IP Library Granted Patent US 11,361,453
Granted Patent B2
US 11,361,453 · App. 16/916,317 · Granted Jun 14, 2022

Method and apparatus for detecting and tracking target, electronic device and storage media

Inventors: Xiaoxing Zhu (Beijing, CN); Yongyi Sun (Beijing, CN); Chengfa Wang (Beijing, CN)
Assignee: APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECHNOLOGY CO., LTD.
G06T7/292G08B13/19641G08B13/19645H04L47/125H04N5/247H04N7/025H04N7/08
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 11,361,453
App. No.
16/916,317
Granted
Jun 14, 2022
Kind
B2
Abstract

A method and apparatus for detecting and tracking a target, an electronic device and a storage medium are provided. The method includes: cameras, detection modules, tracking modules and storage queues are provided in advance; the numbers of cameras, storage queues and tracking modules are equal, and there is a one-to-one correspondence between the cameras and the storage queues and between the cameras and the tracking modules; distributing data streams collected by the cameras to the plurality of detection modules; detecting, by the detection modules, the received data streams, and sending detection results of the data streams collected by the cameras, to the storage queues corresponding to the cameras; and extracting, by the tracking modules corresponding to the cameras, the detection results from the storage queues corresponding to the cameras, and using the detection results for tracking the target.

Claims (69)

1. A method for detecting and tracking a target, comprises:

collecting a plurality of data streams by a plurality of cameras;

distributing a data stream collected by each of the plurality of cameras in parts to a plurality of different detection modules;

detecting, by each of the plurality of different detection modules, a part of the data stream received by the detection module;

sending, by each of the plurality of different detection modules, a detection result of the part, received by the detection module, of the data stream collected by the camera, to a storage queue corresponding to the camera; wherein the plurality of cameras corresponds to a plurality of storage queues;

extracting, by a tracking module corresponding to the camera, detection results of parts of the data stream from the storage queue corresponding to the camera; wherein the plurality of cameras correspond to a plurality of tracking modules; and

using, by the tracking module, the detection results of the parts of the data stream for tracking the target;

wherein there is a one-to-one correspondence between the plurality of cameras and the plurality of storage queues and between the plurality of cameras and the plurality of tracking modules.

2. The method according to claim 1 , wherein the distributing the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, comprises:

distributing the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, in a load balancing manner.

3. The method according to claim 1 , wherein the storage queue comprises a storage middleware.

4. The method according to claim 2 , wherein the storage queue comprises a storage middleware.

5. The method according to claim 1 , wherein the distributing the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, comprises:

adding an identification of the camera to the data stream;

distributing the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

wherein the sending the detection result of the part, received by the detection module, of the data stream collected by the camera, to the storage queue corresponding to the camera, comprises:

determining the corresponding camera according to the identification of the camera contained in the data stream; and

sending the detection result of the data stream collected by the camera, to the storage queue corresponding to the determined camera.

6. The method according to claim 2 , wherein the distributing the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, comprises:

adding an identification of the camera to the data stream;

distributing the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

wherein the sending the detection result of the part, received by the detection module, of the data stream collected by the camera, to the storage queue corresponding to the camera, comprises:

determining the corresponding camera according to the identification of the camera contained in the data stream; and

sending the detection result of the data stream collected by the camera, to the storage queue corresponding to the determined camera.

7. An apparatus for detecting and tracking a target, comprising:

a plurality of cameras for collecting a plurality of data streams;

a plurality of different detection modules;

at least a processor; and

a memory communicatively connected to at least one processor, wherein the memory includes at least a plurality of storage queues, and there is a one-to-one correspondence between the plurality of cameras and the plurality of storage queues,

wherein the memory stores instructions executable by the at least one processor, and the instructions, when executed by the at least one processor, cause the at least one processor to implement a plurality of tracking modules, and there is a one-to-one correspondence between the plurality of cameras and the plurality of tracking modules, and

wherein the instructions, when executed by the at least one processor, cause the at least one processor to:

distribute a data stream collected by each of the plurality of cameras to in parts the plurality of different detection modules;

detect, by each of the plurality of different detection modules, a part of the data stream received by the detection module;

send, by each of the plurality of different detection modules, a detection result of the part, received by the detection module, of the data stream collected by the camera, to a storage queue corresponding to the camera;

extract, by a tracking module corresponding to the camera, detection results of parts of the data stream from the storage queue corresponding to the camera; and

use, by the tracking module, the detection results of the parts of the data stream for tracking the target.

8. The apparatus according to claim 7 , wherein the instructions, when executed by the at least one processor, cause the at least one processor further to: distribute the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, in a load balancing manner.

9. The apparatus according to claim 7 , wherein the storage queue comprises a storage middleware.

10. The apparatus according to claim 8 , wherein the storage queue comprises a storage middleware.

11. The apparatus according to claim 7 , wherein the instructions, when executed by the at least one processor, cause the at least one processor further to:

add an identification of the camera to the data stream;

distribute the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

determine the corresponding camera according to the identification of the camera contained in the data stream; and

send the detection result of the data stream collected by the camera, to the storage queue corresponding to the determined camera.

12. The apparatus according to claim 8 , wherein the instructions, when executed by the at least one processor, cause the at least one processor further to:

add an identification of the camera to the data stream;

distribute the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

determine the corresponding camera according to the identification of the camera contained in the data streams; and

send the detection result of the data stream collected by the camera, to the storage queue corresponding to the determined camera.

13. A non-transitory computer readable storage medium storing computer instructions, wherein the computer instructions, when executed by a computer, cause the computer to:

collecting a plurality of data streams by a plurality of cameras;

distribute a data stream collected by each of the plurality of cameras in parts to a plurality of different detection modules;

detect, by each of the plurality of different detection modules, a part of the data stream received by the detection module;

send, by each of the plurality of different detection modules, a detection result of the part, received by the detection module, of the data stream collected by the camera, to a storage queue corresponding to the camera; wherein the plurality of cameras corresponds to a plurality of storage queues, wherein there is a one-to-one correspondence between the plurality of cameras and the plurality of storage queues;

extract, by a tracking module corresponding to the camera, detection results of parts of the data stream from the storage queue corresponding to the camera; wherein the plurality of cameras correspond to a plurality of tracking modules; and

use, by the tracking module, the detection results of the parts of the data stream for tracking the target, wherein there is a one-to-one correspondence between the plurality of cameras and the plurality of tracking modules.

14. The non-transitory computer readable storage medium according to claim 13 , wherein the computer instructions, when executed by the computer, cause the computer further to: distribute the data stream collected by each of the plurality of cameras in parts to the plurality of different detection modules, in a load balancing manner.

15. The non-transitory computer readable storage medium according to claim 13 , wherein the storage queue comprises a storage middleware.

16. The non-transitory computer readable storage medium according to claim 14 , wherein the storage queue comprises a storage middleware.

17. The non-transitory computer readable storage medium according to claim 13 , wherein the computer instructions, when executed by the computer, cause the computer further to:

add an identification of the camera to the data stream;

distribute the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

determine the corresponding camera according to the identification of the camera contained in the data stream; and

send the detection result of the data stream collected by the camera, to the storage queue corresponding to the determined camera.

18. The non-transitory computer readable storage medium according to claim 14 , wherein the computer instructions, when executed by the computer, cause the computer further to:

add an identification of the camera to the data stream;

distribute the data stream containing the identification of the camera in parts, to the plurality of different detection modules;

determine the corresponding camera according to the identification of the camera contained in the data stream; and

send the detection result of the data stream collected by the camera, to thestorage queue corresponding to the determined camera.

Assignments (2)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2021
From: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
To: APOLLO INTELLIGENT CONNECTIVITY (BEIJING) TECHNOLOGY CO., LTD.
Reel/Frame 057789/0357 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 30, 2020
From: ZHU, XIAOXING; SUN, YONGYI; WANG, CHENGFA
To: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.
Reel/Frame 053085/0258 →
Priority Claims (1)
CN 201911025501.4 · Oct 25, 2019 · national
Continuity (1)
Related Publication 20210125353A1 · Apr 29, 2021