Video analysis method based on video abstraction and video retrieval

A technology of video summarization and video analysis, applied in the field of video processing, can solve the problems that the acquisition of detailed information stays at the experience level, the efficiency is low, and the target is easily missed, so as to reduce the target omission and improve the efficiency.

Inactive Publication Date: 2013-04-03
SUZHOU QIANSHI COMM TECH
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the current video detection is mainly carried out by viewing the video with the naked eye, which is inefficient and easy to miss the target
Even if photos and video clips of suspected targets such as people are obtained, its further application can only be carried out through manual investigation, and the acquisition of detailed information remains at the empirical level without process guarantees

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
  • Video analysis method based on video abstraction and video retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] If there is a major robbery and wounding case in a certain place, judging from the methods of disguise and escape, it is a well-planned crime. After other investigation methods failed, they turned to video investigation, preparing to step on the spot from the suspect as a breakthrough. But the problem is that the number of videos that need to be viewed is too large. The videos that usually need to be viewed include videos from the month before the incident. Although there are only 5 closely related cameras around, they record video day and night, with a total of 3600 hours of video. Even if 10 people watch 12 hours a day, it takes a month to watch, the workload is too heavy, and it is easy to miss the target. Then how will the video analysis method based on video summarization and video retrieval in this embodiment be processed?

[0059] 1: Copy the original video from the monitoring platform or local storage medium, and upload the original video from the video conde...

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 discloses a video analysis method based on video abstraction and video retrieval, which includes the following steps of: 1) importing the original video; 2) judging whether the original video needs video enrichment treatment or not; 3) conducting video enrichment treatment; 4) conducting video retrieval treatment; 5) judging whether image enhancement treatment is necessary or not; 6) conducting image enhancement treatment; and 7) conducting portrait surveillance treatment. The video analysis method improves the efficiency of surveillance of huge amount of videos and reduces the possibility of omission of the targets.

Description

technical field [0001] The invention belongs to the technical field of video processing, and relates to a video analysis method, in particular to a method for automatically acquiring several key features of a person based on video summarization and video retrieval. Background technique [0002] With the development of video surveillance network, video investigation using surveillance video as clues to solve crimes has become an important means of public security criminal investigation and investigation, which has greatly cracked down on the criminal behavior of lawbreakers. [0003] However, the current video detection is mainly carried out by viewing the video with the naked eye, which is inefficient and easy to miss the target. Even if photos and video clips of suspected targets such as people are obtained, its further application can only be carried out through manual investigation, and the acquisition of detailed information remains at the empirical level without process...

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 Applications(China)
IPC IPC(8): G06F17/30H04N21/8549
Inventor 姚领众
Owner SUZHOU QIANSHI COMM TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap