Video concentration method used for video with still picture

Abstract

The invention relates to a video concentration method used for a video with a still picture, and belongs to the technical field of video compression. At first a video to be concentrated is processed frame by frame, initial judgment state of all pixel points of video frames are confirmed by utilizing a motion detection method based on Gaussian mixture, and the final judgment state is confirmed by carrying out spatial filtering processing on all the pixel points of the video frames, and comparing the size of the number of the pixel points with the final judgment state of motion state with a threshold value to obtain the initial judgment state of the video frames. When process of frame by frame is finished, time-domain filtering is carried out on the initial judgment state of all the video frames and the final judgment state of all the video frames is obtained, video frames of the stationary state within all the video frames are removed, and the video after concentration is obtained. The video concentration method used for the video with the still picture lowers video data amount substantially under the premise of retaining amount of information in a maximum degree, brings convenience for storage and transmission, at the same time concentrates the video to facilitate a viewer to extract information in a high-efficient mode, and has the advantages of being flexible and easily-controlled in concentration degree, and high in robustness in a slowly-changing environment and the like.

Description

technical field [0001] The invention relates to a video concentrating method for video with still pictures, belonging to the technical field of video compression. Background technique [0002] Digital video needs to be compressed because it takes up a staggeringly large amount of space in its original form. After the video is compressed, it will be more convenient to store. Digital video compression does not affect the final visual effect of the work, because it only affects the part of the video that cannot be perceived by human vision. For example, there are billions of colors, but only about 1024 can be distinguished. Since there is no perceptible subtle difference between a color and its neighbours, there is no need to preserve every color. There's also the issue of redundant images—if the same chair is in the same position in every frame of a 60-second video production, there's no need to save that chair's data in every frame, In short, compressing video is essentia...

AI Technical Summary

Problems solved by technology

The process of manual labeling is long and cumbersome, because most of the time segments of surveillance video can provide limited information, especially considering that most surveillance cameras are fixed, and there are a large number of continuous still images in the captured surveillance video, which basically cannot be Viewers provide any information, but in order not to miss the core content, skipping some video clips is not a feasible solution. Overall, this working mode is inefficient, limits the processing speed of surveillance video, and increases security Burden of departmental video processing

Existing video compression methods are helpless to this problem, because they will not change the video duration and cannot collect and condense the amount of video information

Images