METHOD AND APPARATUS TO BUILD 3-DIMENSIONAL GRID MAP AND METHOD AND APPARATUS TO CONTROL AUTOMATIC TRAVELING APPARATUS USING THE SAME

• US 20100040279A1
• Filed: 03/26/2009
• Published: 02/18/2010
• Est. Priority Date: 08/12/2008
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Kwon, Woong, Hyung, Seung Yong, Roh, Kyung Shik, Yoon, Sukjune, Kim, Hyun Kyu
• Granted Patent: US 8,571,302 B2
• Time in Patent Office: Days
• US Class Current: 382/153
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/593 from stereo images
• CPC Class Codes: G09B 25/06 for surveying; for geography, e.g. relief models globes G09B27/00; maps G09B29/00

Abstract

A method and apparatus to build a 3-dimensional grid map and a method and apparatus to control an automatic traveling apparatus using the same. In building a 3-dimensional map to discern a current location and a peripheral environment of an unmanned vehicle or a mobile robot, 2-dimensional localization and 3-dimensional image restoration are appropriately used to accurately build the 3-dimensional grid map more rapidly.

Claims

1. A method to build a 3-dimensional grid map, comprising:

acquiring a peripheral omni-directional image using a stereo omni-directional camera;

confirming a current 2-dimensional location using the omni-directional image;

performing 3-dimensional restoration of the omni-directional image; and

building the 3-dimensional grid map of the periphery of the stereo omni-directional camera by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration.

2. The method according to claim 1, wherein the confirming of a 2-dimensional location is performed through 2-dimensional localization and mapping using the omni-directional image.

3. The method according to claim 2, wherein the confirming of a 2-dimensional location is performed using feature points on an epipolar line of the omni-directional image.

4. The method according to claim 3, wherein the feature points are obtained by extracting a color edge.

5. The method according to claim 1, wherein a degree of occupation of a 3-dimensional grid is obtained using a result of the 3-dimensional restoration.

6. The method according to claim 5, wherein if a count occupied by a voxel of the 3-dimensional grid exceeds a prescribed number, a corresponding voxel is determined to be occupied.

7. A method to control an automatic traveling apparatus, comprising:

acquiring a peripheral omni-directional image using a stereo omni-directional camera;

confirming a current 2-dimensional location using the omni-directional image;

performing 3-dimensional restoration of the omni-directional image;

building a 3-dimensional grid map of the periphery of the stereo omni-directional camera by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration;

determining a traveling path to a target point from a current location based on the 3-dimensional restoration; and

controlling the automatic traveling apparatus to travel to the target point along the traveling path.

8. The method according to claim 7, wherein the confirming of a 2-dimensional location is performed through 2-dimensional localization and mapping using the omni-directional image.

9. The method according to claim 8, wherein the confirming of a 2-dimensional location is performed using feature points on an epipolar line of the omni-directional image.

10. The method according to claim 8, wherein the feature points are obtained by extracting a color edge.

11. The method according to claim 7, wherein a degree of occupation of a 3-dimensional grid is obtained using a result of the 3-dimensional restoration.

12. The method according to claim 11, wherein if a count occupied by a voxel of the 3-dimensional grid exceeds a prescribed number, a corresponding voxel is determined to be occupied.

13. A computer readable medium to contain computer-readable codes as a program to perform a method to build a 3-dimensional grid map, the method comprising:

acquiring a peripheral omni-directional image using a stereo omni-directional camera;

confirming a current 2-dimensional location using the omni-directional image;

performing 3-dimensional restoration of the omni-directional image; and

building the 3-dimensional grid map of the periphery of the stereo omni-directional camera by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration.

14. An apparatus to build a 3-dimensional grid map, comprising:

a camera to acquire a peripheral omni-directional image using a stereo omni-directional camera; and

a controller to confirm a current 2-dimensional location using the omni-directional image, to perform 3-dimensional restoration of the omni-directional image, and to build the 3-dimensional grid map of the periphery of the stereo omni-directional camera by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration.

15. A traveling apparatus to move along a path, comprising:

a controller to receive one or more peripheral omni-directional images from a stereo omni-directional camera, to confirm a current 2-dimensional location using the omni-directional images, to perform 3-dimensional restoration of the omni-directional images, and to build the 3-dimensional grid map of the periphery of the stereo omni-directional camera by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration; and

a moving device to move a body of the traveling apparatus according to a traveling path with respect to the 3-dimensional grid map.

16. A method to build a 3-dimensional grid map, comprising:

generating a current 2-dimensional location using one or more omni-directional images, and a 3-dimensional restoration of the omni-directional image; and

building the 3-dimensional grid map by combining a result of the 2-dimensional localization and a result of the 3-dimensional restoration.