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

Vehicle damage identification method and device, equipment and storage medium

A recognition method and vehicle technology, applied in the field of computer vision, can solve the problem of low vehicle accuracy

Pending Publication Date: 2021-06-15
创新奇智(上海)科技有限公司
View PDF14 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the biggest difficulty in intelligent damage assessment is that the identification of vehicle damage requires high precision, which requires not only the precise location of the damage, but also the judgment of the damage category. However, the accuracy of vehicle damage in the existing damage assessment schemes is not high.

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 damage identification method and device, equipment and storage medium
  • Vehicle damage identification method and device, equipment and storage medium
  • Vehicle damage identification method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] see figure 1 , figure 1 It is a schematic flowchart of a vehicle damage identification method disclosed in the embodiment of the present application. Such as figure 1 As shown, the method of the embodiment of the present application includes steps:

[0063] 101. Obtain the damage picture of the vehicle to be monitored;

[0064] 102. Extract the image features of the damage picture of the vehicle to be monitored according to the neural network;

[0065] 103. Determine several damage candidate regions in the damage picture according to the image features;

[0066] 104. Process the damage picture with several damage candidate regions according to the instance segmentation model, so that the instance segmentation model outputs the damage detection result of the vehicle to be monitored. The damage detection result includes at least one damage information, and the damage information includes The type and location of the injury.

[0067] In the embodiment of the present ...

Embodiment 2

[0103] see Figure 4 , Figure 4 It is a structural schematic diagram of a vehicle damage recognition device disclosed in the embodiment of the present application. Such as Figure 4 As shown, the device of the embodiment of the present application includes:

[0104] Obtaining module 201, used to obtain the damage picture of the vehicle to be monitored;

[0105] The extraction module 202 is used to extract the image features of the damage picture of the vehicle to be monitored according to the neural network;

[0106] A determination module 203, configured to determine several damage candidate regions in the damage picture according to image features;

[0107] The identification module 204 is configured to process the damage picture with several damage candidate regions according to the instance segmentation model, so that the instance segmentation model outputs a damage detection result of the vehicle to be monitored, and the damage detection result includes at least one ...

Embodiment 3

[0118] see Figure 5 , Figure 5 It is a structural schematic diagram of a vehicle damage recognition device disclosed in the embodiment of the present application. Such as Figure 5 As shown, the device of the embodiment of the present application includes:

[0119] processor 301; and

[0120] The memory 302 is configured to store machine-readable instructions. When the instructions are executed by the processor 301, the processor 301 executes the vehicle damage identification method according to Embodiment 1 of the present application.

[0121] The device in the embodiment of the present application executes the vehicle damage identification method, and then can detect the damage picture of the vehicle to be monitored, and then can extract the image features of the damage picture of the vehicle to be monitored according to the neural network, and then can determine the damage picture according to the image features. Several damage candidate areas in , and then the damage...

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 a vehicle damage identification method and device, equipment and a storage medium; the method comprises the steps: obtaining a damage picture of a to-be-monitored vehicle; extracting image features of the damage picture of the to-be-monitored vehicle according to a neural network; determining a plurality of injury candidate areas in the injury picture according to the image features; and processing the damage picture with the plurality of damage candidate areas according to an instance segmentation model, so that the instance segmentation model outputs a damage detection result of the to-be-monitored vehicle, the damage detection result comprising information of at least one damage, the information of the damage comprising the category and position information of the damage. According to the invention, the accuracy of vehicle damage identification can be improved.

Description

technical field [0001] The present application relates to the field of computer vision, and in particular, relates to a vehicle damage recognition method, device, equipment and storage medium. Background technique [0002] Thanks to the rapid development of deep learning, the commercial value of computer vision has gradually been reflected in many fields such as security, Internet, and industrial manufacturing. Migration, transformation, and innovation of artificial intelligence algorithms can also be applied to auxiliary analysis of vehicle damage assessment. AI can help improve the efficiency and accuracy of determining vehicle damage. At present, the existing vehicle damage assessment process is as follows: identify and judge the vehicle damage status according to the pictures of the vehicle damage taken by the user on site. It can improve user experience and reduce the cost of insurance companies. [0003] At present, the biggest difficulty in intelligent damage asses...

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): G06K9/62G06K9/34G06K9/46G06N3/04G06Q40/08
CPCG06Q40/08G06V10/267G06V10/44G06V10/56G06V2201/08G06N3/048G06N3/045G06F18/24
Inventor 张发恩郭慧娟
Owner 创新奇智(上海)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