Feature fusion-based vehicle behavior recognition method in urban traffic scene

A technology of urban traffic and identification methods, which is applied in the detection and research of vehicle violations, can solve problems such as identification methods that have not yet appeared, and achieve the effect of avoiding road traffic accidents and improving safety

Inactive Publication Date: 2017-05-31
SOUTHEAST UNIV
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the other studies are aimed at the extraction and classification of a vehicle behavior feature. At present, there is no recognition method for vehicle behavior that fuses vehicle features.

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
  • Feature fusion-based vehicle behavior recognition method in urban traffic scene
  • Feature fusion-based vehicle behavior recognition method in urban traffic scene
  • Feature fusion-based vehicle behavior recognition method in urban traffic scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Below in conjunction with specific implementation mode, this technical solution is further described:

[0038] Step 1: Use median filtering to preprocess the traffic scene images recorded by the electronic police system at road intersections to eliminate the noise contained in the images. Light compensation is then used to eliminate the effects of unstable lighting or dark weather on the image.

[0039] In the first step, median filtering is used to denoise the urban traffic scene image, and light compensation is used to preprocess the urban traffic scene image. According to different image characteristics, different filter functions are selected. In this patent, the median filter is used as the filter function to preserve the details of the image. Use formula (1) to carry out median filter processing on the image.

[0040]

[0041] A is the filtering window, X ij , Y ij are the original image and the processed image, respectively. For the filtered image, this p...

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 feature fusion-based vehicle behavior recognition method in an urban traffic scene. An HOG feature and an LBP feature are in head-tail serial connection to form a joint feature as a vehicle behavior fusion feature, a SVM (support vector machine) classifier is adopted, and vehicle behaviors are classified and recognized. According to the feature fusion-based vehicle behavior recognition method in the urban traffic scene disclosed by the invention, abnormal vehicle behaviors can be recognized, a frontier foundation is laid for an automatic traffic event detection system, and an important role is played in improving the vehicle driving safety and avoiding a road traffic accident.

Description

technical field [0001] The invention patent relates to the field of traffic incident detection, especially the detection and research of vehicle violations. Background technique [0002] The annual statistical report on global traffic accidents shows that most road traffic accidents are caused by vehicle abnormalities, such as running red lights, vehicles pressing the line, and speeding. Vehicle behavior detection plays an important role in ensuring traffic safety, improving vehicle driving safety, and avoiding traffic accidents. [0003] Vehicle behavior recognition is the first step and an important part of automatic traffic incident detection system. Traditional vehicle behavior detection technologies such as ring detection and microwave detection have been gradually eliminated due to the need to excavate the road surface and affect traffic, which often cost a lot. The image processing detection technology uses computer vision technology to perceive the surrounding scen...

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): G08G1/017G08G1/01G06K9/62G06K9/46G06K9/32G06K9/00
CPCG08G1/0104G08G1/017G06V20/584G06V20/62G06V10/443G06V10/50G06V2201/08G06V20/625G06F18/2411
Inventor 赵池航赵敏慧齐行知
Owner SOUTHEAST UNIV
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