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

A vehicle classification flow detection method based on dynamic characteristic extraction

A technology of dynamic feature and flow detection, which is applied in the field of computer vision, can solve the problems of vehicle classification flow detection, etc., and achieve the effect of fast calculation speed and good recognition rate

Inactive Publication Date: 2016-11-09
马平 +2
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Vehicle flow detection technology based on video image processing technology has become a research hotspot at home and abroad, but there is no mature method that can be applied to the classification and real-time detection of vehicle flow
At present, the domestic vehicle flow detection system can only detect the total traffic flow, and cannot detect the classified flow of vehicles according to the vehicle type.

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
  • A vehicle classification flow detection method based on dynamic characteristic extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Specific embodiments of the present invention will be further described in detail below.

[0023] Such as figure 1 As shown, a system corresponding to a vehicle classification flow detection method based on dynamic feature extraction in the present invention includes: image preprocessing, background selection, dynamic background difference, vehicle area calculation, vehicle classification flow detection, and establishment of a standard vehicle classification library.

[0024] Image preprocessing is to segment the lanes and detect vehicles according to the lanes. The irrelevant lane is blackened, and the part of other lanes in the detection area is blackened, so as to extract the lane to be detected.

[0025] The background selection is based on whether there are vehicles in the background to judge the validity of the background.

[0026] The dynamic background difference is to make the difference between the detection area of ​​the current picture and the detection ar...

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 belongs to the field of computer vision, and especially relates to video image processing and identification of moving vehicles in the field of computer vision. The invention discloses a vehicle classification flow detection method based on dynamic characteristic extraction. The method is characterized in that (1) background selection and background dynamic updating are carried out on original video images; (2), dynamic feature extraction is carried out on moving vehicle targets; and (3) classification flow detection is carried out on moving vehicles through utilization of a standard vehicle classification database. According to the vehicle classification flow detection method based on the dynamic characteristic extraction, pre-classification is carried out through utilization of area characteristics; a relatively high recognition rate with regard to different vehicle models is achieved; the calculating speed is fast; moving vehicle classification and identification can be carried out in real time; and the vehicle classification flow detection method can be applied to real time vehicle classification flow detection systems such as highways.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to video image processing and recognition of moving vehicles therein. Background technique [0002] Vehicle flow detection refers to the process of computer analyzing and identifying the characteristics of moving vehicles based on the data collected by video image acquisition equipment. It involves disciplines such as video image processing and recognition, is an important research direction in the field of computer vision, and has extensive and important applications in modern traffic management. The intelligent transportation system effectively integrates advanced information technology, data communication transmission technology, electronic sensing technology, electronic control technology and computer processing technology into the entire transportation management system. Vehicle flow detection is an important part of the intelligent transportation system. It is also an important...

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): G08G1/017G08G1/065G06K9/00
CPCG08G1/0175G08G1/065G06V20/584
Inventor 马平穆宇黄曦
Owner 马平
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