Tracking method and tracking apparatus

• US 20080193009A1
• Filed: 01/29/2008
• Published: 08/14/2008
• Est. Priority Date: 02/08/2007
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Digital Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Sonoura, Takafumi
• Granted Patent: US 8,180,104 B2
• Time in Patent Office: Days
• US Class Current: 382/153
• CPC Class Codes: G01S 5/0294 Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
• CPC Class Codes: G01S 5/12 by co-ordinating position lines of different shape, e.g. hyperbolic, circular, elliptical or radial
• CPC Class Codes: G06V 10/40 Extraction of image or video features

Abstract

According to an embodiment of the present invention, a tracking method includes detecting a mobile unit within a space, tracking the detected mobile unit, making a position determination of the mobile unit to be tracked to obtain positional data, and making a movement prediction of the mobile unit, based on a high frequency component of positional data.

Claims

1. A tracking method comprising:

detecting a mobile unit within a space;

tracking the detected mobile unit;

making a position determination of the mobile unit to be tracked to obtain positional data; and

making a movement prediction of the mobile unit, based on a high frequency component of positional data.

2. The method according to claim 1, wherein the detection comprises detecting the mobile unit within the space, using an image obtained by imaging the mobile unit.

3. The method according to claim 2, wherein the detection comprises detecting the mobile unit within the space, through a difference process between the image obtained by imaging the mobile unit and a reference image for the difference process.

4. The method according to claim 2, wherein the position determination comprises deciding a representative point in an image area where the mobile unit is detected from the image, and determining the representative point as the position of the mobile unit.

5. The method according to claim 4, wherein the position determination comprises deciding a point nearest to the lower end of the image in the image area, as the representative point.

6. The method according to claim 4, wherein the position determination comprises deciding a point nearest to the center of the image in the image area, as the representative point.

7. The method according to claim 1, wherein the detection comprises detecting the mobile unit within the space, using a signal transmitted from the mobile unit.

8. The method according to claim 1, wherein high pass positional data obtained by filtering the positional data through a high pass filter is used as the high frequency component.

9. The method according to claim 8, wherein the high pass filter is of a sequential or recursive computation type.

10. The method according to claim 1, wherein the movement prediction is made, based on the high frequency component and a low frequency component of the positional data obtained by the position determination.

11. The method according to claim 10, wherein low pass positional data obtained by filtering the positional data through a low pass filter is used as the low frequency component.

12. The method according to claim 11, wherein the low pass filter is of a sequential or recursive computation type.

13. The method according to claim 10, wherein the movement prediction is made, based on a differential amount of the high frequency component, and the angle between a differential amount of the high frequency component and a differential amount of the low frequency component.

14. The method according to claim 1, further comprising:

extracting a motion feature amount of the mobile unit to be tracked;

filtering the motion feature amount through a frequency filter; and

distinguishing each mobile unit, based on the motion feature amount filtered through the frequency filter.

15. The method according to claim 14, wherein the extraction comprises extracting an optical flow of the mobile unit, as the motion feature amount of the mobile unit.

16. The method according to claim 15, wherein the distinction comprises distinguishing each mobile unit, based on the angle of the optical flow.

17. The method according to claim 1, further comprising:

outputting prediction data obtained by the movement prediction, via a user interface or via a communication interface, or notifying the prediction data to the mobile unit that is an autonomous mobile unit.

18. The method according to claim 1, further comprising:

intervening in the movement operation of the mobile unit, according to prediction data obtained by the movement prediction.

19. A tracking apparatus comprising:

a detection unit configured to detect a mobile unit within a space;

a tracking unit configured to track the detected mobile unit;

a determination unit configured to make a position determination of the mobile unit to be tracked; and

a prediction unit configured to make a movement prediction of the mobile unit, based on a high frequency component of positional data obtained by the position determination.

20. The apparatus according to claim 19, further comprising:

an extraction unit configured to extract a motion feature amount of the mobile unit to be tracked;

a filtering unit configured to filter the motion feature amount through a frequency filter; and

a distinction unit configured to distinguish each mobile unit, based on the motion feature amount filtered through the frequency filter.