IP Library › Granted Patent US 11,699,240
Granted Patent B2
US 11,699,240 · App. 16/819,487 · Granted Jul 11, 2023

Target tracking method and apparatus, and storage medium

Inventors: Shaohui Liu (Beijing, CN); Hongwei Qin (Beijing, CN)
Assignee: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.
G06T7/248G06T7/70G06T2207/10016G06T2207/30241
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 11,699,240
App. No.
16/819,487
Granted
Jul 11, 2023
Kind
B2
Abstract

A target tracking method includes: obtaining feature data of a reference frame of a first image frame, wherein the first image frame and at least one second image frame have the same reference frame; and determining the position of a tracking target in the first image frame based on the feature data of the reference frame. Based on the embodiments in the present disclosure, feature data of a reference frame of a first image frame is acquired, and the position of a tracking target in the first image frame is determined based on the feature data of the reference frame.

Claims (56)

1. A target tracking method, comprising:

obtaining feature data of a reference frame of a first image frame, wherein the first image frame and at least one second image frame have a same reference frame; and

determining a position of a tracking target in the first image frame based on the feature data of the reference frame,

wherein determining the position of the tracking target in the first image frame based on the feature data of the reference frame comprises:

obtaining, based on the feature data of the reference frame, relative position information of the tracking target in the first image frame relative to the tracking target in the reference frame; and

obtaining the position of the tracking target in the first image frame based on the relative position information and position information of the tracking target in the reference frame,

wherein the method further comprises:

determining whether the first image frame is used as an updated reference frame, which comprises:

determining, based on an intersection over union between a first bounding box of the tracking target in the first image frame and a second bounding box of the tracking target in the reference frame, whether the first image frame is used as the updated reference frame, which specifically comprises:

in response to the intersection over union between the first bounding box and the second bounding box being less than or equal to a preset threshold, determining that the first image frame is used as the updated reference frame; and

in response to the intersection over union between the first bounding box and the second bounding box being greater than the preset threshold, determining that the reference frame does not need to be updated and the feature data of the reference frame is continually used for guiding a next image frame.

2. The method according to claim 1 , wherein obtaining the feature data of the reference frame comprises:

obtaining the feature data of the reference frame from a memory.

3. The method according to claim 1 , wherein determining whether the first image frame is used as the updated reference frame further comprises:

determining, based on an interval between the first image frame and the reference frame, whether the first image frame is used as the updated reference frame.

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

storing feature data of the first image frame in response to determining that the first image frame is used as the updated reference frame.

5. The method according to claim 1 , wherein determining the position of the tracking target in the first image frame based on the feature data of the reference frame comprises:

performing feature extraction on the first image frame to obtain feature data of the first image frame; and

obtaining the position of the tracking target in the first image frame based on the feature data of the reference frame and the feature data of the first image frame.

6. The method according to claim 5 , wherein obtaining the position of the tracking target in the first image frame based on the feature data of the reference frame and the feature data of the first image frame comprises:

connecting the feature data of the first image frame to the feature data of the reference frame to obtain a connection feature; and

obtaining the position of the tracking target in the first image frame based on the connection feature.

7. A target tracking apparatus, comprising:

a processor; and

a memory, configured for storing instructions executable by the processor, wherein the processor is configured to:

obtain feature data of a reference frame of a first image frame, wherein the first image frame and at least one second image frame have a same reference frame;

determine a position of a tracking target in the first image frame based on the feature data of the reference frame;

obtain, based on the feature data of the reference frame, relative position information of the tracking target in the first image frame relative to the tracking target in the reference frame; and

obtain the position of the tracking target in the first image frame based on the relative position information and position information of the tracking target in the reference frame,

wherein the processor is configured to determine, based on an intersection over union between a first bounding box of the tracking target in the first image frame and a second bounding box of the tracking target in the reference frame, whether the first image frame is used as an updated reference frame,

wherein the processor is specifically configured to:

in response to the intersection over union between the first bounding box and the second bounding box being less than or equal to a preset threshold, determine that the first image frame is used as the updated reference frame; and

in response to the intersection over union between the first bounding box and the second bounding box being greater than the preset threshold, determine that the reference frame does not need to be updated and the feature data of the reference frame is continually used for guiding a next image frame.

8. The apparatus according to claim 7 , wherein the processor is configured to obtain the feature data of the reference frame from the memory.

9. The apparatus according to claim 7 , wherein the processor is further configured to:

use the first image frame as the updated reference frame when an interval between the first image frame and the reference frame meets a preset condition.

10. The apparatus according to claim 7 , wherein the processor is further configured to store the feature data of the first image frame in response to determining that the first image frame is used as the updated reference frame.

11. The apparatus of claim 7 , wherein the processor is further configured to:

perform feature extraction on the first image frame to obtain feature data of the first image frame; and

obtain the position of the tracking target in the first image frame based on the feature data of the reference frame and the feature data of the first image frame.

12. A non-transitory computer storage medium, configured to store computer-readable instructions that, when being executed by a processor, cause the processor to execute a target tracking method, the target tracking method comprising:

obtaining feature data of a reference frame of a first image frame, wherein the first image frame and at least one second image frame have a same reference frame; and

determining a position of a tracking target in the first image frame based on the feature data of the reference frame,

wherein determining the position of the tracking target in the first image frame based on the feature data of the reference frame comprises:

obtaining, based on the feature data of the reference frame, relative position information of the tracking target in the first image frame relative to the tracking target in the reference frame; and

obtaining the position of the tracking target in the first image frame based on the relative position information and position information of the tracking target in the reference frame,

wherein the target tracking method further comprises:

determining whether the first image frame is used as an updated reference frame, which comprises:

determining, based on an intersection over union between a first bounding box of the tracking target in the first image frame and a second bounding box of the tracking target in the reference frame, whether the first image frame is used as the updated reference frame, which specifically comprises:

in response to the intersection over union between the first bounding box and the second bounding box being less than or equal to a preset threshold, determining that the first image frame is used as the updated reference frame; and

in response to the intersection over union between the first bounding box and the second bounding box being greater than the preset threshold, determining that the reference frame does not need to be updated and the feature data of the reference frame is continually used for guiding a next image frame.

13. The non-transitory computer storage medium according to claim 12 , wherein obtaining the feature data of the reference frame comprises:

obtaining the feature data of the reference frame from a memory.

14. The non-transitory computer storage medium according to claim 12 , wherein determining whether the first image frame is used as the updated reference frame further comprises:

determining, based on an interval between the first image frame and the reference frame, whether the first image frame is used as the updated reference frame.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 22, 2020
From: LIU, SHAOHUI; QIN, HONGWEI
To: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.
Reel/Frame 053285/0961 →
Priority Claims (2)
CN 201810182797.X · Mar 6, 2018 · national
CN 201810184967.8 · Mar 6, 2018 · national
Continuity (2)
Continuation PCTCN2019076355 · Feb 27, 2019
Related Publication 20200258242A1 · Aug 13, 2020
Cited By (1)
US 12,205,339