METHOD OF MOBILE PLATFORM DETECTING AND TRACKING DYNAMIC OBJECTS AND COMPUTER-READABLE MEDIUM THEREOF

• US 20110052043A1
• Filed: 08/16/2010
• Published: 03/03/2011
• Est. Priority Date: 08/25/2009
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Hyung, Seung Yong, Roh, Kyung Shik, Ahn, Sung Hwan, Yoon, Suk June
• Granted Patent: US 8,649,557 B2
• Time in Patent Office: Days
• US Class Current: 382/154
• CPC Class Codes: G05D 1/0242 using non-visible light signals, e.g. IR or UV signals
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/30252 Vehicle exterior; Vicinity of vehicle
• CPC Class Codes: G06T 7/277 involving stochastic approaches, e.g. using Kalman filters

Abstract

Disclosed herein is a computer-readable medium and method of a mobile platform detecting and tracking dynamic objects in an environment having the dynamic objects. The mobile platform acquires a three-dimensional (3D) image using a time-of-flight (TOF) sensor, removes a floor plane from the acquired 3D image using a random sample consensus (RANSAC) algorithm, and individually separates objects from the 3D image. Movement of the respective separated objects is estimated using a joint probability data association filter (JPDAF).

Claims

1. A method of a mobile platform detecting and tracking moving objects, comprising:

acquiring a three-dimensional (3D) image of an environment in which the mobile platform moves;

extracting and removing, using a processor, a floor plane from the 3D image; and

individually separating, using the processor, objects from the 3D image with the floor plane removed.

2. The method according to claim 1, wherein the extracting and removing the floor plane from the 3D image comprises using a random sample consensus (RANSAC) algorithm.

3. The method according to claim 1, wherein the 3D image acquired by the mobile platform comprises a depth map acquired by a time-of-flight (TOF) sensor.

4. The method according to claim 3, wherein the extracting and removing the floor plane from the 3D image comprises performing a RANSAC algorithm using pixel information of the depth map acquired by the TOF sensor as data.

5. The method according to claim 3, wherein the individually separating the objects from the 3D image with the floor plane removed comprises using a blob algorithm.

6. The method according to claim 3, further comprising estimating movement of the respective separated objects using a joint probability data association filter (JPDAF).

7. The method according to claim 6, further comprising registering the respective separated objects as formal dynamic objects when it is determined that the respective separated objects are dynamic objects as a result of estimating the movement of the respective separated objects using the JPDAF and when a predetermined condition is satisfied.

8. The method according to claim 6, wherein the predetermined condition entails a covariance value being less than a predetermined critical value.

9. The method according to claim 6, further comprising estimating location or velocity of the registered formal dynamic objects to track the dynamic objects.

10. The method according to claim 9, further comprising designing a travel route along which the mobile platform avoids the registered formal dynamic objects using the estimated location or velocity of the registered formal dynamic objects.

11. At least one computer readable medium comprising computer readable instructions that control at least one processor to implement a method, comprising:

acquiring a three-dimensional (3D) image of an environment in which the mobile platform moves;

extracting and removing a floor plane from the 3D image; and

individually separating objects from the 3D image with the floor plane removed.

12. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 11, wherein the extracting and removing the floor plane from the 3D image comprises using a random sample consensus (RANSAC) algorithm.

13. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 11, wherein the 3D image acquired by the mobile platform comprises a depth map acquired by a time-of-flight (TOF) sensor.

14. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 13, wherein the extracting and removing the floor plane from the 3D image comprises performing a RANSAC algorithm using pixel information of the depth map acquired by the TOF sensor as data.

15. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 13, wherein the individually separating the objects from the 3D image with the floor plane removed comprises using a blob algorithm.

16. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 13, further comprising estimating movement of the respective separated objects using a joint probability data association filter (JPDAF).

17. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 16, further comprising registering the respective separated objects as formal dynamic objects when it is determined that the respective separated objects are dynamic objects as a result of estimating the movement of the respective separated objects using the JPDAF and when a predetermined condition is satisfied.

18. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 16, wherein the predetermined condition entails a covariance value being less than a predetermined critical value.

19. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 16, further comprising estimating location or velocity of the registered formal dynamic objects to track the dynamic objects.

20. The at least one computer readable medium comprising computer readable instructions that control at least one processor to implement the method of claim 19, further comprising designing a travel route along which the mobile platform avoids the registered formal dynamic objects using the estimated location or velocity of the registered formal dynamic objects.