# US 2020/0394467 A1 · Detecting device, detecting method, generating method, computer program, and storage medium

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0394467 A1
- Document ID: US20200394467A1
- Status: Published application
- Kind: A1
- Application number: 16/900,711
- Filed: 2020-06-12
- Published: 2020-12-17
- Earliest claimed: 2019-06-14
- Assignees: Shimano Inc.
- Applicants: SHIMANO Inc.
- Inventors: Hayato Shimazu; Yasuhiro Nakashima; Noriko Masuta
- Web page: https://patentgrep.com/patent/US20200394467A1

## CPC

- G06Q 10/20: Administration of product repair or maintenance
- B62J 50/21: intended to provide information to rider or passenger
- G05B 13/0265: {the criterion being a learning criterion}
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques}
- G06F 18/24: Classification techniques
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/20: in augmented reality scenes
- B62J 50/22: electronic, e.g. displays
- G06Q 10/06316: {Sequencing of tasks or work}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- B62J: CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Provided are a detecting device, a detecting method, a generating method, and a computer-readable storage medium that allow the user to readily obtain information on the degree of wear for a worn portion in the human-powered vehicle. A detecting device includes a control unit that detects a worn portion in a human-powered vehicle as a target worn portion from a first image including at least a part of the human-powered vehicle and outputs wear information related to a degree of wear for the target worn portion.

## Claims

### Claim 1

A detecting device comprising a control unit including processing circuitry, the control unit being configured to detect, in a first image including at least a part of a human-powered vehicle, a worn portion of the human-powered vehicle that is classified as a target worn portion and output wear information related to a degree of wear for the detected target worn portion.

### Claim 2 (depends on 1)

The detecting device according to claim 1, wherein
the worn portion is one of a plurality of worn portions in the first image,
the target worn portion is one of a plurality of defined target worn portions; and
the control unit detects the plurality of worn portions in the human-powered vehicle from the first image as the plurality of target worn portions, and outputs associated wear information for each of the plurality of detected target worn portions.

### Claim 3 (depends on 1)

The detecting device according to claim 1, wherein
the worn portion includes a component of the human-powered vehicle, and
the control unit detects a component of the human-powered vehicle from the first image as the target worn portion.

### Claim 4 (depends on 3)

The detecting device according to claim 3, wherein the component includes at least one of a brake shoe, a brake pad, a sprocket assembly, a crank assembly, a chain, a tire, a disk brake rotor, a rim, and a wire.

### Claim 5 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs wear information for the detected target worn portion by a machine learning model trained to output the wear information in response to a run-time input of an image.

### Claim 6 (depends on 5)

The detecting device according to claim 5, wherein a training computing device trains the machine learning model with training data obtained by labeling training data images including at least one of a brake shoe, a brake pad, a disk brake rotor, and a rim with a degree of abrasion.

### Claim 7 (depends on 5)

The detecting device according to claim 5, wherein a training computing device trains the machine learning model with training data obtained by labeling training data images including at least one of a sprocket assembly and a crank assembly with a degree of abrasion.

### Claim 8 (depends on 5)

The detecting device according to claim 5, wherein a training computing device trains the machine learning model with training data obtained by labeling training data images including at least one of a chain and a wire with a degree of extension.

### Claim 9 (depends on 5)

The detecting device according to claim 5, wherein a training computing device trains the machine learning model with training data obtained by labeling training data images including a tire with a depth of ridges.

### Claim 10 (depends on 5)

The detecting device according to claim 5, wherein a training computing device trains the machine learning model with training data including a plurality of training data images obtained when the worn portion is viewed from different angles.

### Claim 11 (depends on 5)

The detecting device according to claim 5, wherein,
at run-time, the machine learning model outputs the wear information in response to run-time input of the first image and user information including physical information or attribute information of a user of the human-powered vehicle.

### Claim 12 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs a second image in which the target worn portion is featured.

### Claim 13 (depends on 12)

The detecting device according to claim 12, wherein the control unit changes a visual emphasis of the target worn portion depending on the wear information.

### Claim 14 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs related information related to the detected target worn portion.

### Claim 15 (depends on 14)

The detecting device according to claim 14, wherein the related information includes at least one of information on a type of the target worn portion, an installing method for a component related to the target worn portion, a removing method for a component related to the target worn portion, and an adjusting method for a component related to the target worn portion.

### Claim 16 (depends on 15)

The detecting device according to claim 15, wherein the information on the installing method includes at least one of information on a component related to the target worn portion for installing the component in the worn portion, and information on a tool for installing or removing the component related to the target worn portion.

### Claim 17 (depends on 14)

The detecting device according to claim 14, wherein the related information includes information on a replacement to be replaced with a component related to the target worn portion.

### Claim 18 (depends on 17)

The detecting device according to claim 17, wherein the information on a replacement includes information on another component required when a component related to the target worn portion is replaced with the replacement.

### Claim 19 (depends on 14)

The detecting device according to claim 14, wherein the related information includes link information to access a web site for purchasing an item related to the target worn portion detected.

### Claim 20 (depends on 14)

The detecting device according to claim 14, wherein the control unit outputs the related information as text data and/or graphical data.

### Claim 21 (depends on 1)

The detecting device according to claim 1, further comprising a display unit that displays information output from the control unit.

### Claim 22 (depends on 21)

The detecting device according to claim 21, wherein
the display unit receives user input of selected related information related to the target worn portion, and
the control unit outputs detailed information of the selected related information.

### Claim 23 (depends on 21)

The detecting device according to claim 21, wherein
the display unit is configured to select the target worn portion as a selected worn portion on a second image in which the target worn portion is featured, and
the control unit outputs related information of the selected worn portion.

### Claim 24 (depends on 1)

The detecting device according to claim 1, further comprising a storage device that stores information output from the control unit.

### Claim 25 (depends on 24)

The detecting device according to claim 24, wherein the control unit stores identification information of the target worn portion in the storage device in association with information related to the degree of wear.

### Claim 26 (depends on 24)

The detecting device according to claim 24, wherein the control unit stores identification information of the target worn portion in the storage device in association with identification information of a user of the human-powered vehicle.

### Claim 27 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs identification information of the target worn portion in association with the information related to the degree of wear to an external device.

### Claim 28 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs identification information of the target worn portion in association with identification information of a user of the human-powered vehicle to an external device.

### Claim 29 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs information for prompting a user to input the first image in accordance with a traveling history of the human-powered vehicle.

### Claim 30 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs the first image input to an external device, in association with a traveling history of the human-powered vehicle.

### Claim 31 (depends on 1)

The detecting device according to claim 1, wherein the control unit outputs the first image as input to an external device, in association with traveling environment information indicating traveling environment of the human-powered vehicle.

### Claim 32

A detection method executable by a processor, the method comprising:
detecting a worn portion in a human-powered vehicle from a first image including at least a part of the human-powered vehicle as a target worn portion; and
outputting wear information related to a degree of wear for the target wear portion.

### Claim 33

A method for generating a machine learning model, the method comprising:
creating training data obtained by labeling a plurality of training data images, each including at least a part of a human-powered vehicle, with a wear portion of the human-powered vehicle and a degree of wear; and
generating, based on the created training data, a machine learning model that detects, in response to input of a run-time input image of at least a portion of the human-powered vehicle, a worn portion of the human-powered vehicle in the run-time image as a target worn portion, and outputs the target worn portion and a degree of wear.

### Claim 34

A computer-readable storage medium comprising instructions configured to be executed by a processor of a computer, to cause the processor to execute processing steps of;
detecting a worn portion in a human-powered vehicle as a target worn portion from a first image including at least a part of the human-powered vehicle; and
outputting wear information related to a degree of wear for the target worn portion.
