IP Library Granted Patent US 11,657,485
Granted Patent B2
US 11,657,485 · App. 17/226,408 · Granted May 23, 2023

Method for expanding image depth and electronic device

Inventors: Yu-Kai Huang (New Taipei, TW); Winston H. Hsu (New Taipei, TW); Yueh-Cheng Liu (New Taipei, TW); Tsung-Han Wu (New Taipei, TW); Tzu-Kuei Huang (New Taipei, TW); Chun-Hsiang Huang (New Taipei, TW)
Assignee: Mobile Drive Netherlands B.V.
G06T5/50G06T7/55G06T7/97G06V10/143G06V10/22G06V10/764
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,657,485
App. No.
17/226,408
Granted
May 23, 2023
Kind
B2
Abstract

An electronic device used in a method for expanding image depth obtains first images by a first sensor, the first images comprising depth information. The electronic device obtains second images by a second sensor, the second images comprising gradient information, and the first images correspond to the second images. The electronic device determines the pixels in the first images which contain expandable content according to the gradient information of the second images, applies expansion accordingly to the pixels in the first images to generate third images, and generate target depth maps according to the gradient information of the second images and the depth information of the third images.

Claims (85)

1. An electronic device comprising:

a processor; and

a non-transitory storage medium coupled to the processor and configured to store a plurality of instructions, which cause the processor to:

obtain first images by a first sensor, wherein the first images comprise depth information;

obtain second images by a second sensor, wherein the second images comprise gradient information, and the first images correspond to the second images;

expand the depth information of the first images according to the depth information of the first images and the gradient information of the second images;

generate third images based on the expanded depth information of the first images;

generating target depth map based on the depth information of the third images and the gradient information of the second images.

2. The electronic device according to claim 1 , wherein the plurality of instructions is further configured to cause the processer to:

select pixels in a preset area in the second images;

determine a pixel of a center point of the preset area;

calculate gradient differences between the gradient values of the gradient information of the pixels in the preset area and the gradient value of the gradient information of the pixel of the center point;

determine target pixels from the pixels of the second images according to the gradient differences and the gradient differences of the target pixels being in a preset range;

take pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expand the depth information of the image contents in the first images.

3. The electronic device according to claim 2 , wherein the plurality of instructions is further configured to cause the processer to:

determine the preset area in the second images according to the depth information of the first images, wherein the depth value of the pixel of the first images correspond to the preset area of the second images being in a threshold range.

4. The electronic device according to claim 2 , wherein the plurality of instructions is further configured to cause the processer to:

determine the depth information of the image contents in the first images;

expand target depth information on the pixels with missing depth information of the image contents of the first images, wherein the target depth information is identical with the depth information of the image contents to be expanded.

5. The electronic device according to claim 1 , wherein the gradient information is RGB color information or gray information.

6. The electronic device according to claim 5 , wherein the plurality of instructions is further configured to cause the processer to:

select a matrix pixel block as the preset area in the second images, and determine the pixel of the center point of the matrix pixel block;

calculate RGB color differences between the RGB color values of the RGB color information of the pixels of the same column and the center point in the matrix pixel block, and the RGB color value of the RGB color information of the pixel of the center point;

determine target rows from rows of the matrix pixel block, and the RGB color differences of the pixels of the target rows are in the preset range;

calculate the RGB color differences between the RGB color values of the RGB color information of the pixels of the target rows and the RGB color value of the RGB color information of the pixel of the center point;

determine the pixels of the target rows as the target pixels and the RGB color differences of the target pixels being in the preset range;

take the pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expand the depth information of the image contents in the first images.

7. The electronic device according to claim 1 , wherein the first images and the second images are the images shoot on the same object and shoot at the same angle.

8. A method for expanding image depth comprising:

obtaining first images by a first sensor, wherein the first images comprise depth information;

obtaining second images by a second sensor, wherein the second images comprise gradient information, and the first images correspond to the second images;

expanding the depth information of the first images according to the depth information of the first images and the gradient information of the second images;

generating third images based on the expanded depth information of the first images;

generating target depth map based on the depth information of the third images and the gradient information of the second image.

9. The method for expanding image depth according to claim 8 , further comprising:

selecting pixels in a preset area in the second images;

determining a pixel of a center point of the preset area;

calculating gradient differences between the gradient values of the gradient information of the pixels in the preset area and the gradient value of the gradient information of the pixel of the center point;

determining target pixels from the pixels of the second images according to the gradient differences and the gradient differences of the target pixels being in a preset range;

taking pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expanding the depth information of the image contents in the first images.

10. The method for expanding image depth according to claim 9 , further comprising:

determining the preset area in the second images according to the depth information of the first images, and the depth value of the pixel of the first images corresponding to the preset area of the second images being in a threshold range.

11. The method for expanding image depth according to claim 9 , further comprising:

determining the depth information of the image contents in the first images;

expanding target depth information on the pixels with missing depth information of the image contents of the first images, wherein the target depth information is identical with the depth information of the image contents to be expanded.

12. The method for expanding image depth according to claim 8 , wherein the gradient information is RGB color information or gray information.

13. The method for expanding image depth according to claim 12 , further comprising:

selecting a matrix pixel block as the preset area in the second images, and determining the pixel of the center point of the matrix pixel block;

calculating RGB color differences between the RGB color values of the RGB color information of the pixels of the same column with the center point in the matrix pixel block, and the RGB color value of the RGB color information of the pixel of the center point;

determining target rows from rows of the matrix pixel block, and the RGB color differences of the pixels of the target rows being in the preset range;

calculating the RGB color differences between the RGB color values of the RGB color information of the pixels of the target rows and the RGB color value of the RGB color information of the pixel of the center point;

determining the pixels of the target rows as the target pixels and the RGB color differences of the target pixels being in the preset range;

taking the pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expanding the depth information of the image contents in the first images.

14. The method for expanding image depth according to claim 8 , wherein the first images and the second images are the images shoot on the same object and shoot at the same angle.

15. A non-transitory storage medium having stored thereon instructions that, when executed by at least one processor of an electronic device, causes the least one processor to execute instructions of a method for expanding image depth, the method for expanding image depth comprising:

obtaining first images by a first sensor, wherein the first images comprise depth information;

obtaining second images by a second sensor, wherein the second images comprise gradient information, and the first images corresponding to the second images;

expanding the depth information of the first images according to the depth information of the first images and the gradient information of the second images;

generating third images based on the expanded the depth information of first images;

generating target depth map based on the depth information of the third images and the gradient information of the second image.

16. The non-transitory storage medium according to claim 15 , wherein method for expanding image depth further comprising:

selecting pixels in a preset area in the second images;

determining a pixel of a center point of the preset area;

calculating gradient differences between the gradient values of the gradient information of the pixels in the preset area and the gradient value of the gradient information of the pixel of the center point;

determining target pixels from the pixels of the second images according to the gradient differences and the gradient differences of the target pixels being in a preset range;

taking pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expanding the depth information of the image contents in the first images.

17. The non-transitory storage medium according to claim 16 , wherein the method for expanding image depth further comprising:

determining the preset area in the second images according to the depth information of the first images, wherein the depth value of the pixel of the first images correspond to the preset area of the second images being in a threshold range.

18. The non-transitory storage medium according to claim 16 , wherein the method for expanding image depth further comprising:

determining the depth information of the image contents in the first images;

expanding target depth information on the pixels with missing depth information of the image contents of the first images, wherein the target depth information is identical with the depth information of the image contents to be expanded.

19. The non-transitory storage medium according to claim 16 , wherein the gradient information is RGB color information or gray information.

20. The non-transitory storage medium according to claim 19 , wherein method for expanding image depth comprising:

selecting a matrix pixel block as the preset area in the second images, and determining the pixel of the center point of the matrix pixel block;

calculating RGB color differences between the RGB color values of the RGB color information of the pixels of the same column with the center point in the matrix pixel block, and the RGB color value of the RGB color information of the pixel of the center point;

determining target rows from rows of the matrix pixel block, and the RGB color differences of the pixels of the target rows being in the preset range;

calculating the RGB color differences between the RGB color values of the RGB color information of the pixels of the target rows and the RGB color value of the RGB color information of the pixel of the center point;

determining the pixels of the target rows as the target pixels and the RGB color differences of the target pixels being in the preset range;

taking the pixels of the first images corresponding to the target pixels of the second images as the image contents of the depth information to be expanded in the first images;

expanding the depth information of the image contents in the first images.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 31, 2021
From: MOBILE DRIVE TECHNOLOGY CO., LTD.
To: MOBILE DRIVE NETHERLANDS B.V.
Reel/Frame 057391/0564 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 9, 2021
From: HUANG, YU-KAI; HSU, WINSTON H.; LIU, YUEH-CHENG; WU, TSUNG-HAN; HUANG, TZU-KUEI; HUANG, CHUN-HSIANG
To: MOBILE DRIVE TECHNOLOGY CO.,LTD.
Reel/Frame 055876/0459 →
Continuity (2)
Provisional Application 63007929 · Apr 9, 2020
Related Publication 20210319576A1 · Oct 14, 2021