Automatic detection method of double-mode masked person event based on video feature statistics

A video feature and automatic detection technology, which is applied to computer components, character and pattern recognition, calculation, etc., can solve the problems of insufficient processing speed, low recognition rate, and inability to meet real-time monitoring, and achieve waste of human resources and simple calculation methods , high compatibility effect

Active Publication Date: 2021-08-10
SOUTH CHINA UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These intelligent video surveillance technologies are all developed for specific problems. There is no real-time identification technology for masked people in video surveillance, and these technologies often have insufficient processing speed and low recognition rate, which cannot meet the requirements of real-time monitoring.

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
  • Automatic detection method of double-mode masked person event based on video feature statistics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The implementation of the present invention will be further described below in conjunction with the accompanying drawings, but the implementation of the present invention is not limited thereto. If there are any processes that are not specifically described in detail below, those skilled in the art can refer to the prior art.

[0039] Such as figure 1 , the main flow of the dual-mode masked person event automatic detection method based on video feature statistics includes the following steps:

[0040] (a) read in the video file, scale the video image, and convert it to a grayscale image;

[0041] (b) obtaining a moving object foreground image;

[0042] (c) Find the largest rectangular outline of the moving object by calculating the position of the coordinates of the midpoint of the outline and the overlap ratio with the moving foreground of the previous frame;

[0043] (d) Detecting the movement process obtained in step (c), obtaining the head position information for...

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 a dual-mode masked person event automatic detection method based on video feature statistics, including: after obtaining the source video image, first zooming the video frame and converting it into a grayscale image, and then obtaining the largest object moving foreground rectangular frame, Then roughly locate the head area, then obtain the face position information, then estimate the mouth area in the obtained face range, cut the mouth area to narrow the range, then calculate the gradient map, and calculate the connected domain on the basis of the obtained gradient map The number is used to preliminarily judge whether it is a masked person, and then calculate the proportion of the area of ​​the first two connected domains to further judge whether it is a masked person. The present invention has no specific requirements on video scenes. In addition, the calculation method of the present invention is simple and efficient, capable of real-time processing, and can be used for real-time investigation and solving of crimes. At the same time, the information of suspicious masked persons is saved, and it can also provide first-hand information for obtaining evidence after a crime has occurred.

Description

technical field [0001] The invention generally relates to the field of computer intelligent monitoring video processing, in particular to a dual-mode masked person event automatic detection method based on video feature statistics. Background technique [0002] Since the reform and opening up, driven by the rapid development of the national economy and the improvement of people's living standards, my country's security industry has flourished and gradually grown up. After more than 30 years of development, China's security industry has formed a huge industry with complete categories and advanced technologies. system, and has maintained a good momentum of rapid and healthy development. The use of safety protection is very extensive, and the demand is constantly expanding. No matter in large or collective places such as banks, enterprises, transportation, communities, military, or personal residences, the requirements for safety protection are increasing day by day. With the ra...

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): G06K9/00
CPCG06V40/172G06V20/42G06V20/46
Inventor 黄翰王琥梁椅辉郝志峰
Owner SOUTH CHINA UNIV OF 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