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

Vehicle brand model identification method based on deep learning

A technology of vehicle brand and identification method, which is applied in the field of brand and model of motor vehicles, can solve the problems of fake license plates and fake license plates, and achieve the effect of enhancing the ability of expression recognition

Active Publication Date: 2016-04-13
广东冠网信息科技有限公司
View PDF3 Cites 32 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the process of detecting such cases, although the license plate can provide authoritative vehicle information, it is powerless to deal with fake or fake license plates.

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 brand model identification method based on deep learning
  • Vehicle brand model identification method based on deep learning
  • Vehicle brand model identification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] In order to clarify the content of the present invention, further description will be made in conjunction with the accompanying drawings and preferred embodiments.

[0019] Refer to attached figure 1 , a vehicle brand model recognition method based on deep learning overall framework includes the following steps:

[0020] S1. Prepare vehicle model training data set

[0021] The collection of high-definition bayonet points in different cities has prepared more than 20 million snapshots. After manual screening, they are accurately divided into more than 3,000 categories according to the brand and model of the vehicle, and a rich database of vehicle brand and model pictures covering various conditions has been established.

[0022] In order to adapt to the complex and changeable real scene, the present invention collected more than 20 million high-definition checkpoint pictures from different checkpoints in multiple cities, and then after several months of manual and prec...

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 vehicle brand model identification method based on deep learning. The method designs a firm deep convolution network structure by aiming at vehicle brand model identification, adopts the deep convolution network to extract the image characteristics of a vehicle face area under different scales and combines with a support vector machine to classify the image characteristics so as to automatically finish the vehicle brand model identification. The method is high in identification accuracy.

Description

technical field [0001] The invention relates to the field of image pattern recognition and intelligent transportation, in particular to a method for automatically identifying the brand and model of a motor vehicle in a high-definition bayonet snapshot in an intelligent transportation system. Background technique [0002] The rapid development of the economy has led to a sharp increase in the number of motor vehicles, and vehicle-related crimes have become more and more frequent. How to quickly lock suspect vehicles is very important. In the process of detecting such cases, although the license plate can provide authoritative vehicle information, it is powerless to counterfeit and fake license plates. In order to effectively solve this problem, the present invention proposes a brand-new method that can automatically identify the brand model of the vehicle in the high-definition bayonet snapshot, and the relevant departments combine the vehicle brand model information with oth...

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): G06K9/62G06N3/08
CPCG06N3/084G06V2201/08G06F18/2411
Inventor 曾凡涛
Owner 广东冠网信息科技有限公司
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