through self-screenshots, it means that the video stream needs to be continuously reflowed to the desired scene moment, which reduces the efficiency of image collection and affects the final viewing effect of the imag...

AI Technical Summary

Problems solved by technology

[0002] For a video stream, if the user wants to obtain a part of the scene in a video stream, he usually adopts the method of self-screenshot, but the moment of self-screenshot is likely to be the transition between the film frame and the frame, it is possible The interception of the desired image is not accurate, and if there is a dynamic scene in the video stream, it is even more difficult to collect a photo with an excellent viewing effect of the dynamic scene; at the same time, the video stream includes many If the image is only collected through self-screenshots, it means that the video stream needs to be continuously reflowed to the desired scene moment, which reduces the efficiency of image collection and affects the final viewing effect of the image.

Images