Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Pedestrian detection method based on video monitoring

A pedestrian detection and video surveillance technology, applied in the field of pattern recognition, can solve the problems of inability to apply video surveillance and high false detection rate, and achieve the effects of fast detection speed, reduction of false detection rate, and reduction of complexity.

Active Publication Date: 2010-11-17
HUNAN CHUANGHE FUTURE TECH CO LTD
View PDF2 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing pedestrian detection methods such as haar feature and Adaboost classifier (References: P.Viola, M.J.Jones, and D.Snow, "Pedestrian Detection Techniques Based on Movement and Appearance Patterns," International Conference on Computer Vision, Vol. 1, 734-741 pages, 2003), although this method has achieved good results, it has the disadvantage of high false detection rate and cannot be applied to actual video surveillance

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
  • Pedestrian detection method based on video monitoring
  • Pedestrian detection method based on video monitoring
  • Pedestrian detection method based on video monitoring

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described in detail below with reference to the drawings and embodiments.

[0041] figure 1 It is a schematic flow diagram of the pedestrian detection method based on video surveillance proposed by the present invention, which includes a training module and a detection module. First, the known well-classified pedestrian samples are used to generate an Adaboost cascade classifier and a support vector machine classifier that can detect unknown pedestrian samples with different accuracy using the extended gradient histogram feature. In the detection module, the input video sequence first determines the candidate area of ​​the pedestrian through the frame difference method, and then uses the Adaboost cascade classifier to quickly determine the location of the pedestrian. The support vector machine classifier further verifies the detection results. The basic steps of the specific training module are as follows:

[0042] Step 1: Normalize th...

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 pedestrian detection method based on video monitoring, which comprises the following steps of: rapidly detecting a pedestrian by utilizing an expanded gradient histogram characteristic and an Adaboost algorithm, and then further identifying and verifying the detected pedestrian by utilizing the gradient histogram characteristic and a support vector machine. In the invention, experiments based on a standard pedestrian database indicate that the method not only can greatly reduce the detection time, but also markedly improves the detection rate. As one of key technologies of target detection, pedestrian detection has broad application prospect in the fields of video monitoring safety, intelligent traffic management and the like.

Description

Technical field: [0001] The invention relates to the technical field of pattern recognition, in particular to a pedestrian detection method based on video surveillance. Background technique: [0002] Pedestrian detection refers to locating all pedestrian positions in an image or video and marking their positions. A broader concept can be understood as target detection or target recognition. Compared with traditional infrared or radar-based technologies, the reliability, convenience and low cost of image or video-based pedestrian detection technology has attracted more and more attention, and is widely used in video surveillance, autonomous vehicle driving and other fields . [0003] Existing pedestrian detection methods such as haar features and Adaboost classifiers (References: P.Viola, MJ Jones, and D. Snow, "Pedestrian Detection Technology Based on Movement and Appearance Patterns," International Computer Vision Conference, Volume 1, 734-741 pages, 2003). Although this method...

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): G06K9/62G06T5/40H04N7/18
Inventor 吴希贤
Owner HUNAN CHUANGHE FUTURE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com