Information processing apparatus, information processing method, and information processing program

1 . An information processing apparatus comprising a processor configured to:

acquire a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquire a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extract a plurality of feature points from the first image;

extract a plurality of feature points from the second image;

search for corresponding feature points between the first image and the second image;

perform coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculate a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the processor is configured to:

individually extract a plurality of feature points from the first images;

individually extract a plurality of feature points from the second images;

search for corresponding feature points between a first image and a second image that correspond to each other among the first images and the second images;

perform registration between a piece of first damage information and a piece of second damage information that correspond to each other among the pieces of first damage information and the pieces of second damage information;

calculate a difference between the piece of first damage information and the piece of second damage information that correspond to each other;

acquire composition processing information necessary for panoramic composition of the plurality of first images; and

combine differences, each calculated between one of the first images and a corresponding one of the second images, on the basis of the composition processing information.

2 . The information processing apparatus according to claim 1 , wherein

the processor is configured to:

perform rigid registration as the coarse registration; and

perform non-rigid registration as the fine registration.

3 . The information processing apparatus according to claim 1 , wherein

the processor is configured to:

perform rigid registration as the coarse registration; and

perform, as the fine registration, registration by correcting a difference in lens distortion.

4 . The information processing apparatus according to claim 1 , wherein

the first damage information and the second damage information are crack information, and

the processor is configured to calculate a difference in crack width and/or length.

5 . The information processing apparatus according to claim 4 , wherein

the processor is configured to generate a pair of corresponding cracks and calculate a difference in width between the corresponding cracks in the pair to calculate a difference in crack width.

6 . The information processing apparatus according to claim 4 , wherein

the processor is configured to generate a pair of corresponding cracks and calculate a length of a crack that is not paired to calculate a difference in crack length.

7 . The information processing apparatus according to claim 5 , wherein

the processor is configured to generate a pair of adjacent cracks.

8 . The information processing apparatus according to claim 5 , wherein

the processor is configured to generate a pair of corresponding cracks by DP matching.

9 . The information processing apparatus according to claim 1 , wherein

the first damage information and the second damage information are damaged-region information, and

the processor is configured to calculate a difference between corresponding damaged regions.

10 . An information processing apparatus, comprising a processor configured to:

acquire a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquire a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extract a plurality of feature points from the first image;

extract a plurality of feature points from the second image;

search for corresponding feature points between the first image and the second image;

perform coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculate a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of second images, each having an image capturing area that partially overlaps an image capturing area of the first image, and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the processor is configured to:

individually extract a plurality of feature points from the second images;

individually search for corresponding feature points between the first image and each of the second images;

individually perform registration between the first damage information and each of the pieces of second damage information;

individually calculate differences between the first damage information and the pieces of second damage information; and

combine the differences individually calculated between the first damage information and the pieces of second damage information.

11 . The information processing apparatus according to claim 1 , wherein the processor is configured to:

extract a region in which a difference between the first damage information and the second damage information is calculable, in the first image and the second image; and

output information on the extracted region.

12 . The information processing apparatus according to claim 11 , wherein the processor is configured to:

generate an image in which the region in which the difference is calculable is indicated in the first image and output the generated image to a display destination when outputting information on the region in which the difference is calculable.

13 . An information processing apparatus, comprising a processor configured to:

acquire a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquire a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extract a plurality of feature points from the first image;

extract a plurality of feature points from the second image;

search for corresponding feature points between the first image and the second image;

perform coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculate a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the processor is configured to:

perform panoramic composition of the plurality of first images;

combine the plurality of pieces of first damage information on the basis of composition processing information for the panoramic composition of the plurality of first images;

perform panoramic composition of the plurality of second images;

combine the plurality of pieces of second damage information on the basis of composition processing information for the panoramic composition of the plurality of second images;

extract a plurality of feature points from a first image obtained after the panoramic composition;

extract a plurality of feature points from a second image obtained after the panoramic composition;

search for corresponding feature points between the first image obtained after the panoramic composition and the second image obtained after the panoramic composition;

perform registration between first damage information obtained after combining of the plurality of pieces of first damage information and second damage information obtained after combining of the plurality of pieces of second damage information; and

calculate a difference between the first damage information obtained after combining of the plurality of pieces of first damage information and the second damage information obtained after combining of the plurality of pieces of second damage information.

14 . The information processing apparatus according to claim 1 , wherein

the first damage information and the second damage information are acquired before the coarse registration is performed.

15 . An information processing method comprising:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the method comprises:

individually extracting a plurality of feature points from the first images;

individually extracting a plurality of feature points from the second images;

searching for corresponding feature points between a first image and a second image that correspond to each other among the first images and the second images;

performing registration between a piece of first damage information and a piece of second damage information that correspond to each other among the pieces of first damage information and the pieces of second damage information;

calculating a difference between the piece of first damage information and the piece of second damage information that correspond to each other;

acquiring composition processing information necessary for panoramic composition of the plurality of first images; and

combining differences, each calculated between one of the first images and a corresponding one of the second images, on the basis of the composition processing information.

16 . The information processing method according to claim 15 , wherein

the first damage information and the second damage information are acquired before the coarse registration is performed.

17 . A non-transitory, computer-readable tangible recording medium which records thereon a program for causing, when read by a computer, the computer to implement:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the computer is caused to implement:

individually extracting a plurality of feature points from the first images;

individually extracting a plurality of feature points from the second images;

searching for corresponding feature points between a first image and a second image that correspond to each other among the first images and the second images;

performing registration between a piece of first damage information and a piece of second damage information that correspond to each other among the pieces of first damage information and the pieces of second damage information;

calculating a difference between the piece of first damage information and the piece of second damage information that correspond to each other;

acquiring composition processing information necessary for panoramic composition of the plurality of first images; and

combining differences, each calculated between one of the first images and a corresponding one of the second images, on the basis of the composition processing information.

18 . An information processing method comprising:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of second images, each having an image capturing area that partially overlaps an image capturing area of the first image, and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the method comprises:

individually extracting a plurality of feature points from the second images;

individually searching for corresponding feature points between the first image and each of the second images;

individually performing registration between the first damage information and each of the pieces of second damage information;

individually calculating differences between the first damage information and the pieces of second damage information; and

combining the differences individually calculated between the first damage information and the pieces of second damage information.

19 . An information processing method comprising:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the method comprises:

performing panoramic composition of the plurality of first images;

combining the plurality of pieces of first damage information on the basis of composition processing information for the panoramic composition of the plurality of first images;

performing panoramic composition of the plurality of second images;

combining the plurality of pieces of second damage information on the basis of composition processing information for the panoramic composition of the plurality of second images;

extracting a plurality of feature points from a first image obtained after the panoramic composition;

extracting a plurality of feature points from a second image obtained after the panoramic composition;

searching for corresponding feature points between the first image obtained after the panoramic composition and the second image obtained after the panoramic composition;

performing registration between first damage information obtained after combining of the plurality of pieces of first damage information and second damage information obtained after combining of the plurality of pieces of second damage information; and

calculating a difference between the first damage information obtained after combining of the plurality of pieces of first damage information and the second damage information obtained after combining of the plurality of pieces of second damage information.

20 . A non-transitory, computer-readable tangible recording medium which records thereon a program for causing, when read by a computer, the computer to implement:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of second images, each having an image capturing area that partially overlaps an image capturing area of the first image, and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the computer is caused to implement:

individually extracting a plurality of feature points from the second images;

individually searching for corresponding feature points between the first image and each of the second images;

individually performing registration between the first damage information and each of the pieces of second damage information;

individually calculating differences between the first damage information and the pieces of second damage information; and

combining the differences individually calculated between the first damage information and the pieces of second damage information.

21 . A non-transitory, computer-readable tangible recording medium which records thereon a program for causing, when read by a computer, the computer to implement:

acquiring a first image obtained by capturing an image of a structure and first damage information of the structure extracted from the first image;

acquiring a second image obtained by capturing an image of the structure at a time point different from a time point at which the first image is captured and second damage information of the structure extracted from the second image;

extracting a plurality of feature points from the first image;

extracting a plurality of feature points from the second image;

searching for corresponding feature points between the first image and the second image;

performing coarse registration followed by fine registration on the first damage information and the second damage information on the basis of information on the corresponding feature points to perform registration between the first damage information and the second damage information; and

calculating a difference between the first damage information and the second damage information after the registration,

wherein

in a case where a plurality of first images obtained by capturing images of segments of the structure and a plurality of pieces of first damage information extracted from the plurality of first images are acquired, and a plurality of second images obtained by capturing images of the segments of the structure and a plurality of pieces of second damage information extracted from the plurality of second images are acquired,

the computer is caused to implement:

performing panoramic composition of the plurality of first images;

combining the plurality of pieces of first damage information on the basis of composition processing information for the panoramic composition of the plurality of first images;

performing panoramic composition of the plurality of second images;

combining the plurality of pieces of second damage information on the basis of composition processing information for the panoramic composition of the plurality of second images;

extracting a plurality of feature points from a first image obtained after the panoramic composition;

extracting a plurality of feature points from a second image obtained after the panoramic composition;

searching for corresponding feature points between the first image obtained after the panoramic composition and the second image obtained after the panoramic composition;

performing registration between first damage information obtained after combining of the plurality of pieces of first damage information and second damage information obtained after combining of the plurality of pieces of second damage information; and

calculating a difference between the first damage information obtained after combining of the plurality of pieces of first damage information and the second damage information obtained after combining of the plurality of pieces of second damage information.