System and method for automatic person counting and detection of specific events

• US 20070003141A1
• Filed: 11/30/2005
• Published: 01/04/2007
• Est. Priority Date: 06/30/2005
• Status: Active Grant

• Current Assignee: GE Security Incorporated (Carrier Global Corporation)
• Original Assignee: GE Security Incorporated (Carrier Global Corporation)
• Inventors: Liu, Xiaoming, Rittscher, Jens, Sebastian, Thomas, Perera, Amitha, Krahnstoever, Nils, Tu, Peter
• Granted Patent: US 7,596,241 B2
• Time in Patent Office: Days
• US Class Current: 382/181
• CPC Class Codes: G06V 20/53 Recognition of crowd images, e.g. recognition of crowd congestion

Abstract

A system for detecting and counting individuals in a stationary or moving crowd based on a digital or digitized image captured from a single camera. Initial information is assumed based on a foot-to-head plane homology, where a geometric construct is developed to best enclose image features with a high probability of being an individual within a crowd. These geometric constructs are then subjected to further probabilistic analysis to determine individuals. The vector track of each individual is determined to validate the determination of a group of features as individuals, thereby compensating for occlusion of an individual within any given frame image. A virtual gate is then employed to count the individuals moving past the virtual gate. Also, by weighting portions of the individual, events near the gate can be predicted.

Claims

1. a system for segmenting a crowd into individual objects comprising:

an image capturing system;

a computing system connected to the image capturing system, wherein the computing system utilizes a foot-to-head plane technique to segment the crowd.

2. The system of claim 1, wherein the image capturing system comprises an analog image capturing device and an analog to digital converter.

3. The system of claim 1, wherein the image capturing system comprises a digital video camera.

4. The system of claim 1, wherein the image capturing system comprises a single image capturing device.

5. The system of claim 1, wherein the crowd comprises people.

6. The system of claim 1, wherein the computing system is configured to differentiate between the crowd and background image information.

7. The system of claim 1, wherein the computing system is configured to calibrate automatically.

8. The system of claim 1, wherein the computing system is configured to insert a virtual gate in the image.

9. A method for counting at least one individual in a crowd comprising the steps of:

(i) calibrating an image capturing device and an image processing device;

(ii) capturing a frame of an image with the image capturing device;

(iii) drawing a virtual gate through the image;

(iv) applying a foreground estimation module to the image;

(v) applying a tracking module to the image;

(vi) applying a crowd segmentation module to the image to separate the individual from the crowd; and

(vii) counting the individual.

10. The method of claim 9, wherein the calibration of step (i) utilizes foot-to-head plane homology.

11. The method of claim 9, wherein the crowd segmentation module in step (v) comprises the steps of

(i) identifying at least one low level image feature;

(ii) hypothesizing at least one clique from the low level image features; and

(iii) constraining the clique according to a geometric shape model.

12. The method of claim 11 wherein the constraining of step (iii) comprises

(iv) assigning each low level image feature to a single clique;

(v) establishing future assignments according to an assignment vector based on a likelihood function.

13. The method of claim 12, wherein the likelihood function is a free energy equation.

14. The method of claim 9, wherein the tracking module comprises applying the Hungarian algorithm.

15. The method of claim 9, wherein the tracking module and the segmentation module are integrated.

16. The method of claim 9, wherein the individual comprises a person.

17. A method for detecting an event comprising the steps of:

(i) calibrating an image capturing device and an image processing device;

(ii) capturing a frame of an image with the image capturing device;

(iii) drawing a boundary of a zone of interest in the image;

(iv) applying a foreground estimation module to the image;

(v) applying a crowd segmentation module to the image to separate the individual from the crowd;

(vii) identifying a point on the individual; and

(viii) determining the location of the point with respect to the boundary.

18. The method of claim 17, further comprising the steps of

(ix) drawing a line through the point;

and

(x) determining if any portion of the individual to one side of the line is within the zone of interest

19. The method of claim 18, wherein the individual comprises a person.

20. The method of claim 19, wherein the zone of interest comprises a restricted area.