OBJECT TRACKING

• US 20130022234A1
• Filed: 07/22/2011
• Published: 01/24/2013
• Est. Priority Date: 07/22/2011
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Gellaboina, Mahesh Kumar, Miller, Ben A., Ramegowda, Dinesh, Swaminathan, Gurumurthy, U S, Yadhunandan, Mariappan, MaryRosaline
• Granted Patent: US 8,929,588 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• 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

Methods, devices, and systems for object tracking are described herein. One or more method embodiments include receiving an initial set of track points associated with a trajectory of an object, compressing the initial set of track points into a plurality of track segments, each track segment having a start track point and an end track point, and storing the plurality of track segments to represent the trajectory of the object.

Claims

1. A computer implemented method for tracking an object, comprising:

receiving an initial set of track points associated with a trajectory of an object;

compressing the initial set of track points into a plurality of track segments, each track segment having a start track point and an end track point; and

storing the plurality of track segments to represent the trajectory of the object.

2. The method of claim 1, wherein the method includes:

assigning the initial set of track points a track identification number; and

storing the initial set of track points and the track identification number.

3. The method of claim 2, wherein compressing the initial set of track points into a plurality of track segments includes:

receiving a track point of the initial set of track points associated with the trajectory of the object; and

identifying the track identification number of the track point.

4. The method of claim 3, wherein compressing the initial set of track points into a plurality of track segments includes:

determining a covariance matrix from a number of available track point spatial positions;

determining eigen values for the covariance matrix;

using a least of the eigen values as a measure to determine a variation from a straight line trajectory; and

comparing the least of the eigen values with a spatial variation threshold to determine whether to stop or continue the compression.

5. The method of claim 3, wherein the method further includes:

determining a velocity based error and a spatial error of the track point based on a previous track point having the track identification number; and

determining if the velocity error and the spatial error of the track point are below a predetermined error threshold.

6. The method of claim 5, wherein the method further includes:

updating a track segment with the track point if the velocity error and the spatial error are below the predetermined error threshold; and

analyzing a subsequent track point having the track identification number.

7. The method of claim 5, wherein the method further includes:

storing the track segment without the track point to represent a portion of the trajectory of the object, wherein the previous track point is the end track point of the track segment of the plurality of track segments.

8. The method of claim 6, wherein the method further includes:

re-writing the track segment with the track point a start track point of a track segment.

9. The method of claim 1, wherein the method includes:

determining an angle of each of the plurality of track segments representing the trajectory of the object with respect to a horizontal axis of a boundary; and

storing the angle of each of the plurality of track segments.

10. A computer implemented method for tracking an object, comprising:

compressing a plurality of initial data points associated with a trajectory of an object into a plurality of track segments, each track segment having a start track point and an end track point;

determining an angle of each track segment contained in the plurality of track segments with respect to a horizontal axis;

storing the plurality of track segments and the angle of each track segment in a database; and

determining whether an event detection rule has been satisfied by at least a portion of the plurality of track segments associated with the object.

11. The method of claim 10, wherein the method further includes:

receiving metadata for the plurality of initial data points associated with the trajectory of the object.

12. The method of claim 11, wherein the metadata includes positions, boundary of a restricted zone, velocity, and direction at each data point in the trajectory of the object.

13. The method of claim 10, wherein determining the angle of each track segment includes using the starting point of each track segment as an origin of an axis for calculation of the angle along the track segment from the start point to the end point.

14. The method of claim 10, wherein the event detection rule includes restricted zone coordinates of a restricted zone.

15. The method of claim 14, wherein the method further includes:

detect and retrieve track segments of a trajectory of an object that have intersected the restricted zone coordinates of the bounding box; and

detect and retrieve track segments that have an angle such that the track segment enters the restricted zone coordinates of the bounding box.

16. The method of claim 14, wherein the method further includes:

sending an alarm when the event detection rule has been satisfied.

17. A computing device for tracking an object, comprising:

a memory; and

a processor coupled to the memory, wherein the processor is configured to execute executable instructions stored in the memory to;

compress a plurality of data points associated with a trajectory of an object into a plurality of track segments, each track segment having a start track point and an end track point;

index the plurality of track segments in a database; and

detect an event based on an event rule.

18. The computing device of claim 17, wherein the processor is configured to execute the executable instructions to:

index characteristics of the plurality of track segments for the trajectory of the object in the database, wherein the characteristics include positions of the track segment relative to a restricted zone boundary, time stamps of the track segment, velocity, and direction at track segment in the trajectory of the object.

19. the computing device of claim 17, wherein the processor is configured to execute the executable instructions to:

determine the angle of each track segment of the trajectory of the object; and

store and index the angle of each track segment in the database.

20. The computing device of claim 19, wherein the processor is configured to execute the executable instructions to:

receive a request from a user to analyze the trajectory of an object; and

query the database for the event rules based on the track segments and the angles of the track segments of the trajectory of the object.

21. The computing device of claim 19, wherein the processor is configured to execute the executable instructions to:

assign the plurality of data points associated with the trajectory of the object a track identification number; and

storing the plurality of track segments associated with the plurality of data points along with the track identification number.

22. A computer implemented method for tracking an object, comprising:

compressing a trajectory of an object,

storing the compressed trajectory in a database; and

retrieving the compressed trajectory to execute a video analytics algorithm on the compressed trajectory for detection of an event.