System and method for extracting corner point in space using pixel information, and robot using the system

• US 20060083427A1
• Filed: 09/29/2005
• Published: 04/20/2006
• Est. Priority Date: 10/15/2004
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Jung, Myung-Jin, Bang, Seok-Won, Park, Dong-Ryeol, Lee, Hyoung-Ki
• Granted Patent: US 7,653,247 B2
• Time in Patent Office: Days
• US Class Current: 382/201
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20164 Salient point detection; Corner detection
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 2207/30248 Vehicle exterior or interior
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

A system and method extracting a corner point in a space using pixel information obtained from a camera are provided. The corner point extracting system includes a light generation module emitting light in a predetermined form (such as a plane form), an image acquisition module acquiring an image of a reflector reflecting the light emitted from the light generation module, and a control module obtaining distance data between the light generation module and the reflector using the acquired image and extracting a corner point by performing split-merge using a threshold proportional to the distance data. The threshold is a value proportional to the distance data which corresponds to pixel information of the image acquisition module.

Claims

1. A corner point extracting system comprising:

a light generation module emitting light in a predetermined form;

an image acquisition module acquiring an image of a reflector reflecting the light emitted from the light generation module; and

a control module obtaining distance data between the light generation module and the reflector using the acquired image and extracting a corner point by performing split-merge using a threshold proportional to the distance data,

wherein the threshold is a value proportional to the distance data which corresponds to pixel information of the image acquisition module.

2. The corner point extracting system of claim 1, wherein the light is laser light.

3. The corner point extracting system of claim 1, wherein the threshold is the value proportional to the distance data corresponding to a 1 pixel distance in the image acquisition module.

4. The corner point extracting system of claim 1, wherein the threshold is proportional to |F(x_s, y_s)−

F(x_s, y_s+1)|, where x_s and y_s indicate random coordinates in the acquired image, y_s+1 is a coordinate shifted from the position y_s by 1 pixel in a y-direction, and F(a, b) is a coordinate value on a new plane, into which a coordinate value [a b]^T is converted using the triangulation.

5. The corner point extracting system of claim 1, wherein the control module obtains the distance data using coordinates of the acquired image in a triangulation.

17. The corner point extracting system of claim 1, wherein the predetermined form comprises a plane form.

6. A method of extracting a corner point, comprising:

emitting light to a reflector in a predetermined form;

acquiring an image of the reflector reflecting the light;

obtaining distance data between a light emission point and the reflector using the acquired image; and

extracting a corner point by performing split-merge based on a threshold proportional to the distance data,

wherein the threshold is a value proportional to the distance data which corresponds to pixel information of the acquired image.

7. The method of claim 6, wherein the light is laser light.

8. The method of claim 6, wherein the threshold is the value proportional to the distance data corresponding to a 1 pixel distance in the image acquisition module.

9. The method of claim 6, wherein the threshold is proportional to |F (x_s, y_s)−

F (x_s, y_s+1)|, where x_s and y_s indicate random coordinates in the acquired image, y_s+1 is a coordinate shifted from the position y_s by 1 pixel in a y-direction, and F (a, b) is a coordinate value on a new plane, into which a coordinate value [a b]^T is converted using the triangulation.

10. The method of claim 6, wherein the obtaining of the distance data includes obtaining the distance data using coordinates of the acquired image in a triangulation.

18. The method of claim 6, wherein the predetermined form comprises a plane form.

11. A mobile robot comprising:

a corner point extracting system acquiring an image of a reflector which reflects light emitted thereto in a predetermined form and extracting a corner point using pixel information of the acquired image;

a central control system determining a moving direction and speed based on a position of the extracted corner point; and

a driving system moving the mobile robot according to the moving direction and speed determined by the central control system.

12. The mobile robot of claim 11, wherein the corner point extracting system comprises:

a light generation module emitting the light in the plane form;

an image acquisition module acquiring the image of the reflector reflecting the light emitted from the light generation module; and

a control module obtaining distance data between the light generation module and the reflector using the acquired image and extracting the corner point by performing split-merge using a threshold proportional to the distance data, and

the threshold is a value proportional to the distance data corresponding to pixel information of the image acquisition module.

13. The mobile robot of claim 12, wherein the light is laser light.

14. The mobile robot of claim 12, wherein the threshold is the value proportional to the distance data corresponding to a 1 pixel distance in the image acquisition module.

15. The mobile robot of claim 12, wherein the threshold is proportional to |F(x_s, y_s)−

F(x_s, y_s+1)|, where x_s and y_s indicate random coordinates in the acquired image, y_s+1 is a coordinate shifted from the position y_s by 1 pixel in a y-direction, and F(a, b) is a coordinate value on a new plane, into which a coordinate value [a b]^T is converted using the triangulation.

16. The mobile robot of claim 12, wherein the control module obtains the distance data using coordinates of the acquired image in a triangulation.

19. The mobile robot of claim 11, wherein the predetermined form comprises a plane form.