Vehicle behavior recognition method

A recognition method and vehicle technology, applied in vehicle behavior recognition, extracting and matching differential image features to identify vehicle behavior, can solve the problems of high requirements in the process of building a feature library, large amount of calculation for feature extraction, weak scalability, etc., to avoid background Interference problem, small amount of computation, effect of suppression

Active Publication Date: 2014-08-20
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method has high requirements for the establishment of the feature library. It needs to collect various vehicle images of different poses, different models, and different scenes. The scalability is weak. In addition, the amount of calculation for feature extraction in each frame of image is large.

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
  • Vehicle behavior recognition method
  • Vehicle behavior recognition method
  • Vehicle behavior recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The technical solution of the invention will be described in detail below in conjunction with the accompanying drawings: the present invention extracts the horizontal edge of the differential image as an image feature, performs binarization processing on the horizontal edge and screens the vehicle feature descriptor, and matches the vehicle feature descriptor to identify vehicle behavior , the process is as figure 1 shown.

[0030] Step 1. Preprocess the image taken on the road to obtain a normalized image. Image preprocessing includes: image grayscale, image rotation and scaling, effective area extraction, and median filtering:

[0031] (1) Image grayscale is determined according to the video format: if the input is in YUV format, then directly extract the Y component; if the input is in RGB format, then follow the formula GrayValue=(306×R+601×G+117×B)> >10 Calculate the gray value of each pixel;

[0032] (2) For the detection area shown in Figure 2(a), the input ima...

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 vehicle behavior recognition method, particularly relates to a method for extracting matching difference image features to recognize vehicle behaviors, and belongs to the technical field of intelligent traffic. According to the vehicle behavior recognition method, differential treatment is performed on a pretreated image, the horizontal edge of the differential image is extracted to generate vehicle feature descriptors, and the motion trail of a vehicle is determined through two adjacent vehicle feature descriptors successfully matched; afterwards, vehicle behaviors are analyzed according to the motion trail of the vehicle. The method has an excellent inhibiting effect on all types of interference in a complex scene. Meanwhile, the amount of calculation is small, and reliability is high. Besides, the problem of background interference in motion target detection and the problem that the amount of calculation for feature extraction in a single image is large are effectively avoided.

Description

technical field [0001] The invention discloses a vehicle behavior recognition method, in particular a method for extracting and matching difference image features to recognize vehicle behavior, and belongs to the technical field of intelligent transportation. Background technique [0002] Among many intelligent transportation system applications, the video-based vehicle behavior recognition and analysis system is more and more favored by the traffic management department due to its advantages of convenient installation and maintenance and high reliability. Correspondingly, the video-based vehicle behavior recognition technology The product market demand is expanding day by day, and the application is more and more extensive. [0003] Vehicle behavior recognition is the process of discriminating the vehicle's motion behavior and trajectory through real-time analysis of video sequences. Vehicle behavior recognition technology mainly involves steps such as vehicle image acquis...

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
Inventor 孙涵潘铭星刘宁钟黄元元
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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