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

A method and system for cross-video target retrieval and collision in video surveillance system

A target and video technology, applied in the field of video investigation, can solve problems such as the inability to obtain target frequency and the inability to quickly retrieve target feature information, and achieve the effects of improving case handling efficiency and saving manpower

Active Publication Date: 2022-12-02
成都神州数码索贝科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a cross-video target retrieval and collision method and system in a video surveillance system, which is used to solve the problems in the prior art that cannot be quickly retrieved, cannot obtain target frequency and quickly locate targets due to unknown target feature information

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 system for cross-video target retrieval and collision in video surveillance system
  • A method and system for cross-video target retrieval and collision in video surveillance system
  • A method and system for cross-video target retrieval and collision in video surveillance system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A cross-video target retrieval and collision method in a video surveillance system, comprising:

[0042] Step S1: Log in to the media metadata intelligent processing server, create a case and upload surveillance video files in the case;

[0043] Step S2: Initiate surveillance video analysis tasks and target frequency calculation tasks;

[0044] Step S3: extracting all moving objects of the surveillance video file separately;

[0045] Step S4: collide with the extracted moving target to obtain the target frequency related to the case in the surveillance video, the target frequency includes the target frequency of people and the frequency of non-motor vehicle targets;

[0046] Step S5: display the target frequency, and provide key information to case handlers.

[0047] Described step S4 comprises:

[0048] Step A, read the feature data of the moving target from all the moving targets extracted, the number S of moving targets contained in the T monitoring video files T...

Embodiment 2

[0068] combined with figure 1 As shown, a system for cross-video object retrieval and collision in a video surveillance system includes a media metadata intelligent processing server, a post-event content processing server, an intelligent metadata server and a client, wherein:

[0069] The media metadata intelligent processing server is configured to allow the client to log in and provide task management, task distribution, case management and user management services;

[0070] The post-event content processing server is configured to upload the surveillance video file and extract all the moving objects of the surveillance video file separately;

[0071] The intelligent metadata server is configured to collide with the moving target extracted by the post-event content processing server, obtain the target frequency, and return it to the client; the target frequency includes the human target frequency and the non-motor vehicle target frequency;

[0072] The client is configured...

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 cross-video target retrieval and collision method and system in a video investigation system, comprising: logging into a media metadata intelligent processing server, creating a case and uploading a monitoring video file in the case; initiating a monitoring video analysis task and target frequency Calculation tasks; extract all the moving targets of the surveillance video file separately; collide the extracted moving targets to obtain the target frequency related to the case in the surveillance video, the target frequency includes the target frequency of people and non-motor vehicle targets; display the target frequency, Provide key information to investigators. The invention extracts the moving target from the uploaded monitoring video file, and after the target collides with the case-related video, quickly obtains the frequency of the owner target and non-motor vehicle target in the case-related video file, and then assists the case-handling personnel to quickly lock The goal is to improve the efficiency of case handling personnel, and effectively save manpower and time costs.

Description

technical field [0001] The invention relates to the technical field of video investigation, in particular to a method and system for cross-video target retrieval and collision in a video investigation system. Background technique [0002] Various existing video investigation application technologies mainly analyze the characteristics of moving targets in the video, and then the investigators quickly retrieve them through the target characteristics. However, in many cases, the investigators do not know any characteristic information of the target, but only know that the target has appeared many times. At this time, using the traditional video detection function will have no effect, and the frequency of the target in the relevant video files of the case cannot be obtained, resulting in Cannot quickly locate the target. Contents of the invention [0003] The purpose of the present invention is to provide a cross-video target retrieval and collision method and system in a vid...

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): G06F16/783G06F16/75G06F16/74H04N7/18
CPCG06F16/784G06F16/75G06F16/74H04N7/18
Inventor 宋擘庄永姜峰李竞
Owner 成都神州数码索贝科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com