Inspection support apparatus, inspection support method, and inspection support program for concrete structure

Patent metadata

Field	Value
Publication number	US-12159387-B2
Application number	US-202117318794-A
Country	US
Kind code	B2
Filing date	May 12, 2021
Priority date	Nov 29, 2018
Publication date	Dec 3, 2024
Grant date	Dec 3, 2024

Abstract

An inspection support apparatus includes: an image acquisition unit ( 11 ) that acquires an image obtained by photographing a concrete structure that is an inspection target; a damage region extraction unit ( 12 ) that extracts from the acquired image, a damage region (water leakage, free lime, etc.) appearing on a surface of the concrete structure; a causal part detection unit ( 17 ) that detects, in a case where the damage region is extracted, a causal part (a crack, a construction joint, a joint, a peeling part, etc.) causing damage from the image on the basis of a result of extraction of the damage region; and an output unit ( 19 ) that outputs the result of extraction of the damage region and a result of detection of the causal part.

First claim

What is claimed is:

1. An inspection support apparatus for a concrete structure, the inspection support apparatus comprising a processor configured to:
acquire an image obtained by photographing a concrete structure that is an inspection target;
extract, from the image, a damage region appearing on a surface of the concrete structure;
detect, in a case where the damage region is extracted, a causal part causing damage from the image on the basis of a result of extraction of the damage region;
output the result of extraction of the damage region and a result of detection of the causal part;
acquire information about a damaged surface from which the damage region is extracted;
detect the causal part from the image on the basis of the result of extraction of the damage region and the information about the damaged surface;
acquire as the information about the damaged surface, information about a direction of gravity and about an inclination state of the damaged surface relative to the direction of gravity;
detect the causal part while a central part of the damage region is weighted in a case where an inclination of the damaged surface is greater than or equal to a threshold value; and
detect the causal part while a part on an upper side of the damage region in direction of gravity is weighted in a case where the inclination of the damaged surface is less than the threshold value.

2. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to detect the causal part from within the damage region.

3. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to acquire information about a photographed surface of the concrete structure, and
detect the causal part from the image on the basis of the result of extraction of the damage region and the information about the photographed surface.

4. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to determine the direction of gravity from the image, and
acquire the information about the direction of gravity.

5. The inspection support apparatus for a concrete structure according to claim 4 ,
wherein the processor is further configured to determine the direction of gravity on the basis of a shape of a spread of the damage region and/or a state of damage.

6. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to determine, from the image, the inclination state of the damaged surface relative to the direction of gravity.

7. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to extract as the damage region, a free lime region and/or a water leakage region appearing on the surface of the concrete structure.

8. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to detect as the causal part, at least one of a crack part, a construction joint part, a joint part, or a peeling part.

9. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to generate a composite image obtained by adding a frame that surrounds the damage region and a line that traces the causal part to the image, and
output the composite image to a display device as the result of extraction of the damage region and the result of detection of the causal part.

10. The inspection support apparatus for a concrete structure according to claim 9 ,
wherein the processor is further configured to correct the result of extraction of the damage region and the result of detection of the causal part.

11. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to quantify the damage region and/or the causal part, and
output information about the quantified damage region and/or the quantified causal part.

12. The inspection support apparatus for a concrete structure according to claim 11 ,
wherein the processor is further configured to quantify the damage region by obtaining an area and/or a color of the damage region, and quantify the causal part by obtaining at least one of a width, a length, or an area of the causal part.

13. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to determine a degree of damage on the basis of the result of extraction of the damage region and the result of detection of the causal part.

14. The inspection support apparatus for a concrete structure according to claim 1 ,
wherein the processor is further configured to determine a damage state from the image in a case where the damage region is extracted.

15. The inspection support apparatus for a concrete structure according to claim 14 ,
wherein the processor is further configured to determine a degree of damage on the basis of the result of extraction of the damage region, the result of detection of the causal part, and a result of determination of the damage state.

16. An inspection support method for a concrete structure, the inspection support method comprising:
acquiring an image obtained by photographing a concrete structure that is an inspection target;
extracting, from the image, a damage region appearing on a surface of the concrete structure;
detecting, in a case where the damage region is extracted, a causal part causing damage from the image on the basis of a result of extraction of the damage region;
outputting the result of extraction of the damage region and a result of detection of the causal part;
acquiring information about a damaged surface from which the damage region is extracted;
detecting the causal part from the image on the basis of the result of extraction of the damage region and the information about the damaged surface;
acquiring as the information about the damaged surface, information about a direction of gravity and about an inclination state of the damaged surface relative to the direction of gravity;
detecting the causal part while a central part of the damage region is weighted in a case where an inclination of the damaged surface is greater than or equal to a threshold value; and
detecting the causal part while a part on an upper side of the damage region in direction of gravity is weighted in a case where the inclination of the damaged surface is less than the threshold value.

17. A non-transitory computer readable recording medium storing an inspection support program for a concrete structure, the inspection support program causing a computer to implement:
a function of acquiring an image obtained by photographing a concrete structure that is an inspection target;
a function of extracting, from the image, a damage region appearing on a surface of the concrete structure;
a function of detecting, in a case where the damage region is extracted, a causal part causing damage from the image on the basis of a result of extraction of the damage region;
a function of outputting the result of extraction of the damage region and a result of detection of the causal part;
a function of acquiring information about a damaged surface from which the damage region is extracted;
a function of detecting the causal part from the image on the basis of the result of extraction of the damage region and the

Assignees

• Fujifilm Corp

Inventors

• Matsumoto Kazuma

Classifications

• G06V10/82

  using neural networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06T2207/30132

  Masonry; Concrete · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T7/40

  Analysis of texture (depth or shape recovery from texture G06T7/529) · CPC title