SYSTEM AND METHOD FOR DETERMINING A TRAJECTORY

• US 20200132465A1
• Filed: 12/31/2019
• Published: 04/30/2020
• Est. Priority Date: 11/03/2017
• Status: Active Grant

• Current Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Original Assignee: Beijing Didi Infinity Technology And Development Co.Ltd.
• Inventors: SHU, Weihuan, XU, Hailiang
• Granted Patent: US 11,692,829 B2
• Time in Patent Office: Days
• CPC Class Codes: G01C 21/1654 with electromagnetic compass
• CPC Class Codes: G01C 22/006 Pedometers
• CPC Class Codes: G06T 2207/20081 Training; Learning
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51

Abstract

Embodiments of the disclosure provide a system and method for determining a trajectory of a subject. The method can include acquiring motion data of the subject to which the mobile device is attached; determining a motion status of the subject based on the motion data; and determining the trajectory based on the motion data using a trajectory model corresponding to the motion status.

Claims

1. A computer-implemented method for determining a trajectory of a subject, comprising:

acquiring, via at least one sensor of a mobile device, motion data of the subject to which the mobile device is attached;

determining, by a processor, a motion status of the subject based on the motion data; and

determining, by the processor, the trajectory based on the motion data using a trajectory model corresponding to the motion status.

2. The computer-implemented method of claim 1, herein the determining a motion status of the subject based on the motion data further comprises;

determining at least one of a stride length, a stride frequency, and a direction of movement based on the motion data; and

determining the motion status based on at least one of the stride length, the stride frequency, and the direction of movement, wherein the motion status comprises a movement gesture of the subject or a place on the subject where the mobile device is attached.

3. The computer-implemented method of claim 2, wherein the determining the trajectory based on the motion data using a trajectory model corresponding to the motion status further comprises:

generating the trajectory based on the at least one of the stride length, the stride frequency, and the direction of movement using the trajectory model corresponding to the motion status.

4. The computer-implemented method of claim 1, further comprising:

training the trajectory model based on training data.

5. The computer-implemented method of claim 4, further comprising:

acquiring the training data associated with the subject in a plurality of time periods;

acquiring reference movements associated with the subject in respective time periods;

clustering the training data and the reference movements into groups; and

generating the trajectory model based on the training data and the reference movements of respective groups.

6. The computer-implemented method of claim 5, wherein the generating the trajectory model based on the training data and the reference movements of the respective groups further comprises:

generating the trajectory model using machine learning techniques.

7. The computer-implemented method of claim 5, wherein each group is associated with a different motion status.

8. The computer-implemented method of claim 1, wherein the at least one sensor includes at least one of an accelerometer, a gyroscope, an electronic compass, or a barometer of the mobile device.

9. The computer-implemented method of claim 4, wherein the training data comprises Pedestrian Dead Reckoning (PDR) data.

10. The method of claim 2, wherein the movement gesture comprises at least one of walking, jogging, or climbing.

11. A system for generating a trajectory of a subject, comprising:

a communication interface configured to communicate with a mobile device attached to the subject, acquiring motion data of the subject;

a memory configured to store at least one trajectory model; and

at least one processor configured to;

determine a motion status of the subject based on the motion data, and

determine the trajectory based on the motion data using a trajectory model corresponding to the motion status.

12. The system of claim 11, wherein the at least one processor is further configured to:

determine at least one of a stride length, a stride frequency, and a direction of movement based on the motion data; and

determine the motion status based on at east one of the stride length, the stride frequency, and the direction of movement, wherein the motion status comprises a movement gesture of the subject or a place on the subject where the mobile device is attached.

13. The system of claim 12, wherein the at least one processor is further configured to:

generate the trajectory based on the at least one of the stride length, the stride frequency, and the direction of movement using the trajectory model corresponding to the motion status.

14. The system of claim 11, wherein the at least one processor is further configured to:

train the trajectory model based on training data.

15. The system of claim 14, wherein the at least one processor is further configured to:

acquire the training data associated with the subject in a plurality of time periods;

acquire reference movements associated with the subject in respective time periods;

cluster the training data and the reference movements into groups; and

generate the trajectory model based on the training data and the reference movements of respective groups.

16. The system of claim 15, wherein the processor is further configured to:

generate the trajectory model using machine learning techniques.

17. The system of claim 15, wherein each group is associated with a different motion status.

18. The system of claim 11, wherein the at least one sensor includes at least one of an accelerometer, a gyroscope, an electronic compass, or a barometer of the mobile device.

19. The system of claim 12, wherein the movement gesture comprises at least one of walking, jogging, or climbing.

20. A non-transitory computer-readable medium that stores a set of instructions, when executed by at least one processor of a device, cause the device to perform a method for generating a trajectory of a subject, the method comprising:

acquiring motion data of the subject to which the mobile device is attached;

determining a motion status of the subject based on the motion data; and

determining the trajectory based on the motion data using a trajectory model corresponding to the motion status.