TRACKING DEVICE AND TRACKING METHOD

• US 20150131858A1
• Filed: 11/10/2014
• Published: 05/14/2015
• Est. Priority Date: 11/13/2013
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: NAKAYAMA, Osafumi
• Granted Patent: US 9,734,395 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/443 by matching or filtering
• CPC Class Codes: G06V 10/761 Proximity, similarity or dissimilarity measures

Abstract

A non-transitory computer-readable medium storing a program for tracking a feature point in an image that causes a computer to execute a process, the process includes: calculating first values indicating degree of corner for respective pixels in another image, based on change of brightness values in horizontal direction and vertical direction; calculating second values indicating degree of similarity between respective areas in the another image and a reference area around the feature point in the image, based on comparison between the respective areas and the reference area; calculating third values indicating overall degree of corner and similarity, based on the first values and the second values; and tracking the feature point by identifying a point in the another image corresponding to the feature point in the image, based on the third values.

Claims

1. A non-transitory computer-readable medium storing a program for tracking a feature point in an image that causes a computer to execute a process, the process comprising:

calculating first values indicating degree of corner for respective pixels in another image, based on change of brightness values in horizontal direction and vertical direction;

calculating second values indicating degree of similarity between respective areas in the another image and a reference area around the feature point in the image, based on comparison between the respective areas and the reference area;

calculating third values indicating overall degree of corner and similarity, based on the first values and the second values; and

tracking the feature point by identifying a point in the another image corresponding to the feature point in the image, based on the third values.

2. The non-transitory computer-readable medium according to claim 1, wherein the third values are products of the first values and the second values, respectively.

4. The non-transitory computer-readable medium according to claim 1, the process further comprising:

storing information regarding coordination of the point that is identified into a memory for next tracking.

5. The non-transitory computer-readable medium according to claim 1, wherein the calculating of the first values calculates the first values by derivation of the brightness values in the horizontal direction and the vertical direction.

6. The non-transitory computer-readable medium according to claim 1, the process further comprising:

setting a searching area in the another image based on a position of the feature point in the image, and

wherein the areas are set within the searching area.

7. The non-transitory computer-readable medium according to claim 6, wherein the searching area is centered at the position of the feature point or at another position that is predicted based on the position of the feature point.

8. The non-transitory computer-readable medium according to claim 1, wherein the calculating of the second values calculates the second values based on the comparison between respective brightness patterns of the areas and a brightness pattern of the reference area.

3. The non-transitory computer-readable medium according to claim 3, wherein the identifying identifies the point which has a maximum third value from among the pixels in the another image.

9. A tracking device for tracking a feature point in an image comprising:

a memory; and

a processor coupled to the memory and configured to;

calculate first values indicating degree of corner for respective pixels in another image, based on change of brightness values in horizontal direction and vertical direction,

calculate second values indicating degree of similarity between respective areas in the another image and a reference area around the feature point in the image, based on comparison between the respective areas and the reference area,

calculate third values indicating overall degree of corner and similarity, based on the first values and the second values, and

track the feature point by identifying a point in the another image corresponding to the feature point in the image, based on the third values.

10. The tracking devise according to claim 9, wherein

the tracking device is mounted on a vehicle, and

the image and the another image are captured by a camera that is installed on the vehicle.

11. The tracking device according to claim 9, wherein the third values are products of the first values and the second values, respectively.

12. The tracking device according to claim 11, wherein the identifying identifies the point which has a maximum third value from among the pixels in the another image.

13. The tracking device according to claim 9, wherein the processor is configured to store information regarding coordination of the point that is identified into a memory for next tracking.

14. The tracking device according to claim 9, wherein the first values are calculated by derivation of the brightness values in the horizontal direction and the vertical direction.

15. The tracking device according to claim 9, wherein

the processor is configured to set a searching area in the another image based on a position of the feature point in the image, and

the areas are set within the searching area.

16. The tracking device according to claim 15, wherein the searching area is centered at the position of the feature point or at another position that is predicted based on the position of the feature point.

17. The tracking device according to claim 9, wherein the second values are calculated based on the comparison between respective brightness patterns of the areas and a brightness pattern of the reference area.

18. A tracking method executed by a computer for tracking a feature point in an image, the tracking method comprising:

calculating first values indicating degree of corner for respective pixels in another image, based on change of brightness values in horizontal direction and vertical direction;

calculating second values indicating degree of similarity between respective areas in the another image and a reference area around the feature point in the image, based on comparison between the respective areas and the reference area;

calculating third values indicating overall degree of corner and similarity, based on the first values and the second values; and

tracking the feature point by identifying a point in the another image corresponding to the feature point in the image, based on the third values.