Deep learning-based pedestrian target tracking method

A pedestrian target and deep learning technology, applied in optical device exploration, signal transmission systems, instruments, etc., can solve problems such as difficult to organize and messy information, and achieve the effect of improving quality, helping arrest work, and conveniently sorting out information

Inactive Publication Date: 2019-08-23
SHENZHEN POLYTECHNIC
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a pedestrian target tracking method based on deep learning to solve the problem that when the appearance of people changes in the above-mentioned background technology, the system will re-create a user folder if it cannot recognize it, resulting in messy information and difficult Organized questions

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
  • Deep learning-based pedestrian target tracking method
  • Deep learning-based pedestrian target tracking method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.

[0033] see Figure 1-2 , an embodiment provided by the present invention: a pedestrian target tracking method based on deep learning, including a control module 1, a wireless data transmission module 2, a face recognition module 3, a camera 4, a server 5, an infrared human body sensor 6, USB port 7, Beidou module 8 and voice broadcast module 9;

[0034] Wherein, the control module 1 is electrically connected to the server 5 in two directions through the wireless data transmission module 2;

[0035] The control module 1 is electrically connected to the public security alarm platform in two directions through the wireless data transmission module 2;

[0036] The cont...

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 deep learning-based pedestrian target tracking method, which relates to the technical field of pedestrian target tracking methods and solves the problem that when the appearance of a person changes, the system cannot perform recognition, a user folder is re-built, and messy information is caused. The method comprises the following steps: 1, the image information of persons prohibited from entering the area and wanted criminals on the whole network is inputted; 2, an infrared human body sensor detects whether a person enters the area; 3, a camera is used for face acquisition; 4, image analysis is carried out; 5, information comparison is carried out; 6, comparison with stored ordinary people is carried out, and the latest information is stored to the correspondingfolder; 7, if no person is matched, a folder is built for the information and stored; 8, match with the forbidden entry persons is carried out, and the staff is reminded through voice broadcasting; and 9 match with the wanted criminals is carried out, the staff is reminded through voice broadcasting, and positioning and video information is sent for alarming.

Description

technical field [0001] The invention relates to the technical field of pedestrian target tracking methods, in particular to a pedestrian target tracking method based on deep learning. Background technique [0002] At present, most of the pedestrian target tracking methods are suitable for road monitoring systems. By identifying, capturing and saving the shape and appearance of pedestrians, the status of pedestrians on the road is recorded, which is convenient for the security work of the community, and the information statistics of personnel entering and exiting are more accurate. intuitive. [0003] However, the pedestrian target tracking methods currently on the market can only realize the single-time storage of personnel capture and entry and exit information, but the monitoring system automatically updates the personnel shape and appearance information. After a period of time, when people's appearance changes, If the system cannot identify it, it will rebuild a user fol...

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): G08C17/02H04N7/18G08B13/196G06K9/00G01V8/10
CPCG08C17/02H04N7/18G08B13/196G01V8/10G06V40/172G06V40/103
Inventor 连国云孙宏伟
Owner SHENZHEN POLYTECHNIC
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