Video-based detection and recognition system and method of vehicles

A vehicle detection and traffic technology, which is applied in the field of video-based traffic vehicle detection and recognition system, can solve the problems of low resolution accuracy and poor ability to distinguish traffic vehicles, etc., to expand the search step size, reduce image noise, and reduce search time. The effect of the step size

Inactive Publication Date: 2012-08-15
北京尚易德科技有限公司
View PDF7 Cites 80 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] For this reason, what the present invention aims to solve is the technical problem that the existing video-based vehicle detection has poor ability to distinguish traffic vehicles and low resolution accuracy under the conditions of significant background movement, vehicle adhesion and vehicle occlusion, and provides a better Vehicle discrimination ability, high-precision video-based traffic vehicle detection and recognition system and method

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
  • Video-based detection and recognition system and method of vehicles
  • Video-based detection and recognition system and method of vehicles
  • Video-based detection and recognition system and method of vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] A specific implementation manner of a video-based traffic vehicle detection and recognition system according to the present invention is given below, see figure 1 As shown, the video-based traffic vehicle detection and recognition system in this embodiment includes:

[0055] (1) Target feature database module 2, which stores the target feature database of traffic vehicle samples obtained according to the normalized type, angle type and vehicle type after pattern recognition training on the sample images of traffic vehicles, including a sample image preprocessing unit 21, The traffic vehicle sample image classification unit 22, the sample image feature extraction unit 23, the sample image pattern recognition training unit 24, and the target feature database storage unit 25, which are described in detail below.

[0056] The sample image preprocessing unit 21 cuts out the non-traffic vehicle sample image and the traffic vehicle sample image from the traffic video, and performs i...

Embodiment 2

[0079] On the basis of the foregoing embodiment, in step ② of the traffic vehicle detection and identification method, a specific method may also be used to detect the moving target area. In the step ③, the size of the moving target area can be approached by sequentially expanding the search window. The specific steps are as follows:

[0080] ②Read the traffic video image sequence, and the process of detecting the moving target area from the traffic video image sequence is as follows, see image 3 Shown:

[0081] T01: Read traffic video image sequence and perform relief calculation. The principle of relief calculation is to perform difference calculation between a pixel of the image and the adjacent upper left pixel plus a constant (in order to maintain the gray level of the image, the constant here Can be set to 128) to increase the brightness of dark areas. After performing the relief operation, the Gaussian mixture model is then used to model the background of the traffic vide...

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 video-based detection and recognition system and a method of vehicles. The system comprises a target characteristic database module, a moving target detection module and a vehicle recognition module. A vehicle sample target characteristic database is built to store data by virtue of the target characteristic database module. After a moving target zone is detected by the moving target detection module, the vehicle recognition module builds a search window and recognizes vehicles. The system and the method resolve the technical problems of poor vehicle distinguishing capability and low distinguishing accuracy of the video-based vehicle detection under the condition of obvious background movement, vehicle adhesion, vehicle occlusion and the like in the prior art. The video-based detection and recognition system and the method of the vehicles have the advantages of excellent vehicle distinguishing capability and high accuracy.

Description

Technical field [0001] The invention relates to the technical field of image processing and pattern recognition, in particular to a video-based traffic vehicle detection and recognition system and method. Background technique [0002] In recent years, with the rapid development of the electronics industry, especially new sensors and large-scale storage devices, video monitoring technology has become more and more popular for its flexibility and comprehensiveness. It takes real-time dynamic information as its core and uses computers, Modern high-tech such as control technology can flexibly and quickly process video images in real time to achieve real-time monitoring. Vehicle detection is an important link in the traffic system, providing information for traffic supervision and traffic control. Commonly used vehicle detection methods include coil detection, radar detection, and laser detection. The installation and maintenance work of coil detection is large, which damages the roa...

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): G06K9/62G06K9/00G08G1/017
Inventor 张凤春童剑军刘劲松
Owner 北京尚易德科技有限公司
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