Video pushing method and system, equipment and readable storage medium

Abstract

The invention discloses a multi-channel video pushing method and system, equipment and a readable storage medium. The method comprises the following steps: acquiring a first channel video stream and asecond channel video stream; respectively converting the first path of video stream and the second path of video stream into images according to video frames, performing feature point extraction on the image in each path of video stream every other i frames from the first frame, taking the frame for feature point extraction as an extraction frame, matching the feature points extracted from the corresponding frames in the first path of video stream and the second path of video stream to obtain a feature matrix, storing the feature matrix, splicing graphs between the current extraction frame and the next extraction frame based on the feature matrix of the current extraction frame to form a spliced image, and transmitting the spliced image after compression coding. According to the technicalscheme provided by the embodiment of the invention, multi-channel video streams are spliced and pushed, the obtained video streams are subjected to single-frame processing, and feature extraction andfeature matching are carried out once on each frame of images, so that the video splicing effect can be ensured, and the real-time performance of the video is not influenced.

Description

technical field [0001] The present invention generally relates to the field of video push, and in particular to a video push method, system, device and readable storage medium. Background technique [0002] At the video collection end, multiple cameras collect video content at the same time. After the video is collected, the videos collected by each camera are stitched together, and the stitched video is pushed to the server. In this process, the most important thing is the real-time splicing process of the video. At present, the splicing of the video is generally carried out through the image splicing step. In the process of image splicing, feature points need to be extracted and matched, and each frame of the video needs to be The extraction and matching of feature points are all carried out, which consumes a lot of time. Contents of the invention [0003] In view of the above defects or deficiencies in the prior art, it is desired to provide a video push method, system...

AI Technical Summary

Problems solved by technology

In this process, the most important thing is the real-time splicing process of the video. At present, the splicing of the video is generally carried out through the image splicing step. In the process of image splicing, feature points need to be extracted and matched, and each frame of the video needs to be Extraction and matching of feature points are performed, which consumes a lot of time

Images