Intelligent video monitoring method and system based on computer vision analysis technology

An intelligent video surveillance and computer vision technology, applied in computer parts, computing, instruments, etc., can solve the problems of high false alarm rate, omission, inconvenient search and playback, etc., and achieve the effect of reducing labor intensity

Active Publication Date: 2017-10-03
SHANGHAI BAOSIGHT SOFTWARE CO LTD
View PDF10 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] (1) The existing video surveillance system requires the monitoring personnel to always pay attention to the monitoring screen, and it is easy to miss some important events due to the fatigue of the monitoring personnel.
[0005] (2) Although some video surveillance systems have some automatic video analysis functions, they are often relatively elementary, with a high false alarm rate, and an alarm will be generated if there is a slight disturbance, which basically has no practical value
[0006] (3) The existing video monitoring system cannot automatically record the events of interest in the video, and it is very inconvenient to find and play back afterwards; it is unable to make statistics on the events in the video and provide statistical reports to decision makers

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
  • Intelligent video monitoring method and system based on computer vision analysis technology
  • Intelligent video monitoring method and system based on computer vision analysis technology
  • Intelligent video monitoring method and system based on computer vision analysis technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] Embodiment 1: Passenger flow statistics in public places.

[0095] Hardware requirements: The camera is installed facing the aisle or doorway. The horizontal direction of the camera is at an angle of about 30 degrees to the ground. Try not to appear other obvious moving objects (such as vehicles, etc.) except pedestrians in the field of view.

[0096] After the system hardware and software configuration is complete, open the analysis service configuration program, select the video channel for passenger flow counting, use the drawing area function to draw a quadrilateral area in it as the pedestrian detection area for passenger flow counting; use the area direction function to draw in the area An arrow, pedestrians walking in the direction of the arrow is regarded as entering the area, and walking against the direction of the arrow is regarded as leaving the area; use the function of drawing far and near human body frames to draw a rectangle similar in size to the distant...

Embodiment 2

[0098] Example 2: Anti-intrusion monitoring of industrial sites

[0099] Hardware requirements: The camera is facing a place that is not allowed to enter at random, and other obvious moving objects (such as vehicles, etc.) other than pedestrians should not appear in the field of vision as much as possible. If the camera is installed in a place with lights, frequent changes in lights should be avoided as much as possible .

[0100] After the system hardware and software configuration is complete, open the analysis service configuration program, select the video channel for intrusion detection, use the drawing area function to draw one or more polygonal areas in it as the intrusion detection area; use the function of drawing far and near human body frames in the video Draw a rectangular frame with a size similar to that of a distant (small) pedestrian, and a rectangular frame with a similar size to a nearby (large) pedestrian; finally, select to enable the intrusion detection fu...

Embodiment 3

[0102] Embodiment 3: Crowd density estimation of rail transit platform

[0103] Hardware requirements: The camera is installed facing the rail transit platform, and the field of view covers the area where crowd density estimation is to be performed.

[0104] Training phase: Due to the particularity of the crowd density estimation algorithm, each camera needs to be trained once before it can be used (each camera only needs to be trained once when the position remains unchanged, and it is also possible without training, but the estimated accuracy rate will get worse). In the training phase, after the system hardware and software configuration is complete, open the analysis service configuration program, select the video channel for crowd density training, and use the drawing area function to draw a polygonal area in it as the crowd density estimation area; after that, in the "Algorithm Settings" dialogue In the "Crowd Density" tab of the box, select the required crowd density t...

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 present invention provides an intelligent video monitoring method and system based on computer vision analysis technology. The method comprises: a video acquisition step: acquiring a monitoring video of a fixed scene by using a camera with a fixed stand; a video analysis step: analyzing the monitoring video to obtain an analysis result; and a monitoring management step: displaying the analysis result to a person or alarming. According to the method, the monitoring video is automatically analyzed by using computer vision technology, and specific information in the video can be further extracted, and alarm information is automatically generated when a particular event happens and recorded into the database, so that intelligence of video monitoring is improved, and labor intensity of monitoring personnel is greatly decreased.

Description

technical field [0001] The invention relates to video monitoring, in particular to an intelligent video monitoring method and system based on computer vision analysis technology. Background technique [0002] Intelligent video surveillance is a branch of the application of computer vision technology in the field of security, and it is an intelligent monitoring technology based on target behavior. Traditional video surveillance only provides original video images or only uses some primary video analysis techniques; the intelligent video surveillance system first separates the background from the target in the scene, identifies the real target, and removes background interference (such as shaking leaves, water waves, lights, etc.) change), and then analyze and track the target behavior in the camera scene, and automatically give an alarm message when the set behavior occurs. Compared with traditional video surveillance, intelligent video surveillance can realize full automati...

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): G06K9/00
CPCG06V20/44G06V20/40G06V20/53
Inventor 姚文韬韩帅峰
Owner SHANGHAI BAOSIGHT SOFTWARE CO LTD
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