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

Checkpoint vehicle re-identification method based on dual network structure

A network structure and re-identification technology, which is applied in the field of bayonet vehicle re-identification based on a dual network structure, can solve problems such as the inability to solve vehicle re-identification problems

Active Publication Date: 2019-08-02
广州紫为云科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of vehicle re-identification when the vehicle is blocked, removed or even forged license plate can not be solved by the above prior art, the present invention provides a bayonet vehicle re-identification method based on dual network structure

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
  • Checkpoint vehicle re-identification method based on dual network structure
  • Checkpoint vehicle re-identification method based on dual network structure
  • Checkpoint vehicle re-identification method based on dual network structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as figure 1 , 2 Shown, the method provided by the invention comprises the following steps:

[0026] S1. Obtain a part of the captured vehicle images from the database of the bayonet system as a training set;

[0027] S2. For each vehicle image in the training set, it is divided into two regions, the upper half region and the lower half region;

[0028] S3. Constructing the first neural network and the second neural network, the first neural network and the second neural network carry out the study of the apparent features on the upper half area and the lower half area of ​​the vehicle image in the training set respectively, wherein the first neural network is used for Learning different appearance features of vehicles of the same model, the second neural network is used to learn different appearance features of vehicles of different models;

[0029] S4. Each vehicle image in the training set obtains corresponding apparent features after being learned by the firs...

Embodiment 2

[0053] This embodiment has carried out concrete experiment, and experimental result is as shown in the figure, image 3 Shown is the CMC evaluation standard performance curve, wherein our curve represents the method adopted in the present invention, and it can be seen that the curve is at the top of the curve shown in other methods, indicating that the effect achieved by this method is the best. Figure 4 Shown is an example of re-identification retrieval of an input vehicle image, the first column of each row is the query image, and the other columns are the corresponding re-result matching scores top-1 to top-5. From these results, it can be seen that the hit rate of the re-identification result is relatively high.

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

According to the method, extraction of the appearance characteristics of vehicle images and inquiring images in a gate system database is performed by using a first neural network and a second neural network which are trained, and then the similarity is calculated based on the extracted appearance characteristics so as to obtain the reidentification result. Compared with the methods in the prior art, vehicle reidentification in case of fake vehicle plate, removing and even forgery license plate can be realized by the reidentification method.

Description

technical field [0001] The invention relates to the field of intelligent traffic monitoring, and more specifically, to a method for re-identifying bayonet vehicles based on a dual network structure. Background technique [0002] In recent years, with the advancement of my country's safe city, intelligent transportation and other projects, the images of motor vehicles taken at traffic checkpoints have left image data for most cases, which has brought great convenience to the police in solving cases. The bayonet vehicle pictures taken in the bayonet system are frontal photos of vehicles with relatively consistent angles, and generally include information such as the vehicle's license plate, front window, front lights, and bumper. [0003] Today, large surveillance image and video databases have an exploding demand for vehicle search and re-identification (Re-ID) in public safety systems. The license plate is naturally the unique ID of the vehicle, and license plate recognitio...

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 Patents(China)
IPC IPC(8): G08G1/017
CPCG08G1/0175
Inventor 赖剑煌谷扬
Owner 广州紫为云科技有限公司
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