UNSUPERVISED PARAMETER SETTINGS FOR OBJECT TRACKING ALGORITHMS

• US 20130058523A1
• Filed: 09/01/2011
• Published: 03/07/2013
• Est. Priority Date: 09/01/2011
• Status: Active Grant

• Current Assignee: Conduent Business Services, LLC (Conduent, Inc.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Wu, Wencheng, XU, Beilei
• Granted Patent: US 8,582,811 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 20/54 of traffic, e.g. cars on the road, trains or boats

Abstract

A method for automatically optimizing a parameter set for a tracking algorithm comprising receiving a series of image frames and processing the image frames using a tracking algorithm with an initialized parameter set. An updated parameter set is then created according to the processed image frames utilizing estimated tracking analytics. The parameters are validated using a performance metric that may be manually or automatically preformed using a GUI. The image frames are collected from a video camera with a fixed set-up at a fixed location. The image frames may include a training traffic video or a training video for tracking humans.

Claims

1. A method for parameter optimization, said method comprising:

receiving a series of image frames;

processing said series of image frames utilizing a tracking algorithm with an initialized parameter set;

creating an updated parameter set according to image frames processed from among said series of image frames; and

validating said updated parameter set utilizing a performance metric to automatically optimize said parameter set for said tracking algorithm.

2. The method of claim 1 wherein receiving said series of image frames further comprises:

collecting said series of image frames from at least one video camera with a fixed setup at a fixed location.

3. The method of claim 2 wherein processing said series of image frames further comprises:

estimating tracking analytics according to received image frames from among said series of image frames.

4. The method of claim 3 wherein creating said updated parameter set according to said processed image frames from among said series of image frames, further comprises:

deriving said updated parameter set utilizing said estimated tracking analytics in response to estimating said tracking analytics according to said received image frames from among said series of image frames.

5. The method of claim 4 wherein said series of image frames comprise a training traffic video.

6. The method of claim 4 wherein said series of image frames comprise a training video for tracking a human.

7. The method of claim 1 wherein validating said updated parameter set utilizing said performance metric to automatically optimize said parameter for tracking said tracking algorithm, further comprises:

validating said updated parameter set by manually inspecting said updated parameter set utilizing a graphical user interface associated with a computer.

8. The method of claim 7 wherein validating said updated parameter set by manually inspecting said updated parameter set using said graphical user interface associated with said computer further includes:

displaying video analysis of said image frames thereby providing a semi-automated update of said parameter set.

9. A method for parameter optimization, said method comprising:

receiving a series of image frames collected from a video camera with a fixed set-up fixed location;

processing said series of image frames utilizing a tracking algorithm with an initialized parameter set;

estimating tracking analytics according to image frames received from among said series of image frames;

creating an updated parameter set utilizing said tracking analytics according to said processed image frames from among said series of image frames; and

validating said updated parameter set utilizing a performance metric to automatically optimize said parameter set for said tracking algorithm.

10. The method of claim 9 wherein said series of image frames comprise at least one of:

a training traffic video and a training video for tracking a human.

11. The method of claim 9 wherein validating said updated parameter set further includes:

validating said updated parameter set by manually inspecting said updated parameter set utilizing a graphical user interface associated with a computer.

12. The method of claim 11 wherein validating said updated parameter set by manually inspecting said updated parameter set utilizing said graphical user interface associated with said computer further comprises:

displaying video analysis of said series of image frames to provide a semi-automated update of said parameter set.

13. A system for parameter optimization, said system comprising:

a processor;

a data bus coupled to said processor; and

a computer-usable medium embodying computer code, said computer-usable medium being coupled to said data bus, said computer program code comprising instructions executable by said processor and configured for;

receiving a series of image frames;

processing said series of image frames utilizing a tracking algorithm with an initialized parameter set;

creating an updated parameter set according to said processed image frames among said series of image frames; and

validating said updated parameter set utilizing a performance metric to automatically optimize said parameter set for said tracking algorithm.

14. The system of claim 13 wherein said instructions are further configured for:

collecting said series of image frames from a video camera with a fixed set-up at a fixed location.

15. The system of claim 14 wherein said instructions are further configured for:

estimating tracking analytics according to said image frames received from among said series of image frames.

16. The system of claim 15 wherein said instructions are further configured for:

deriving said updated parameter set utilizing said estimated tracking analytics.

17. The system of claim 16 wherein said series of image frames comprise a training traffic video.

18. The system of claim 16 wherein said series of image frames comprise a training video for tracking a human.

19. The system of claim 13 wherein instructions are further configured for:

validating said updated parameter set by manually inspecting said updated parameter set utilizing a graphical user interface associated with a computer.

20. The system of claim 13 wherein said instructions are further configured for:

validating said updated parameter set by displaying video analysis of said series of image frames; and

manually inspecting said updated parameter set utilizing said graphical user interface associated with said computer to provide a semi-automated update of said parameter set.