Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for extracting video summaries in compressed domain for AVS monitoring files

A technology of video summarization and extraction method, which is applied in closed-circuit television systems, image data processing, instruments, etc., can solve the problems of loss of non-key frame motion information, difficulty in modification, and inability to generate video summaries, so as to improve extraction speed and reduce cost effect

Inactive Publication Date: 2018-01-12
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Recent research on video summarization in the compressed domain has mainly focused on keyframe methods, which lose information about motion in non-keyframes.
[0003] In addition, based on mainstream video coding (such as: MPEG-2, H264, etc.), there are many research works in the compressed domain, such as object recognition, motion segmentation, motion tracking, etc., which can extract motion information, but cannot generate video summaries
Due to the cross-reference relationship between adjacent frames in these video codes, it is difficult to modify, so the video summary cannot be generated

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A method and device for extracting video summaries in compressed domain for AVS monitoring files
  • A method and device for extracting video summaries in compressed domain for AVS monitoring files
  • A method and device for extracting video summaries in compressed domain for AVS monitoring files

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] According to the video standard of AVS surveillance files, the coding structure of a video is as follows: figure 1 shown. The video of the AVS surveillance file is composed of multiple segments, and each segment is composed of multiple groups. The first frame of each group is a G frame or S frame, and the remaining frames are P frames or B frames. Each segment contains one and only one G frame as the first frame. Each segment contains a training set of the same length to train the G frames in the next segment. Except for the G frame in segment 0, which is normally decoded and played, the other G frames are background frames, which are decoded but not played.

[0038] The input video of the present invention only needs to meet the encoding standard of the AVS monitoring file, and is not limited to how transcoding is obtained, nor is it limited to some attributes of video encoding; therefore, the OneStopEnter2front video (address: http: / / homepages.inf.ed.ac.uk / rbf / CAV...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for extracting compressed domain video summaries oriented to AVS monitoring files, belonging to the technical field of computer vision processing; comprising the following steps: first extracting background frames in the AVS code stream, and analyzing the motion vector (MV) in the code stream , to extract foreground moving macroblocks; then track the foreground macroblocks to obtain effective moving object trajectories; finally recombine moving object trajectories and combine them with background frames to generate a summary video. Compared with the prior art, the application of the method of the invention can improve the processing speed, generate abstract video code stream files that can be played by an AVS code stream player, and improve the utilization efficiency of the original video.

Description

Technical field: [0001] The invention relates to a method and device for extracting compressed domain video summaries oriented to AVS monitoring files, and belongs to the technical field of computer vision processing. Background technique: [0002] Due to the large amount of data and unstructured characteristics of surveillance video, it is difficult to effectively use the original surveillance video data. Video summarization is one of the important means to effectively utilize surveillance video. Video Synopsis processes the original video into a short video, preserving the content of the original video. Mainstream surveillance video summarization methods focus on the pixel domain. Although the pixel-domain method is better, it requires a full decoding of the video stream and has high computational complexity. Therefore, extracting video information directly to generate surveillance video summaries in the compressed domain is more suitable for actual needs. Recent resear...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N7/18G06T7/20H04N21/8549
Inventor 黄华赵磊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY