IP Library › Granted Patent US 12,333,746

Granted Patent B2

US 12,333,746 · App. 17/955,884 · Granted Jun 17, 2025

Method for estimating depth, electronic device, and storage medium

Inventors: Yu-Hsuan Chien (New Taipei, TW); Chin-Pin Kuo (New Taipei, TW)

Assignee: HON HAI PRECISION INDUSTRY CO., LTD.

G06T7/521 G01S13/08 G01S13/867 G01S13/89 G06T2207/10028 G06T2207/20081 G06T2207/20084 G06T2207/30261

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 12,333,746
App. No.: 17/955,884
Granted: Jun 17, 2025
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A method for estimating depth implemented in an electronic device includes obtaining a first image; inputting the first image into a depth estimation model, and obtaining a first depth image; obtaining a depth ratio factor, the depth ratio factor indicating a relationship between a relative depth and a depth of each pixel in the first depth image; and obtaining depth information of the first depth image according to the first depth image and the depth ratio factor.

Claims (86)

1. A method for estimating depth implemented in an electronic device comprising:

obtaining a first image;

inputting the first image into a depth estimation model, and obtaining a first depth image;

obtaining a depth scale factor, the depth scale factor indicating a relationship between a relative depth and a depth of each pixel in the first depth image;

obtaining external parameters between a camera device and a radar;

obtaining a second image captured by the camera device and a three-dimensional point cloud image obtained by the radar;

converting the three-dimensional point cloud image into a two-dimensional image according to the external parameters;

inputting the second image into the depth estimation model, and outputting a second depth image;

calculating a depth scale relationship according to the two-dimensional image and the second depth image; and

calculating the depth scale factor according to the depth scale relationship; and

obtaining depth information of the first depth image according to the first depth image and the depth scale factor.

2. The method according to claim 1 , wherein obtaining a depth scale factor comprises:

obtaining a distance between a pixel point and the camera device, and determining the distance to be the depth of the pixel point;

calculating a ratio between the relative depth of the pixel point and the depth value of the pixel point, and obtaining the depth scale relationship of the pixel; and

obtaining the depth scale factor according to the depth scale relationship of the pixels.

3. The method according to claim 2 , wherein obtaining a distance between a pixel point and the camera device comprises:

obtaining the distance between the pixel point and the camera device by the radar.

4. The method according to claim 3 , wherein obtaining the distance between the pixel point and the camera device by the radar comprises:

obtaining a three-dimensional point cloud image scanned by the radar corresponding to the first image;

obtaining external parameters between the camera device and the radar; and

converting the three-dimensional point cloud image into a two-dimensional image according to the external parameters, the two-dimensional image comprising the depth values.

5. The method according to claim 1 , wherein calculating a depth scale relationship according to the two-dimensional image and the second depth image comprises:

obtaining the depth value corresponding to the pixel in the second depth image according to the two-dimensional image;

calculating the depth scale relationship of the pixel point according to the depth value corresponding to the pixel point and the relative depth of the pixel point;

obtaining the depth scale relationship of all pixels in the second depth image; and

calculating the depth scale factor according to the depth scale relationship of all the pixels.

6. The method according to claim 5 , wherein calculating the depth scale factor according to the depth scale relationship of all the pixels comprises:

obtaining the depth scale relationship of all the second images; and

calculating the depth scale factor according to the depth scale relationship of all the second images.

7. An electronic device comprising:

at least one processor; and

a storage device coupled to the at least one processor and storing instructions for execution by the at least one processor to cause the at least one processor to:

obtain a first image;

input the first image into a depth estimation model, and obtain a first depth image;

obtain a depth scale factor, the depth scale factor indicating a relationship between a relative depth and a depth of each pixel in the first depth image;

obtain external parameters between a camera device and a radar;

obtain a second image captured by the camera device and a three-dimensional point cloud image obtained by the radar;

convert the three-dimensional point cloud image into a two-dimensional image according to the external parameters;

input the second image into the depth estimation model, and output a second depth image;

calculate a depth scale relationship according to the two-dimensional image and the second depth image; and

calculate the depth scale factor according to the depth scale relationship; and

obtain depth information of the first depth image according to the first depth image and the depth scale factor.

8. The electronic device according to claim 7 , wherein the at least one processor is further caused to:

obtain a distance between a pixel point and the camera device, and determine the distance to be the depth of the pixel point;

calculate a ratio between the relative depth of the pixel point and the depth value of the pixel point, and obtaining the depth scale relationship of the pixel; and

obtain the depth scale factor according to the depth scale relationship of the pixels.

9. The electronic device according to claim 8 , wherein the at least one processor is further caused to:

obtain the distance between the pixel point and the camera device by the radar.

10. The electronic device according to claim 9 , wherein the at least one processor is further caused to:

obtain a three-dimensional point cloud image scanned by the radar corresponding to the first image;

obtain external parameters between the camera device and the radar; and

convert the three-dimensional point cloud image into a two-dimensional image according to the external parameters, the two-dimensional image comprising the depth values.

11. The electronic device according to claim 7 , wherein the at least one processor is further caused to:

obtain the depth value corresponding to the pixel in the second depth image according to the two-dimensional image;

calculate the depth scale relationship of the pixel point according to the depth value corresponding to the pixel point and the relative depth of the pixel point;

obtain the depth scale relationship of all pixels in the second depth image; and

calculate the depth scale factor according to the depth scale relationship of all the pixels.

12. The electronic device according to claim 11 , wherein the at least one processor is further caused to:

obtain the depth scale relationship of all the second images; and

calculate the depth scale factor according to the depth scale relationship of all the second images.

13. A non-transitory computer-readable storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device, the processor is configured to perform a method for estimating depth, wherein the method comprises: