Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Video Concentration Method Based on Line Cropping

A technology of video concentration and line cutting, applied in digital video signal modification, electrical components, image communication, etc., to achieve the effect of reducing the number of frames, maintaining integrity, and enhancing the value of real-world applications

Active Publication Date: 2016-11-16
FUDAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] (1) Storage space: Since it is a surveillance video, the camera must be monitored all the time, resulting in the generation of endless surveillance videos every minute and every second, which puts a huge pressure on storage

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 Video Concentration Method Based on Line Cropping
  • A Video Concentration Method Based on Line Cropping
  • A Video Concentration Method Based on Line Cropping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] If use the present invention to realize video concentration for a section of video, can adopt figure 1 The method described is implemented. The specific implementation method is:

[0042] First, use existing methods (such as [1,2]) to realize the extraction of video tubes and generate video masks.

[0043] Then the video mask and the video tube are transposed to obtain two new cuboids, where the x-t plane before the transposition faces the user.

[0044]Generate energy maps based on information such as optical flow and gradients in the x-t plane of the video tube. Then, the transposed video tube and video mask are clipped synchronously based on the energy map. In this way, pixels with large changes in the time domain will be retained and pixels with small optical flow values ​​will be cut. Namely: After applying line clipping on each tube, smaller motions will be more condensed, while larger motions will be preserved.

[0045] During online clipping, the current D ...

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 belongs to the technical field of video concentration, in particular to a video concentration method based on line cutting. Video condensing refers to compressing the time of the video, so that the details of the original video can be described as much as possible in a short time, and the redundant information in the time domain of the video can be removed, so that users can quickly browse endless surveillance videos. ability. The method of the present invention uses line cutting to cut the video Tube, thereby reducing the length of the video in the time domain; during the cutting process, the energy map of the video Tube is updated using optical flow, and according to the analysis results about the video Tube energy map, the cutting termination is set According to the criterion, for each tube, the duration of the video tube is compressed as much as possible under the premise of ensuring the continuity of the video, and finally the effect of effective video concentration is achieved. Experimental results show that the method of the present invention can effectively realize video compression in the time domain on the basis of better maintaining the description of object motion.

Description

technical field [0001] The invention belongs to the technical field of video concentration, and in particular relates to a video concentration method. Background technique [0002] Since the last century, tens of millions of surveillance cameras have been deployed at transportation hubs such as railway stations, airports, and various traffic intersections, and a large number of surveillance videos are constantly being produced. In the digital age, the number of surveillance videos has grown explosively. On the streets of the city, every camera is recording 24 hours a day, and many surveillance videos have never been watched at all. The length of the video also brings great difficulties to backtracking. As surveillance cameras become cheaper and easier to deploy, surveillance networks continue to become denser, making it more difficult to monitor people and requiring more storage space. Therefore, various algorithms born to solve various inconveniences caused by monitoring...

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): H04N19/51H04N19/43
Inventor 颜波薛向阳李可王伟祎
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com