Vehicle identification model construction method and device and identification method and device

A technology of vehicle identification and construction method, which is applied in the field of vehicle identification model construction method and device, identification method and device, which can solve the problems of inspection personnel fatigue, human negligence, high work intensity, etc., and achieve the effect of convenient and accurate identification

Active Publication Date: 2020-06-19
广州华工邦元信息技术有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the current manual comparison of motor vehicle modification technology requires human eyes to carry out vehicle modification identification, and because it is necessary to obtain the announcement photos of the same model or the historical inspection appearance photos of the motor vehicle, it is necessary to go to another system to obtain them, and the workload is high. larger, less efficient
Under the long-term and high-intensity inspection work, the inspectors will inevitably be fatigued, which may lead to human negligence, thereby missing or misidentifying the modification status of the motor vehicle

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 identification model construction method and device and identification method and device
  • Vehicle identification model construction method and device and identification method and device
  • Vehicle identification model construction method and device and identification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] This embodiment discloses a method for constructing a vehicle identification model. The vehicle identification model constructed by this method can identify whether the vehicle is qualified. When the annual inspection of the vehicle is carried out in relevant parts, if the vehicle is modified or replaced with another vehicle, this The vehicle identification model constructed by the method of the embodiment can identify the vehicle as unqualified, and can realize the automatic or semi-automatic judgment of the vehicle modification project of the safety technical inspection under the premise of ensuring high recognition accuracy, which greatly reduces the labor cost. Increased inspection speed.

[0065] Such as figure 1 As shown, the method of this embodiment includes the following steps:

[0066] S101. Obtain a plurality of training samples, including positive training samples and negative training samples. In this embodiment, the ratio of the number of positive trainin...

Embodiment 2

[0097] This embodiment discloses a vehicle recognition model building device, such as Figure 4 As shown, the device includes:

[0098] The training sample obtaining module is used to obtain a plurality of training samples, including positive training samples and negative training samples; each training sample includes a first image and a second image; wherein, each positive training sample: the first image corresponds to a vehicle that has been published or Historical appearance photos, the second image is the appearance photo taken when the vehicle in the first image is qualified, and the label is the vehicle is qualified; each negative training sample: the first image is the corresponding published or historical appearance photo of the vehicle, and the second image is the first The exterior photos taken when the vehicle in the image is unqualified or the exterior photos taken by other vehicles are labeled as unqualified vehicles;

[0099] The first building module is used ...

Embodiment 3

[0114] This embodiment discloses a computing device, including a processor and a memory for storing executable programs of the processor. It is characterized in that, when the processor executes the program stored in the memory, the vehicle identification model construction method described in Embodiment 1 is implemented. as follows:

[0115] Obtain a plurality of training samples, including positive training samples and negative training samples; each training sample includes a first image and a second image; wherein, each positive training sample: the first image is a corresponding published or historical appearance photo of the vehicle, and the second image is the appearance photo taken when the vehicle in the first image is qualified, and the label is the vehicle is qualified; each negative training sample: the first image is the corresponding published or historical appearance photo of the vehicle, and the second image is the unqualified vehicle in the first image The app...

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 identification model construction method and device and an identification method and device. In the construction method, two compared images are input through a convolutional neural network; taking two image multi-dimensional feature comparison operation results output by the convolutional neural network model and two image manual preset feature comparison operation results output by the manual preset feature extraction model as input of a first full-connection neural network model; taking the output of the convolutional neural network model as the input of amanual preset feature key parameter calculation model, taking the output of the manual preset feature key parameter calculation model and the output of the first full-connection neural network model as the input of a second full-connection neural network model, and constructing a vehicle identification model; training a vehicle identification model through the training sample; based on the method,automatic or semi-automatic judgment of the vehicle refitting project for safety technology inspection can be realized, the labor cost is greatly reduced, and the inspection speed is increased.

Description

technical field [0001] The invention relates to the technical field of vehicle monitoring, in particular to a method and device for building a vehicle recognition model, and a recognition method and device. Background technique [0002] With the rapid development of the economy, people's demand for car purchases is increasing, and the number of cars in various places has been growing rapidly. In order to ensure road traffic safety, relevant departments need to carry out regular safety technical inspections on motor vehicles to ensure that motor vehicles are in a state of safe use. However, at the same time, lawbreakers and those who ignore the safety inspection of motor vehicles refit motor vehicles for private interests, ignoring the hidden dangers of motor vehicle safety caused by refitting, and may even bring hidden dangers to road traffic safety. Therefore, during the motor vehicle safety technical inspection, the relevant departments will judge the appearance modificat...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/08G06N3/045G06F18/241G06F18/214Y02T10/40
Inventor 吴祥淼张家豪葛武罗建康
Owner 广州华工邦元信息技术有限公司
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