Information processing device, information processing method, computer program product, and vehicle control system

1. An information processing device comprising:

one or more processors configured to:

acquire a plurality of pieces of detection information that is information including detection results at two-dimensional positions different from each other acquired by detection of an object by one or more detection devices through a transmission body, the plurality of pieces of detection information each including distortion due to the transmission body that exists between the detection devices and the object;

detect a feature point from each of the plurality of pieces of detection information; and

estimate, by minimizing an error between a three-dimensional position corresponding to the feature point and a detection position of the feature point corrected based on an initial distortion map expressing distortion at each of the two-dimensional positions, a revised distortion map, the three-dimensional position, and the detection position, wherein

the initial distortion map is expressed at a resolution smaller than that of the pieces of detection information, and

the feature point is corrected by using the distortion corrected according to a difference between the resolution of the initial distortion map and the resolution of the pieces of detection information.

2. The device according to claim 1 , wherein the distortion is a displacement amount at each of the two-dimensional positions.

3. The device according to claim 1 , wherein the one or more processors are configured to:

classify the acquired plurality of pieces of detection information into a plurality of groups including a plurality of pieces of detection information having similar distortion to each other; and

estimate the revised distortion map, the three-dimensional position, and the detection position for each of the plurality of groups.

4. The device according to claim 3 , wherein the one or more processors are configured to classify, into a same group, a plurality of pieces of detection information in which relative positions between the detection devices and the transmission body are similar.

5. The device according to claim 3 , wherein the one or more processors are configured to classify, into a same group, a plurality of pieces of detection information including distortions due to the transmission body in similar states.

6. The device according to claim 1 , wherein the one or more processors are configured to:

generate a mask indicating a region in which the revised distortion map is estimated; and

correct the feature point based on the initial distortion map expressing the distortion at each position included in the region indicated by the mask.

7. The device according to claim 6 , wherein the one or more processors are configured to generate the mask indicating a region including a detection result detected by an electromagnetic wave transmitted through the transmission body among regions included in the pieces of detection information.

8. The device according to claim 6 , wherein the one or more processors are configured to generate the mask indicating a region including a specific object in the pieces of detection information.

9. The device according to claim 6 , wherein the one or more processors are configured to generate the mask indicating a region including more feature points than other regions.

10. The device according to claim 3 , wherein

the plurality of pieces of detection information are a plurality of images, and

the one or more processors are configured to classify the plurality of images into the plurality of groups.

11. The device according to claim 1 , wherein

the detection devices include a camera, and

the transmission body includes a transparent body that transmits visible light.

12. An information processing method comprising:

acquiring a plurality of pieces of detection information that is information including detection results at two-dimensional positions different from each other acquired by detection of an object by one or more detection devices through a transmission body, the plurality of pieces of detection information each including distortion due to the transmission body that exists between the detection devices and the object;

detecting a feature point from each of the plurality of pieces of detection information; and

estimating, by minimizing an error between a three-dimensional position corresponding to the feature point and a detection position of the feature point corrected based on an initial distortion map expressing distortion at each of the two-dimensional positions, a revised distortion map, the three-dimensional position; and the detection position, wherein

the initial distortion map is expressed at a resolution smaller than that of the pieces of detection information, and

the feature point is corrected by using the distortion corrected according to a difference between the resolution of the initial distortion map and the resolution of the pieces of detection information.

13. A computer program product comprising a non-transitory computer readable medium including programmed instructions, the instructions causing a computer to execute:

acquiring a plurality of pieces of detection formation that is information including detection results at two-dimensional positions different from each other acquired by detection of an object by one or more detection devices through a transmission body, the plurality of pieces of detection information each including distortion due to the transmission body that exists between the detection devices and the object;

detecting a feature point from each of the plurality of pieces of detection information; and

estimating, by minimizing an error between a three-dimensional position corresponding to the feature point and a detection position of the feature point corrected based on an initial distortion map expressing distortion at each of the two-dimensional positions, a revised distortion map, the three-dimensional position, and the detection position, wherein

the initial distortion map is expressed at a resolution smaller than that of the pieces of detection information, and

the feature point is corrected by using the distortion corrected according to a difference between the resolution of the initial distortion map and the resolution of the pieces of detection information.

14. A vehicle control system that controls a vehicle, the system comprising:

an information processing device configured to estimate a three-dimensional position of an object; and

a vehicle control device configured to control a drive mechanism to drive the vehicle based on the three-dimensional position,

the information processing device comprising:

one or more processors configured to:

acquire a plurality of pieces of detection information that is information including detection results at two-dimensional positions different from each other acquired by detection of the object by one or more detection devices through a transmission body, the plurality of pieces of detection information each including distortion due to the transmission body that exists between the detection devices and the object,

detect a feature point from each of the plurality of pieces of detection information, and

estimate, by minimizing an error between a three-dimensional position corresponding to the feature point and a detection position of the feature point corrected based on an initial distortion map expressing distortion at each of the two-dimensional positions, a revised distortion map, the three-dimensional position, and the detection position, wherein

the initial distortion map is expressed at a resolution smaller than that of the pieces of detection information, and

the feature point is corrected by using the distortion corrected according to a difference between the resolution of the initial distortion map and the resolution of the pieces of detection information.