Systems and methods for stereoscopic imaging

Patent metadata

Field	Value
Publication number	US-2021125361-A1
Application number	US-202117143849-A
Country	US
Kind code	A1
Filing date	Jan 7, 2021
Priority date	Jul 6, 2016
Publication date	Apr 29, 2021
Grant date	—

Abstract

One or more block configurations are selected, based on object information associated with an object, from a plurality of block configurations having at least one of different sizes or different shapes. A first point in a first image is matched with a corresponding second point in a second image using the one or more block configurations.

First claim

What is claimed is:

1 . A block matching method comprising:
selecting, based on object information associated with an object, one or more block configurations from a plurality of block configurations having at least one of different sizes or different shapes; and matching, using the one or more block configurations, a first point in a first image with a corresponding second point in a second image.

2 . The method of claim 1 , wherein:
the object information is indicative of a texture of the object; and sizes in the one or more block configurations are negatively correlated to a roughness of the texture indicated by the object information.

3 . The method of claim 1 , wherein selecting the one or more block configurations comprises selecting a block configuration having a shape that matches at least one of a shape or a size of the object or a portion of the object, such that the selected block configuration matches a texture of the object or a texture of the portion of the object.

4 . The method of claim 1 , wherein:
selecting the one or more block configurations comprises selecting a first block configuration and a second block configuration from the plurality of block configurations that have at least one of different shapes or different sizes; and matching the first point with the corresponding second point comprises:
obtaining a first matching cost by matching, using the first block configuration, the first point in the first image with the corresponding second point in the second image;
obtaining a second matching cost by matching, using the second block configuration, the first point in the first image with the corresponding second point in the second image; and
matching the first point in the first image with the corresponding second point in the second image based on the first matching cost and the second matching cost.

5 . The method of claim 1 , wherein selecting the one or more block configurations comprises dynamically selecting the one or more block configurations from the plurality of block configurations.

6 . The method of claim 1 , wherein matching the first point with the corresponding second point comprises:
determining matching costs between the first point in the first image and a plurality of candidate second points in the second image; and identifying the corresponding second point from the plurality of candidate second points based on the matching costs.

7 . The method of claim 6 , wherein determining the matching costs between the first point and the plurality of candidate second points comprises at least one of:
determining matching costs between the first point in the first image and a plurality of candidate second points on a line of the second image to identify the corresponding second point; or determining, using one block configuration from the block configurations, individual matching costs between the first point and the plurality of candidate second points to determine at least one matching cost that includes at least one of:
selecting the at least one matching cost from the individual matching costs;
determining the at least one matching cost based on weighted individual matching costs by applying first weights to the individual matching costs; or
determining the at least one matching cost based on weighted block configurations by applying second weights to the plurality of block configurations.

8 . The method of claim 1 , further comprising:
determining an object distance based on a disparity between the first point in the first image and the corresponding second point in the second image.

9 . The method of claim 1 , wherein matching the first point with the corresponding second point comprises determining, using each block configuration of the plurality of block configurations, individual matching costs between the first point and each of a plurality of candidate second points in the second image to select candidate second points respectively corresponding to the plurality of block configurations.

10 . The method of claim 9 , further comprising:
obtaining candidate disparities between the first point and the selected candidate second points, respectively; determining a disparity between the first point and the corresponding second point based on the candidate disparities; and determining an object distance based on the disparity.

11 . The method of claim 1 , wherein matching the first point with the corresponding second point comprises at least one of:
matching, using the one or more block configurations, a first pixel in the first image with a corresponding second pixel in the second image; or matching, using the one or more block configurations, a first feature in the first image with a corresponding second feature in the second image.

12 . A stereoscopic imaging system comprising:
a first imaging device configured to obtain a first image; a second imaging device configured to obtain a second image; and one or more processors configured to:
select, based on object information associated with an object, one or more block configurations from a plurality of block configurations having at least one of different sizes or different shapes; and
match, using the one or more block configurations, a first point in the first image with a corresponding second point in the second image.

13 . The stereoscopic imaging system of claim 12 , wherein:
the object information is indicative of a texture of the object; and sizes in the one or more block configurations are negatively correlated to a roughness of the texture indicated by the object information.

14 . The stereoscopic imaging system of claim 12 , wherein the one or more processors are further configured to select a block configuration having a shape that matches at least one of a shape or a size of the object or a portion of the object, such that the selected block configuration matches a texture of the object or a texture of the portion of the object.

15 . The stereoscopic imaging system of claim 12 , where the one or more processors are further configured to:
select a first block configuration and a second block configuration from the plurality of block configurations that have a least one of different shapes or different sizes; obtain a first matching cost by matching, using the first block configuration, the first point in the first image with the corresponding second point in the second image; obtain a second matching cost by matching, using the second block configuration, the first point in the first image with the corresponding second point in the second image; and match the first point in the first image with the corresponding second point in the second image based on the first matching cost and the second matching cost.

16 . The stereoscopic imaging system of claim 12 , wherein the one or more processors are further configured to:
determine matching costs between the first point in the first image and a plurality of candidate second points in the second image; and identify the corresponding second point from the plurality of candidate second points based on the matching costs.

17 . The stereoscopic imaging system of claim 12 , the one or more processors are further configured to determine an object distance based on a disparity between the first point in the first image and the corresponding second point in the second image.

18 . The stereoscopic imaging system of claim 12 , wherein the one or more processors are further configured to determine, using each block configuration of the

Assignees

• Sz Dji Technology Co Ltd

Inventors

• Yang Kang
• Gao Mingming

Classifications

• H04N13/128

  Adjusting depth or disparity · CPC title

• H04N2013/0081

  Depth or disparity estimation from stereoscopic image signals · CPC title

• H04N13/239

  using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) · CPC title

• G06T7/593 Primary

  from stereo images · CPC title

• G06T2207/10012

  Stereo images · CPC title