Granted Patent B2

US 12,361,573 · App. 17/755,725 · Granted Jul 15, 2025

Inventors: Teppei Kurita (Tokyo, JP); Shinichiro Gomi (Tokyo, JP)

Assignee: SONY GROUP CORPORATION

G06T7/50G06T5/70G06T7/11G06V10/141G06V10/25G06V10/60G06V10/761G06T2207/10056

Abstract

Claims (52)

1. An information processing device, comprising:

a central processing unit (CPU) configured to:

acquire a captured image of a target from a sensor, wherein

the captured image is based on reflected light of light emitted to the target from a plurality of light sources, and

each light source of the plurality of light sources is at a different position;

extract a flat region from the captured image based on a luminance value of the captured image;

acquire information regarding the sensor; and

calculate shape information regarding a shape of a surface of the target, based on the flat region and the information regarding the sensor.

2. The information processing device according to claim 1 , wherein the light is simultaneously emitted to the target from the plurality of light sources.

3. The information processing device according to claim 2 , wherein the CPU is further configured to set, as the flat region, a region in which the luminance value of the captured image is equal to or more than a threshold.

4. The information processing device according to claim 2 , wherein the CPU is further configured to:

perform a smoothing process on the captured image;

generate a smoothing image based on the smoothing process on the captured image; and

extract the flat region from the captured image based on the smoothing image.

5. The information processing device according to claim 4 , wherein the CPU is further configured to:

divide the captured image into a plurality of divided regions; and

extract the flat region for each divided region of the plurality of divided regions to calculate the shape information.

6. The information processing device according to claim 5 , wherein the CPU is further configured to:

calculate normal information of the flat region in the captured image; and

input the normal information to a machine learning model by to calculate the shape information.

7. The information processing device according to claim 6 , wherein the CPU is further configured to:

generate the machine learning model;

generate a correct answer candidate image by shift of a correct answer image by a specific number of pixels;

compare the correct answer candidate image with output data of the machine leaning model; and

update a weight associated with the machine learning model, based on a result of the comparison between the correct answer candidate image and the output data.

8. The information processing device according to claim 7 , wherein the CPU is further configured to:

calculate, based on the machine learning model, a least square error between the correct answer candidate image and the output data; and

update the weight based on the least square error.

9. The information processing device according to claim 1 , wherein the CPU is further configured to:

acquire a plurality of captured images of the target from the sensor,

wherein the plurality of captured images includes the captured image; and

extracts, as the flat region, a region in which a change in luminance value between the plurality of captured images is smaller than a threshold.

10. The information processing device according to claim 1 , wherein the CPU is further configured to:

calculate a contrast value based on the luminance value of the captured image; and

extract the flat region based on the contrast value.

11. The information processing device according to claim 10 , wherein the CPU is further configured to:

divide the captured image into a plurality of divided regions;

calculate the contrast value for each divided region of the plurality of divided regions;

determine, based on the contrast value, a divided region of the plurality of divided regions is flat; and

extract the flat region based the determination that the divided region is flat.

12. The information processing device according to claim 10 , wherein the CPU is further configured to:

acquire a plurality of captured images, wherein

each captured image of the plurality of captured images has a different depth-of-field plane of the sensor, and

the plurality of captured images includes the captured image; and

extract the flat region from each captured image of the plurality of captured images.

13. An information processing method, comprising:

acquiring a captured image of a target from a sensor, wherein

the captured image is based on reflected light of light emitted to the target from a plurality of light sources, and

each light source of the plurality of light sources is at a different position;

extracting a flat region from the captured image based on a luminance value of the captured image;

acquiring information regarding the sensor; and

calculating shape information regarding a shape of a surface of the target, based on the flat region and the information regarding the sensor.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (23)