Granted Patent B2

US 12,340,016 · App. 18/372,554 · Granted Jun 24, 2025

Inventors: Bonkon Koo (Suwon-si, KR); Jaewoo Ko (Suwon-si, KR); Wonwoo Lee (Suwon-si, KR)

Assignee: SAMSUNG ELECTRONICS CO., LTD.

G06F3/013G02B27/0093G02B27/017G06T7/521G06T7/593G06T19/006G06V10/145G06V10/25G06V10/94G06V20/20G06V40/18G02B2027/0178G06T2207/10028G06T2215/16

Abstract

Claims (77)

1. An electronic device comprising:

at least one camera;

a depth sensor configured to obtain depth information about at least one object;

a memory storing one or more instructions; and

at least one processor configured to execute the one or more instructions to cause the electronic device to:

obtain, through the at least one camera, an image including at least one object in real world,

detect main object from the image obtained through the at least one camera,

determine a region of interest (ROI) corresponding to a region of the image including the main object,

set a measurement parameter of the depth sensor as a first parameter to obtain depth information for an entire region of the image including the ROI and a remaining region excluding the ROI,

obtain first depth information with a first resolution for the ROI by using the depth sensor with the first parameter,

adjust the measurement parameter of the depth sensor to a second parameter based on the first depth information, and

obtain second depth information with a second resolution for the ROI by using the depth sensor with the second parameter,

wherein the second resolution is higher than the first resolution, and

wherein the measurement parameter of the depth sensor comprises at least one of parameters with respect to the ROI for emitting light, parameters with respect to output of an emission light including an output pattern of the emission light and a magnitude of the output of the emission light of the depth sensor, or parameters with respect to sensing of a reflection light of the depth sensor including a sensing speed, a sensing period, or a sensing sensitivity.

2. The electronic device of claim 1 ,

wherein an accuracy of the first depth information is higher than an accuracy of the second depth information.

3. The electronic device of claim 1 ,

wherein the depth sensor is a time-of-flight (TOF) depth sensor, and

wherein the at least one processor is configured to execute the one or more instructions to cause the electronic device to:

obtain the first depth information by controlling the TOF depth sensor to sense signals corresponding to the ROI by increasing a sampling rate or reducing a sampling cycle, and not to sense signals corresponding to the remaining region.

4. The electronic device of claim 1 ,

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

determine the ROI corresponding to a region including one or more hands, and

estimate a pose of the one or more hands or recognize a gesture of the one or more hands by using the first depth information for the ROI.

5. The electronic device of claim 4 ,

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

obtain the second depth information with the second resolution for the remaining region excluding the one or more hands from the entire region of the image, and

perform camera pose tracking or background modeling by using the obtained second depth information for the remaining region.

6. The electronic device of claim 1 ,

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

obtain a face image by controlling the at least one camera to capture a face of a person,

detect regions including eyes, nose, and mouth from the obtained face image,

determine the ROI corresponding to the detected regions of the face image including the eyes, the nose, and the mouth.

7. The electronic device of claim 1 ,

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

repeatedly perform an operation of obtaining the first depth information according to a first time period, and an operation of obtaining the second depth information according to a second time period.

8. The electronic device of claim 7 , further comprising:

a display; and

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

control the display to display at least one virtual object on the ROI based on the first depth information,

adjust the first time period based on minimum time required for interaction between a user of the electronic device and the at least one virtual object displayed on the ROI.

9. The electronic device of claim 7 ,

wherein the at least one processor is further configured to execute the one or more instructions to cause the electronic device to:

adjust the second time period based on an amount of change in a movement of the remaining region in the image generated by a movement of the electronic device.

10. An operating method of an electronic device, the operating method comprising:

detecting a main object from an image obtained through at least one camera;

determining a region of interest (ROI) corresponding to a region of the image including the main object;

setting a measurement parameter of a depth sensor as a first parameter to obtain depth information for an entire region of the image including the ROI and a remaining region excluding the ROI;

obtaining first depth information with a first resolution for the ROI by using the depth sensor with the first parameter;

adjusting the measurement parameter of the depth sensor to a second parameter based on the first depth information; and

obtaining second depth information with a second resolution for the ROI by using the depth sensor with the second parameter,

wherein the second resolution is higher than the first resolution,

wherein the measurement parameter of the depth sensor comprises at least one of parameters with respect to the ROI for emitting light, parameters with respect to output of an emission light including an output pattern of the emission light and a magnitude of the output of the emission light of the depth sensor, or parameters with respect to sensing of a reflection light of the depth sensor including a sensing speed, a sensing period, or a sensing sensitivity.

11. The operating method of claim 10 ,

wherein an accuracy of the first depth information is higher than an accuracy of the second depth information.

12. The operating method of claim 10 ,

wherein the depth sensor is a time-of-flight (TOF) depth sensor, and

wherein the obtaining of the first depth information comprises obtaining the first depth information by controlling the TOF depth sensor to sense signals corresponding to the ROI by increasing a sampling rate or reducing a sampling cycle, and not to sense signals corresponding to the remaining region.

13. The operating method of claim 10 ,

wherein the determining of the ROI comprises determining the ROI corresponding to a region including one or more hands, and

the operating method further comprising:

estimating a pose of the one or more hands or recognizing a gesture of the one or more hands by using the first depth information for the ROI.

14. The operating method of claim 13 ,

wherein the obtaining of the second depth information comprises obtaining the second depth information with the second resolution for the remaining region excluding the one or more hands from the entire region of the image, and

the operating method further comprising:

performing camera pose tracking or background modeling by using the second depth information for the remaining region.

15. The operating method of claim 10 ,

wherein the obtaining of the image comprises obtaining a face image by controlling the at least one camera to capture a face of a person,

wherein the detecting the main object comprises detecting regions including eyes, nose, and mouth from the obtained face image, and

wherein the determining of the ROI comprises determining the ROI corresponding to the detected regions of the face image including the eyes, the nose, and the mouth.

16. The operating method of claim 10 ,

wherein an operation of the obtaining of the first depth information and an operation of the obtaining of the second depth information are repeatedly performed according to a first time period and a second time period, respectively.

17. The operating method of claim 16 , further comprising:

displaying at least one virtual object on the ROI based on the first depth information; and

adjusting the first time period based on minimum time required for interaction between a user of the electronic device and the at least one virtual object displayed on the ROI.

18. The operating method of claim 16 , further comprising:

adjusting the second time period based on an amount of change in a movement of the remaining region in the image generated by a movement of the electronic device.

Priority Claims (1)

Continuity (5)

References Cited (115)