System and Method for Tracking Objects

• US 20120116662A1
• Filed: 11/09/2010
• Published: 05/10/2012
• Est. Priority Date: 11/09/2010
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations Incorporated (General Motors Company)
• Inventors: Zeng, Shuqing, Li, Yuanhong
• Granted Patent: US 8,818,702 B2
• Time in Patent Office: Days
• US Class Current: 701/300
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/027 comprising intertial navigation means, e.g. azimuth detector inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165

Abstract

A methods for tracking objects by generating kinematic models corresponding to the objects using a computerized object-tracking system including a data collection module receiving scan data associated with an object and generating, using the scan data, a new frame F, associated with a new time t+dt and including new points X. A clustering module identifies a new group G of new points X_i of the new frame F. A data association module associates the new group G with the object based on previous information associated with the object. A tracking module determines a new kinematic module M corresponding to the object based on the new group G.

Claims

1. A method for tracking objects by generating kinematic models corresponding to the objects using a computerized object-tracking system, the method comprising:

a data collection module of the object-tracking system receiving scan data associated with an object and generating, using the scan data, a new frame F, associated with a new time t+dt and including new points X;

a clustering module of the object-tracking system identifying a new group G of new points X_i of the new frame F, where i=1, . . . N, with N being a positive integer corresponding to a number of the new points;

a data association module of the object-tracking system associating the new group G with the object based on previous information associated with the object; and

a tracking module of the object-tracking system determining a new kinematic module M corresponding to the object based on the new group G.

2. The method of claim 1, further comprising a preprocessing module of the object-tracking system processing the new frame F prior to the clustering module identifying the new group G of new points X_i of the new frame F, wherein the preprocessing module processing the new frame F includes the preprocessing module filtering the new frame F to represent the new frame F by at least one of:

vehicle-reference coordinates; and

ground-reference coordinates.

3. The method of claim 1, wherein the clustering module identifies the new group G of new points X_i of the new frame F based on an affinity characteristic between certain of the new points X.

4. The method of claim 1, wherein the data association module associates the new group G with the object in response to determining a relationship between new kinematic characteristics associated with the new frame F and previous information representing the object.

5. The method of claim 1, wherein the tracking module determining the new kinematic module M corresponding to the object based on the new group G includes the tracking module determining the new kinematic model M corresponding to the object as a function of the new Group G and at least one of:

one or more previous groups G representing the object; and

one or more previous kinematic models representing the object.

6. The method of claim 1, wherein the tracking module determining the new kinematic module M corresponding to the object based on the new group G includes the tracking module generating a predicted group G_p.

7. The method of claim 6, wherein:

the tracking module generates the predicted group G_p as a function of a previous kinematic model representing the object, the previous group G, and a translation vector T;

the predicted group G_p corresponds to a future time t+δ

t, and is determined according to;

G<sub>t+δ

t</sub>^p=G_t+T_t|<sub>δ

t</sub>;

the translation vector T includes an x-direction translation component dx and a y-direction translation component dy;

the translation components are determined as a function of a velocity V_t and a velocity direction θ

t of the previous kinematic model representing the object; and

the translation components dx, dy are related to the velocity V_t and the velocity direction θ

t of the previous kinematic model representing the object according to;

8. The method of claim 6, wherein the tracking module, in determining the new kinematic module M iteratively matches the predicted group G_p to the new group G.

9. The method of claim 8, wherein the tracking module iteratively matching the predicted group G_p to the new group G includes the tracking module determining an initial translation adjustment vector Δ

T, and iteratively adjusting the translation vector T using the translation adjustment vector Δ

T.

10. The method of claim 9, wherein the tracking module determines the initial translation adjustment vector Δ

T using at least one of;

a localized point-matching technique; and

a maximum-likelihood technique.

11. The method of claim 10, wherein the localized point-matching technique includes identifying neighboring prediction points X_j, the neighboring prediction points X_j being points of the predicted group G_p located within a specified distance of each of the new points X_i of the new group G.

12. The method of claim 10, wherein the maximum-likelihood technique includes determining the translation adjustment vector Δ

T so as to maximize a likelihood that the predicted group G_p matches the new group G, including matching each of the new points X_i to a neighboring predicted point X_j of the predicted group G_p, such that an aggregate of distances between each new point X_i and neighboring prediction points X_j is minimized.

13. The method of claim 12, wherein the maximum-likelihood technique further includes adding the translation adjustment vector Δ

T to the initial translation vector T to produce an iterated translation vector T′

.

14. The method of claim 13, wherein the maximum-likelihood technique includes the tracking module determining whether the iterated translation vector T′

has converged so as to match the predicted group G_p to the new group G.

15. The method of claim 9 wherein:

if the magnitude of the translation adjustment vector Δ

T is above a predetermined threshold, the iterated translation vector T′

is further iterated; and

if the magnitude of the translation adjustment vector Δ

T is within the predetermined threshold, the iterated translation vector T′

is used to determine parameters of the new kinematic model M, including using components dx′

, dy′

of the iterated translation vector T′

to determine a velocity V_t and an angle of velocity θ

t for the new kinematic model M according to relationships represented as;

16. A tangible, non-transitory computer-readable medium for use in a vehicle to track a physical object external to the vehicle, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform steps of a method comprising:

receiving scan data associated with an object and generating, using the scan data, a new frame F, associated with a new time t+dt and including new points X;

identifying a new group G of new points X_i of the new frame F, where i=1, . . . N, with N being a positive integer corresponding to a number of the new points;

associating the new group G with the object based on previous information associated with the object; and

determining a new kinematic module M corresponding to the object based on the new group G.

17. The tangible, non-transitory computer-readable medium of claim 16, wherein the instructions, in causing the processor to determine the new kinematic module M corresponding to the object based on the new group G, causes the processor to generate a predicted group G_p.

18. The tangible, non-transitory computer-readable medium of claim 17, wherein the instructions, in causing the processor to determine the new kinematic module M, causes the processor to iteratively match the predicted group G_p to the new group G.

19. A transportation vehicle comprising:

a range sensor;

an on-board computer system including;

a processor; and

a computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform steps of a method comprising;

receiving scan data associated with an object from the range sensor and generating, using the scan data, a new frame F, associated with a new time t+dt and including new points X;

identifying a new group G of new points X_i of the new frame F, where i=1, . . . N, with N being a positive integer corresponding to a number of the new points;

associating the new group G with the object based on previous information associated with the object; and

determining a new kinematic module M corresponding to the object based on the new group G.

20. The vehicle of claim 19, wherein the instructions, in causing the processor to determine the new kinematic module M corresponding to the object based on the new group G, causes the processor to:

generate a predicted group G_p; and

iteratively match the predicted group G_p to the new group G.