Detecting objects crossing a virtual boundary line

1. A method for detecting objects crossing a virtual boundary line comprising:

defining a virtual boundary line in a region of interest;

establishing a set of ground patch regions surrounding the virtual boundary line;

extracting a set of attributes from each of the set of ground patch regions;

updating a ground patch history model with the set of attributes from each of the set of ground patch regions; and

analyzing the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

2. The method according to claim 1 further comprising generating an alert in the case that the object is detected crossing the virtual boundary line in the video region of interest.

3. The method according to claim 2 further comprising analyzing each of the set of ground patch regions to identify foreground objects within each of the set of ground patch regions.

4. The method according to claim 3 , the analyzing comprising:

analyzing appearance features within the ground patch history model for each of the set of ground patch regions;

determining if a pair of similar ground patch regions is present among the set of ground patch regions based on the appearance features within the ground patch history model for each of the set of ground patch regions;

determining a location of each of the pair of similar ground patch regions; and

comparing a direction of motion for each of the pair of similar ground patch regions in the case that each of the pair of similar ground patch regions is located on a different side of the virtual boundary line in the video region of interest.

5. The method according to claim 4 , wherein the alert is generated in the case that the direction of motion for each of the pair of similar ground patch regions is substantially the same.

6. A system for detecting objects crossing a virtual boundary line, the system comprising:

at least one processing unit;

memory operably associated with the at least one processing unit; and

an object detection tool storable in memory and executable by the at least one processing unit, the object detection tool comprising:

a boundary component configured to:

define a virtual boundary line in a video region of interest; and

establish a set of ground patch regions surrounding the virtual boundary line;

an extraction component configured to:

extract a set of attributes from each of the set of ground patch regions; and

update a ground patch history model with the set of attributes from each of the set of ground patch regions; and

an analysis component configured to analyze the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

7. The object detection tool according to claim 6 further comprising a reporting component configured to generate an alert in the case that the object is detected crossing the virtual boundary line in the video region of interest.

8. The object detection tool according to claim 7 , the boundary component further configured to analyze each of the set of ground patch regions to identify foreground objects within each of the set of ground patch regions.

9. The object detection tool according to claim 8 , the analysis component further configured to:

analyze appearance features within the ground patch history model for each of the set of ground patch regions;

determine if a pair of similar ground patch regions is present among the set of ground patch regions based on the appearance features within the ground patch history model for each of the set of ground patch regions;

determine a location of each of the pair of similar ground patch regions;

compare a direction of motion for each of the pair of similar ground patch regions in the case that each of the pair of similar ground patch regions is located on a different side of the virtual boundary line in the video region of interest.

10. The object detection tool according to claim 9 , wherein the reporting component is configured to generate the alert in the case that the direction of motion for each of the pair of similar ground patch regions is substantially the same.

11. A computer-readable storage device storing computer instructions, which when executed, enables a computer system to detect objects crossing a virtual boundary line, the computer instructions comprising:

defining a virtual boundary line in a video region of interest;

establish a set of ground patch regions surrounding the virtual boundary line;

extracting a set of attributes from each of the set of ground patch regions;

updating a ground patch history model with the set of attributes from each of the set of ground patch regions; and

analyzing the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

12. The computer-readable storage device according to claim 11 further comprising computer instructions for generating an alert in the case that the object is detected crossing the virtual boundary line in the video region of interest.

13. The computer-readable storage device according to claim 12 further comprising computer instructions for analyzing each of the set of ground patch regions to identify foreground objects within each of the set of ground patch regions.

14. The computer-readable storage device according to claim 13 , the computer instructions for analyzing the appearance model further comprising computer instructions for:

analyzing appearance features within the ground patch history model for each of the set of ground patch regions;

determining if a pair of similar ground patch regions is present among the set of ground patch regions based on the appearance features within the ground patch history model for each of the set of ground patch regions;

determining a location of each of the pair of similar ground patch regions;

comparing a direction of motion for each of the pair of similar ground patch regions in the case that each of the pair of similar ground patch regions is located on a different side of the virtual boundary line in the video region of interest.

15. The computer-readable storage device according to claim 14 , wherein the alert is generated in the case that the direction of motion for each of the pair of similar ground patch regions is substantially the same.

16. A method for deploying an object detection tool for use in a computer system that detects objects crossing a virtual boundary line, the method comprising:

providing a computer infrastructure operable to:

define a virtual boundary line in a video region of interest;

establish a set of ground patch regions surrounding the virtual boundary line;

extract a set of attributes from each of the set of ground patch regions;

update a ground patch history model with the set of attributes from each of the set of ground patch regions; and

analyze the ground patch history model to detect whether an object captured in at least one of the set of ground patch regions is crossing the virtual boundary line in the video region of interest.

17. The method according to claim 16 , the computer infrastructure further operable to generate an alert in the case that the object is detected crossing the virtual boundary line in the video region of interest.

18. The method according to claim 17 , the computer infrastructure further operable to analyze each of the set of ground patch regions to identify foreground objects within each of the set of ground patch regions.

19. The method according to claim 18 , the computer infrastructure operable to analyze the appearance model further operable to:

analyze appearance features within the ground patch history model for each of the set of ground patch regions;

determine if a pair of similar ground patch regions is present among the set of ground patch regions based on the appearance features within the ground patch history model for each of the set of ground patch regions;

determine a location of each of the pair of similar ground patch regions; and

compare a direction of motion for each of the pair of similar ground patch regions in the case that each of the pair of similar ground patch regions is located on a different side of the virtual boundary line in the video region of interest.

20. The method according to claim 19 , the computer infrastructure further operable to generate the alert in the case that the direction of motion for each of the pair of similar ground patch regions is substantially the same.