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

Tire image recognition method and tire image recognition device

A technology of image recognition and tires, applied in tire tread/tread pattern, image enhancement, image analysis, etc., can solve the problems that the analysis parameters are limited to individual situations, and it takes a long time to analyze, etc.

Pending Publication Date: 2020-03-31
BRIDGESTONE CORP
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] However, there is a problem that in Patent Document 1, since feature quantities such as edges and lines of tread patterns as feature geometric information are set in advance by the intervention of a person such as a developer, not only the analysis parameters are limited to individual situation and spend a lot of time analyzing a large number of tires

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
  • Tire image recognition method and tire image recognition device
  • Tire image recognition method and tire image recognition device
  • Tire image recognition method and tire image recognition device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0097] A description will be given regarding the identification results in the case where the amount of tire wear is set to two levels of new tire and large amount of wear for the same type of tire.

[0098] Note that the identification method follows Figure 6 The flowchart shown.

[0099] The specifications of the tires are as follows.

[0100] ·Tire 1

[0101] Size: 245 / 70R19.5

[0102] Pattern: A

[0103] Amount of wear: 0mm (new tires)

[0104] ·Tire 2

[0105] Size: 245 / 70R19.5

[0106] Pattern: A

[0107] Amount of wear: 11mm

[0108] · Capture images

[0109] Six pictures of the circumference of each tire were randomly taken using the camera of the smartphone.

[0110] Figure 7 (a) is the image of tire 1, and Figure 7 (b) is an image of tire 2.

[0111] The size of the images is 480×640 pixels each.

[0112] · Image grade

[0113] The gray scale 255 levels are normalized in the range of 0-1.

[0114] exist Figure 7 Images after data conversion are s...

Embodiment 2

[0141] Identify tire 2 with high wear and tire 3 with medium wear.

[0142] ·Tire 2

[0143] Size: 245 / 70R19.5

[0144] Pattern: A

[0145] Amount of wear: 11mm

[0146] ·Tire 3

[0147] Size: 245 / 70R19.5

[0148] Pattern: A

[0149] Abrasion: 8mm

[0150] Figure 8 (a) and (b) are captured images of tire 2 and tire 3, and Figure 8 (c) and (d) are images after data conversion.

[0151] ·The realization condition conforms to the embodiment 1.

[0152] ·result

[0153] The correct answer rate was judged to be 96%.

[0154] In other words, out of a total of 18 images of 9 images of test tire 2 and 9 images of test tire 3, 17 were correctly identified and classified.

Embodiment 3

[0156] Identify new tire 1, tire with heavy wear 2 and tire with moderate wear 3.

[0157] ·Tire 1

[0158] Size: 245 / 70R19.5

[0159] Pattern: A

[0160] Amount of wear: 0mm (new tires)

[0161] ·Tire 2

[0162] Size: 245 / 70R19.5

[0163] Pattern: A

[0164] Amount of wear: 11mm

[0165] ·Tire 3

[0166] Size: 245 / 70R19.5

[0167] Pattern: A

[0168] Abrasion: 8mm

[0169] Incidentally, the captured images of tire 1 to tire 3 and the images after data conversion are the same as Figure 7 (a)~(d) and Figure 8 The captured images shown in (a) to (d) and the images after data conversion are the same.

[0170] ·The realization condition conforms to the embodiment 1.

[0171] ·result

[0172] The correct answer rate was judged to be 96%.

[0173] In other words, out of a total of 27 images of 9 images of test tire 1, 9 images of test tire 2, and 9 images of test tire 3, 26 were correctly identified and classified.

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

PropertyMeasurementUnit
Laaaaaaaaaa
Laaaaaaaaaa
Laaaaaaaaaa
Login to View More

Abstract

According to the present invention: images of a plurality of tires that differ from one another in either one or both of the type and the tire condition thereof are acquired and are used as teacher images; the teacher images are converted to a size having a fixed number of pixels, after which a plurality of sets of converted teacher image data are used as learning images, which are learned using aconvolutional neural network to set parameters of the network; thereafter, a tire image of a tire to be recognized is acquired, is converted to the same size as the teacher images and is input into the convolutional neural network to assess either one or both of the type and the tire condition of the target tire.

Description

technical field [0001] The present invention relates to methods and devices for recognizing images of tires. Background technique [0002] It has been proposed to replace tires with new ones in the event of reduction of tread rubber due to wear, or damage due to trauma or deterioration, in order to ensure tire performance and safety. Information acquisition for judgment of the above-mentioned phenomenon is mainly performed by external appearance observation by visual inspection. [0003] In the judgment of the amount of wear, although the judgment is important for the running performance and safety performance of the tire, it is difficult to say that the driver's check is performed as frequently as necessary every day. [0004] Therefore, instead of human visual inspection, if tire information such as wear amount can be recognized from images produced by machines such as cameras, not only labor saving of inspection but also reduction of management cost can be expected. [...

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): G01M17/02B60C11/03B60C11/24B60C13/00G06T7/00
CPCG06T2207/20081G06T2207/20084G06T7/0004G01M17/027B60C2019/006B60C11/246G06N3/084G06V2201/06G06N3/045G06T3/40G06T7/001G06T2207/30108
Inventor 西井雅之大泽靖雄若尾泰通
Owner BRIDGESTONE CORP
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