An implementation method of a toll lane vehicle feature recognition system based on video

A vehicle feature and identification system technology, which is applied in the implementation field of the toll lane vehicle feature identification system, can solve the problems that the identification method cannot take into account the accuracy, real-time and economy, and cannot meet the requirements of accurate and real-time identification for large-scale deployment, etc. Achieve the effect of improving real-time performance and network parameter usage efficiency, saving time consumption, and improving real-time performance

Active Publication Date: 2019-01-11
NANJING UNIV
View PDF6 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The problem to be solved by the present invention is: in view of the requirements for vehicle feature recognition in toll lanes, the recognition method adopted by the existing r

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
  • An implementation method of a toll lane vehicle feature recognition system based on video
  • An implementation method of a toll lane vehicle feature recognition system based on video
  • An implementation method of a toll lane vehicle feature recognition system based on video

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0049] The present invention provides a method for implementing a video-based toll lane vehicle feature recognition system, which can effectively realize vehicle detection and tracking, avoid repeated feature recognition of the same vehicle, and improve the accuracy and real-time performance of vehicle feature recognition.

[0050] The present invention will be further described below with reference to the drawings and examples.

[0051] The technical scheme of the present invention is: a method for implementing a vehicle feature recognition system of a toll lane based on video. Such as figure 1 As shown, it specifically includes three parts, namely vehicle detection, vehicle tracking and vehicle feature recognition. The steps are as follows:

[0052] Step S1: For each frame of picture, such as Figure 7 As shown in (a), the vehicle detection based on the deep learning method is performed, and the feature maps of the detected vehicles are normalized and saved, and the location info...

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 an implementation method of a toll lane vehicle feature recognition system based on video, the method comprising three modules: a vehicle detection module, a vehicle tracking module and a vehicle feature recognition module. The invention uses a SSD target detector for detection, uses characteristic map histogram comparison and distance comparison method for tracking, and uses a convolutional neural network to carry out vehicle characteristic identification. The method of the invention can effectively identify features, can run in real time, reduces the repeated consumption of computing resources, and improves the accuracy of the system.

Description

Technical field [0001] The invention belongs to the technical field of image processing and computer vision detection, relates to the application of target detection algorithms and deep learning algorithms in vehicle detection, and is a method for implementing a video-based toll lane vehicle feature recognition system. Background technique [0002] The construction of expressways in my country is developing rapidly, and expressway transportation has become one of the main methods of land cargo transportation. Expressway transportation has the advantages of fast and stable. However, the phenomenon of toll evasion in toll lanes on expressways has become increasingly serious. Many vehicles are obviously large buses, but they install the ETC toll device for cars, and they are charged according to the toll standard of cars when they pass the toll lane. With the increasing maturity of deep learning and target detection technology, automatic detection and feature recognition of vehicl...

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): G06K9/00G06N3/04G06N3/08G07B15/06
CPCG06N3/08G07B15/06G06V20/584G06N3/045
Inventor 阮雅端赵博睿陈林凯葛嘉琦陈启美
Owner NANJING 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