IP Library › Granted Patent US 11,386,576
Granted Patent B2
US 11,386,576 · App. 16/940,178 · Granted Jul 12, 2022

Image processing apparatus, method of tracking a target object, and storage medium

Inventor: Koichi Magai (Tokyo, JP)
Assignee: Canon Kabushiki Kaisha
G06T7/74G06T7/20G06T7/90G06F3/14G06T2207/10024
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,386,576
App. No.
16/940,178
Granted
Jul 12, 2022
Kind
B2
Abstract

An image processing apparatus that tracks a target object by estimating a position of the target object on each of a plurality of images. A first estimating unit estimates the position of the target object in at least one of images. A second estimating unit estimates the position of the target object in at least one of images, wherein estimating accuracy of the position of the target object in the second estimating process is lower than the estimating accuracy in the first estimation process. A correcting unit corrects the position of the target object estimated by the second estimation process on a second image, based on the position of the target object estimated by the first estimation process on a first image. The second image is an image captured at a different time from the first image.

Claims (52)

1. An image processing apparatus that tracks a target object by estimating a position of the target object on each of a plurality of images, the image processing apparatus comprising:

a processor; and

a memory storing executable instructions which, when executed by the processor, cause the image capturing apparatus to perform operations including:

performing a first estimation process to estimate the position of the target object in at least one of the plurality of images;

performing a second estimating process to estimate the position of the target object in at least one of the plurality of images, wherein estimating accuracy of the position of the target object in the second estimating process is lower than the estimating accuracy in the first estimation process;

correcting, based on the position of the target object estimated by the first estimation process on a first image of the plurality of images, the position of the target object estimated by the second estimation process on a second image of the plurality of the images, wherein the second image is an image captured at a different time from the first image; and

determining a reliability of a tracking history composed of a plurality of positions estimated by the first estimation process or the second estimation process for the target object in each of the plurality of images.

2. The image processing apparatus according to claim 1 ,

wherein the first estimation process is a process for estimating the position of the target object included in the image using a pattern matching.

3. The image processing apparatus according to claim 2 , wherein the first estimation process is a process for estimating the position of the target object included in the image using a geometric pattern matching.

4. The image processing apparatus according to claim 1 ,

wherein the second estimation process is an estimation process using an average velocity vector.

5. The image processing apparatus according to claim 1 ,

wherein the second estimation process is a process for estimating the position of the target object included in the image using information of a color of the target object.

6. The image processing apparatus according to claim 1 ,

wherein the second image is captured after the first image, and

the position of the target object estimated by the second estimation process on the second image is corrected based on the position of the target object estimated by the first estimation process on the first image.

7. The image processing apparatus according to claim 6 , wherein the position of the target object estimated by the second estimation process on the second image is corrected based on the position of the target object estimated by the first estimation process on the first image and the position of the target object estimated by the first estimation process on a third image which is captured after the second image.

8. The image processing apparatus according to claim 1 ,

wherein the reliability of the tracking history is determined based on the number of the position of the target object estimated by the first estimation process in the plurality of positions composing the tracking history.

9. The image processing apparatus according to claim 1 ,

wherein a degree of stability of a moving direction of the target object tracked by estimating the position is determined based on the first estimation process or the second estimation process and, if the degree of stability is higher than a predetermined threshold value, the position of the target object estimated by the first estimation process or the second estimation process is corrected on an image of an acquired latest frame.

10. The image processing apparatus according to claim 1 ,

wherein executing the executable instructions causes the information processing apparatus to perform further operations including:

presenting an occurrence of a shift of the position of the target object to a user.

11. The image processing apparatus according to claim 10 ,

wherein a frame including the position of the target object is displayed on a display device and presents the occurrence of the shift of the position of the target object to the user by changing a color of the frame including the position of the target object.

12. The image processing apparatus according to claim 1 , wherein the second image is captured before the first image, and

the position of the target object estimated by the second estimation process on the second image is corrected based on the position of the target object estimated by the first estimation process on the first image and the position of the target object estimated by the first estimation process on a third image which is captured after the second image.

13. The image processing apparatus according to claim 1 , wherein executing the executable instructions causes the information processing apparatus to perform further operations including:

estimating an average velocity vector of the target object based on positions of the target object estimated by the first estimation process on the plurality of images, and

the position of the target object estimated by the second estimation process on the second image is corrected based on the estimated average velocity vector of the target object.

14. The image processing apparatus according to claim 1 , wherein the reliability of the tracking history is determined based on a ratio of a number of positions of the target object estimated by the first estimation process included in the tracking history.

15. The image processing apparatus according to claim 1 ,

wherein if the reliability of the tracking history is higher than or equal to a first threshold value, position satisfying a first condition among the positions of the target object estimated by the second estimation process is corrected, and

if the reliability of the tracking history is lower than the first threshold value, position satisfying a second condition among the positions of the target object estimated by the second estimation process is corrected.

16. The image processing apparatus according to claim 15 ,

wherein the first condition is that at least one of a position in the immediately preceding frame or a position in the immediately succeeding frame of the target object whose position is estimated by the second estimation processing is a position estimated by the first estimation processing,

the second condition is that only one of a position in the immediately preceding frame and a position in the immediately succeeding frame of the target object whose position is estimated by the second estimation processing is a position estimated by the first estimation processing.

17. The image processing apparatus according to claim 1 , wherein executing the executable instructions causes the information processing apparatus to perform further operations including:

tracking the target object by estimating a position of the target object on each of the plurality of images, and wherein

the position of the target object on each of a plurality of images is selected based on a predetermined condition among a plurality of candidates for tracking positions.

18. A method of tracking a target object by estimating a position of the target object on each of a plurality of images, the method comprising:

performing a first estimation process to estimate the position of the target object in at least one of the plurality of images;

performing a second estimating process to estimate the position of the target object in at least one of the plurality of images, wherein estimating accuracy of the position of the target object in the second estimating process is lower than the estimating accuracy in the first estimation process;

correcting the position of the target object estimated by the second estimation process on a second image of the plurality of the images, based on the position of the target object estimated by the first estimation process on a first image of the plurality of images, wherein the second image is an image captured at a different time from the first image; and

determining a reliability of a tracking history composed of a plurality of positions estimated by the first estimation process or the second estimation process for the target object in each of the plurality of images.

19. A non-transitory computer-readable storage medium storing a program that, when executed by a computer, causes the computer to perform a method of tracking a target object by estimating a position of the target object on each of a plurality of images, the method comprising:

performing a first estimation process to estimate the position of the target object in at least one of the plurality of images;

performing a second estimating process to estimate the position of the target object in at least one of the plurality of images, wherein estimating accuracy of the position of the target object in the second estimating process is lower than the estimating accuracy in the first estimation process;

correcting the position of the target object estimated by the second estimation process on a second image of the plurality of the images, based on the position of the target object estimated by the first estimation process on a first image of the plurality of images, wherein the second image is an image captured at a different time from the first image; and

determining a reliability of a tracking history composed of a plurality of positions estimated by the first estimation process or the second estimation process for the target object in each of the plurality of images.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 8, 2020
From: MAGAI, KOICHI
To: CANON KABUSHIKI KAISHA
Reel/Frame 054013/0826 →
Priority Claims (1)
JP JP2019-140086 · Jul 30, 2019 · national
Continuity (1)
Related Publication 20210035327A1 · Feb 4, 2021
Cited By (1)
US 12,236,016