Video-based encroachment detection

• US 20060093187A1
• Filed: 10/06/2005
• Published: 05/04/2006
• Est. Priority Date: 10/12/2004
• Status: Active Grant

• Current Assignee: Siemens Medical Solutions USA Incorporated (Siemens AG)
• Original Assignee: Siemens Corp. (Siemens AG)
• Inventors: Ramesh, Visvanathan, Mittal, Anurag, Zoghlami, Imad
• Granted Patent: US 7,593,547 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 7/254 involving subtraction of images
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Abstract

A method and system for video-based encroachment detection are provided, the method including receiving first and second images, modeling a background from the first image, subtracting the background from the second image to provide a detection map, calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map using dynamic programming, and detecting the object in a region if the projection matches that region of the detection map; and the system including a processor, a background modeling unit coupled with the processor for modeling a background from the first image and subtracting the background from the second image to provide a detection map, and a dynamic programming unit coupled with the processor for calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map, and detecting the object in a region if the projection matches that region of the detection map.

Claims

1. A method for video-based encroachment detection comprising:

receiving first and second images;

modeling a background from the first image;

subtracting the background from the second image to provide a detection map;

calibrating the size of an object at different parts of the image from the pixel level;

integrating a projection of the object with the detection map using dynamic programming; and

detecting the object in a region if the projection matches that region of the detection map.

2. A method as defined in claim 1 wherein the size of the object comprises a specified range and the region corresponds to a prohibited area.

3. A method as defined in claim 1, further comprising:

determining whether a base of the object is grounded in the region; and

signaling an alarm if the base of the object is grounded in the region.

4. A method as defined in claim 1, further comprising determining if there is a new object at a given pixel in the image.

5. A method as defined in claim 1, further comprising integrating pixel-wise detections from the detection map using dynamic programming.

6. A method as defined in claim 1, further comprising processing an integration map to determine the base position of an object.

7. A method as defined in claim 1, further comprising eliminating false base positions that arise due to partial occlusions by using detections that are determined to be reliable.

8. A method as defined in claim 7 wherein the first detection starting from the bottom is determined to be reliable.

9. A method as defined in claim 1, further comprising distinguishing between detections of objects that simply occlude an area versus detection of objects that have their base in the area.

10. A method as defined in claim 1, further comprising performing temporal reasoning to determine if an object remains in a forbidden zone or region for a specified period of time.

11. A method as defined in claim 1, further comprising performing temporal reasoning to determine if an object becomes stationary in a forbidden zone or region.

12. A method as defined in claim 1 wherein calibrating the size of an object from the pixel level is a simple object size calibration rather than a full calibration.

13. A system for video-based encroachment detection between first and second images comprising:

a processor;

a background modeling unit in signal communication with the processor for modeling a background from the first image and subtracting the background from the second image to provide a detection map; and

a dynamic programming unit in signal communication with the processor for calibrating the size of an object from the pixel level, integrating a projection of the object with the detection map, and detecting the object in a region if the projection matches that region of the detection map.

14. A system as defined in claim 13, further comprising at least one of an imaging adapter and a communications adapter in signal communication with the processor for receiving image data.

15. A system as defined in claim 13, further comprising:

base means in signal communication with the processor for determining whether a base of the object is grounded in the region; and

an alarm in signal communication with the base means for signaling if the base of the object is grounded in the region.

16. A system as defined in claim 13, further comprising:

reliability means in signal communication with the processor for determining that the first detection starting from the bottom is reliable; and

occlusion means in signal communication with the reliability means for excluding false base positions that arise due to partial occlusions by using detections that are determined to be reliable.

17. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform program steps for video-based encroachment detection between first and second images, the program steps comprising:

receiving first and second images;

modeling a background from the first image;

subtracting the background from the second image to provide a detection map;

calibrating the size of an object from the pixel level;

integrating a projection of the object with the detection map using dynamic programming; and

detecting the object in a region if the projection matches that region of the detection map.

18. A program storage device as defined in claim 17, the program steps further comprising:

determining whether a base of the object is grounded in the region; and

signaling an alarm if the base of the object is grounded in the region.

19. A program storage device as defined in claim 17, the program steps further comprising eliminating false base positions that arise due to partial occlusions by using detections that are determined to be reliable as being the first detection starting from the bottom.

20. A program storage device as defined in claim 17, the program steps further comprising at least one of:

performing temporal reasoning to determine if an object remains in a forbidden zone or region for a specified period of time;

or

performing temporal reasoning to determine if an object becomes stationary in a forbidden zone or region.