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

Vehicle detecting and tracing method based on video technique

A technology of vehicle detection and video technology, which is applied in the field of traffic monitoring and can solve complex and impractical problems.

Inactive Publication Date: 2008-08-27
SOUTHEAST UNIV
View PDF0 Cites 73 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Vehicle tracking methods based on feature points and snake active contour models are sensitive to occlusion between vehicles, while vehicle tracking methods based on 3D models need to build 3D models for a large number of vehicles, which is too complicated and impractical

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 detecting and tracing method based on video technique
  • Vehicle detecting and tracing method based on video technique
  • Vehicle detecting and tracing method based on video technique

Examples

Experimental program
Comparison scheme
Effect test

specific example 1

[0076] ①Background initialization

[0077] A camera is set up to collect 15 minutes of continuous sequence images for a specific traffic scene, the collection frequency is 30 frames / s, and the image size is 240×320 pixels. Perform an average calculation on all collected images, namely:

[0078] B 0 = ( x , y ) = 1 450 Σ i = 1 450 Q i ( x , y )

[0079] Among them, B 0 represents the initial background image, B 0 (x, y) means B 0 The gray level of the pixel whose coordinates are (x, y), Q i Indicates the i-th frame image collected, Q i (x, y) means Q i The gray level of the pixel whose coordinates are (x, y) ...

specific example 2

[0135] Detection and Processing of Occlusion Phenomena Between Vehicles

[0136] In Example 1, there are fewer vehicles in the traffic scene. In this example, another set of sequence images with a large traffic volume is taken. When the traffic volume is large, there may be vehicles between vehicles, and the occlusion phenomenon between vehicles will cause labeling errors, which will reduce the accuracy of vehicle detection and tracking, so it is necessary to detect and segment the occlusion phenomenon,

[0137] (1) Detection of occlusion between vehicles

[0138] For a single vehicle, the minimum rectangular frame [x min x max the y min the y max ] as the position of the car, the current image P i-1 All the vehicles in are represented by their respective smallest rectangular boxes, and the labels of the rectangular boxes are consistent with the labels of the blocks in the box. All the rectangular boxes are compared and judged pairwise. If there is an overlap between t...

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 provides a method for detecting and tracking vehicles through processing a video image of a traffic scene, comprising the following steps of: collecting images of the traffic scene; deblocking a traffic image according to 8 multiplied by 8 pixels; initiating and continuously updating a background image; setting a virtual detection line with a width of 8 pixels vertical to a direction of a traffic lane at the entrance of the traffic lane; detecting the vehicles through calculating the variation of a gray scale of blocks on the virtual detection line relative to the background image; labeling the blocks belonging to the regions of the vehicles by using a sequence that the vehicles reach the detection line; receiving initial positions of labels of the vehicles; calculating motion vectors of the vehicles by combining a three-step method and a full search method and constantly updating the positions of the labels of the vehicles by using the motion vectors so as to implement the tracking of vehicles. The method also performs detection and splitting against an occlusion occurrence between vehicles in a complicated traffic scene, thereby having the advantages of high accuracy of detection and tracking and good real-time performance.

Description

technical field [0001] The invention relates to a vehicle detection and tracking method based on video technology, the purpose of which is to detect vehicles existing in a traffic scene and continuously track the position of the vehicles, belonging to the technical field of traffic monitoring. Background technique [0002] With the continuous development of the economy and the rapid progress of the urbanization process, the number of motor vehicles in my country has increased sharply, and traffic problems have become more and more prominent, such as increasing traffic accidents and frequent traffic congestion. In order to solve these problems, since the 1990s, countries around the world have started to build intelligent transportation systems (ITS). ITS organically combines people, vehicles and roads by using advanced information technology. [0003] An important subsystem in ITS is the traffic information collection system, and vehicle detection is one of the important fun...

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
IPC IPC(8): G06T7/20G06T7/00G06K9/00G08G1/01G08G1/123
Inventor 路小波刘斌朱周
Owner SOUTHEAST UNIV
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