Robot and control method thereof

• US 20100172571A1
• Filed: 12/11/2009
• Published: 07/08/2010
• Est. Priority Date: 01/06/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kwon, Woong, Hyung, Seung Yong, Roh, Kyung Shik, Ahn, Sung Hwan, Yoon, Suk June, Kim, Hyun Kyu
• Granted Patent: US 8,824,775 B2
• Time in Patent Office: Days
• US Class Current: 382/153
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/248 involving reference images or patches
• CPC Class Codes: G06T 7/55 from multiple images

Abstract

Disclosed herein are a feature point used to localize an image-based robot and build a map of the robot and a method of extracting and matching an image patch of a three-dimensional (3D) image, which is used as the feature point. It is possible to extract the image patch converted into the reference image using the position information of the robot and the 3D position information of the feature point. Also, it is possible to obtain the 3D surface information with the brightness values of the image patches to obtain the match value with the minimum error by a 3D surface matching method of matching the 3D surface information of the image patches converted into the reference image through the ICP algorithm.

Claims

1. A control method of a robot, comprising:

acquiring a 3D image of an environment where the robot moves;

extracting a feature point from the acquired 3D image and converting a plane including the extracted feature point into a reference image; and

extracting image patches from the reference image and matching the image patches.

2. The control method according to claim 1, wherein the converting the plane including the feature point into the reference image comprises converting the plane including the feature point into a reference distance to acquire an image corresponding to the reference distance.

3. The control method according to claim 2, wherein the extracting the image patches from the reference image comprises obtaining a conversion matrix with the reference image to extract predetermined pixel-unit image patches from the reference distance.

4. The control method according to claim 3, wherein the matching the image patches comprises:

obtaining 3D surface information using brightness values of the image patches; and

matching the 3D surface information three-dimensionally using an ICP algorithm.

5. The control method according to claim 4, further comprising determining whether brightness values of the 3D surface information satisfies a predetermined reference value, wherein, when it is determined that the brightness values of the 3D surface information satisfies the predetermined reference value, the 3D surface information is matched by the ICP algorithm.

6. A control method of a robot, comprising:

acquiring a 3D image of an environment where the robot moves;

extracting a feature point from the acquired 3D image and converting the extracted feature point into a reference distance;

extracting an image patch of an image corresponding to the reference distance;

obtaining 3D surface information using a brightness value of the image patch; and

matching the 3D surface information three-dimensionally using an ICP algorithm.

7. The control method according to claim 6, wherein the extracting the image patch of the image corresponding to the reference distance comprises obtaining a conversion matrix with the image corresponding to the reference distance and extracting predetermined pixel-unit image patches from the reference distance.

8. A robot comprising:

an image acquisition unit to acquire a 3D image of an environment where the robot moves; and

a control unit to extract a feature point from the acquired 3D image and convert a plane including the feature point into a reference image and to extract image patches from the reference image and match the image patches.

9. The robot according to claim 8, wherein the control unit converts the plane including the feature point into a reference distance, acquires an image corresponding to the reference distance, and converts the acquired image into the reference image.

10. The robot according to claim 9, wherein the control unit obtains a conversion matrix with the reference image to extract predetermined pixel-unit image patches from the reference distance.

11. The robot according to claim 10, wherein the control unit obtains 3D surface information using brightness values of the image patches, and matches the 3D surface information three-dimensionally using an ICP algorithm.

12. The robot according to claim 11, wherein the control unit determines whether the brightness values of the 3D surface information satisfies a predetermined reference value, and, when it is determined that the brightness values of the 3D surface information satisfies the predetermined reference value, matches the 3D surface information using the ICP algorithm.