# US 2024/0202894 A1 · A method and device for on-site evaluating quality of an image

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

- Number: US 2024/0202894 A1
- Document ID: US20240202894A1
- Status: Published application
- Kind: A1
- Application number: 18/288,306
- Filed: 2022-04-25
- Published: 2024-06-20
- Earliest claimed: 2021-04-26
- Assignees: Ventus Engineering GmbH
- Applicants: Ventus Engineering GmbH
- Inventors: Xavier Tolron; Shavkat Mingaliev; Poul Anker Skaarup Lübker
- Web page: https://patentgrep.com/patent/US20240202894A1

## CPC

- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/12: Edge-based segmentation
- H04N 7/183: {for receiving images from a single remote source}
- H04N 23/66: Remote control of cameras or camera parts, e.g. by remote control devices
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/30168: Image quality inspection
- Y02E 10/72: Wind turbines with rotation axis in wind direction
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

## Abstract

A method (1000) for on-site evaluating quality of an image (90) of apart (34) of a structure, optionally a part (34) of a wind turbine generator (WTG, 30), the method (1000) comprising acts of: —receiving (100) an image (90) from a visual inspection system (10) with a field of view (12) about a line of sight (14) towards the part (34) of the structure; —dividing (200) the image (90) into sub-images (92); —calculating (300) edge scores of the sub-images (92); —sorting (400) the sub-images (92) into a top sub-group (93) having an edge-score above a pre-set edge score and a bottom sub-group (94) having an edge-score below the pre-set edge score; —evaluating (500) the quality of the image as a function of coordinates of the top sub-group (93).

## Claims

### Claim 1

A computer-implemented method (1000) for on-site evaluating quality of an image (90) of a part (34) of a structure, optionally a part (34) of a wind turbine generator (WTG, 30), the method (1000) comprising acts of:
receiving (100) an image (90) from a visual inspection system (10) with a field of view (12) about a line of sight (14) towards the part (34) of the structure;
dividing (200) the image (90) into sub-images (92);
calculating (300) edge scores of the sub-images (92);
sorting (400) the sub-images (92) into a top sub-group (93) having an edge-score above a pre-set edge score and a bottom sub-group (94) having an edge-score below the pre-set edge score; —evaluating (500) the quality of the image as a function of coordinates of the top sub-group (93) by
calculating (300) a first linear regression (95I) of the top sub-group (93) and second linear regression (95II) of the top sub-group (93), where the second linear regression (95II) has reversed the first and second axis relative to the first linear regression (95I); and
evaluating (500) the quality of the image as a function of a regression angle (96) between the first and second linear regression (95I, 95II).

### Claim 2 (depends on 1)

The method (1000) according to claim 1, wherein the structure is a wind turbine generator (WTG, 30).

### Claim 3 (depends on 1, 2)

The method (1000) according to claim 1 or 2, wherein the act of calculating (300) edge scores is by computing the Laplacian of the sub-images (92) and extracting the variance of each sub-image (92) as the edge score.

### Claim 4 (depends on 1, 2, 3)

The method (1000) according to any one of claim 1-3, wherein further acts of
calculating (300) a mean coordinate (97) is performed on the top sub-group (93); and
evaluating (500) the quality of the image as a function of the mean coordinate (97) relative to a pre-set threshold border (98) within the image (90).

### Claim 5 (depends on 1, 2, 3, 4)

The method (1000) according to any one of claims 1-4, wherein the method (1000) is performed on a group of images and an act of sorting (400) the group of images is performed as a function of quality into at least two groups
an accepted image group; and
a non-accepted image group.

### Claim 6 (depends on 1, 2, 3, 4, 5)

The method (1000) according to any one of claims 1-5, the method (1000) comprising further acts of
geotagging (600) the image (90) as a function of position and line of sight (14) of the visual inspection system (10).

### Claim 7 (depends on 1, 2, 3, 4, 5, 6, 7)

The method (1000) according to claim 6, the method (1000) comprising further acts of
sending (700) instruction to the visual inspection system (10) causing the visual inspection system (10) to recapture at least one image having an unaccepted quality at a perturbed position and/or perturbed line of sight (14) as a function of the geotag,
repeating the method (1000) according to any one of claims 1-7.

### Claim 8 (depends on 1, 2, 3, 4, 5, 6, 7)

The method (1000) according to anyone of claims 1-7, the method (1000) comprising a further act of warning a decision maker as a function of the quality of an image and/or as function of the non-accepted image group relative to the accepted image group.

### Claim 9 (depends on 1, 2, 3, 4, 5, 6, 7, 8)

The method (1000) according to any one of claims 1-8, wherein the visual inspection system (10) has a fixed focus.

### Claim 10 (depends on 1, 2, 3, 4, 5, 6, 7, 8, 9)

A device (20) for on-site evaluating an image of a part (34) of a structure, optionally a part (34) of a wind turbine generator (WTG, 30), the device (20) being in communication with a visual inspection system (10) with a field of view (12) about a line of sight (14) towards the wind turbine generator (WTG); and comprising the means for carrying out the method of any one of claims 1-9.

### Claim 11 (depends on 10)

The device (20) according to claim 10, wherein the device further comprises
a display for manual evaluating images (90) in the non-accepted image group.

### Claim 12 (depends on 10)

The device (20) according to claim 10, wherein the device (20) is an unmanned aerial vehicle (UAV) carrying the visual inspection system (10).

### Claim 13 (depends on 1, 2, 3, 4, 5, 6, 7, 8, 9)

A computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 1-9.

### Claim 14 (depends on 13)

A computer-readable data carrier having stored thereon the computer program of claim 13.
