Video surveillance system with trajectory hypothesis scoring based on at least one non-spatial parameter

• US 20050104959A1
• Filed: 08/12/2004
• Published: 05/19/2005
• Est. Priority Date: 11/17/2003
• Status: Abandoned Application

• Current Assignee: Vidient Systems, Inc. (Agilence Incorporated)
• Original Assignee: Vidient Systems, Inc. (Agilence Incorporated)
• Inventors: Gong, Yihong, Han, Mei, Tao, Hai
• Application Number:
  US10/916,966
• Publication Number:
  US 20050104959A1
• Time in Patent Office: Days
• US Class Current: 348/143
• CPC Class Codes: G08B 13/19604 involving reference image or background adaptation with time to compensate for changing conditions, e.g. reference image update on detection of light level change
• CPC Class Codes: G08B 13/19608 Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
• CPC Class Codes: G08B 13/19615 wherein said pattern is defined by the user
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm

Abstract

A video surveillance system uses rule-based reasoning and multiple-hypothesis scoring to detect predefined behaviors based on movement through zone patterns. Trajectory hypothesis spawning allows for trajectory splitting and/or merging and includes local pruning to managed hypothesis growth. Hypotheses are scored based on a number of criteria, illustratively including at least one non-spatial parameter. Connection probabilities computed during the hypothesis spawning process are based on a number of criteria, illustratively including object size. Object detection and probability scoring is illustratively based on object class.

Claims

1. A method for use in a video surveillance system, the method comprising

generating a plurality of hypotheses, each hypothesis comprising a respective different set of hypothesized trajectories of objects hypothesized to have been moving through an area under surveillance at a particular time, and

computing for least ones of said hypotheses an associated likelihood, said likelihood being a measure of the probability that the associated hypothesis represents the actual trajectories of the actual objects moving through the area under surveillance at said particular time,

said likelihood being a function of at least one parameter that is other than a parameter indicative of a spatial relationship between the positions of objects along the trajectories of the associated hypothesis.

2. The method of claim 1 wherein said at least one parameter is a function of the probability that the hypothesized objects are in a particular class of objects distinguishable based on their appearance.

3. The method of claim 2 wherein said class of objects is people.

4. The method of claim 1 wherein said at least one parameter is a function of the relative smoothness of the trajectories of said associated hypothesis.

5. The method of claim 1 wherein said at least one parameter is a function of a measure of the similarity in appearance, at at least two different points in time, of an object hypothesized to be on a particular trajectory.

6. The method of claim 5 wherein said similarity in appearance is a function of histogram distributions of said each hypothesized object and said object that had previously terminated terminates said particular trajectory.

7. The method of claim 1 wherein said at least one parameter is a function of a measure of the size, at at least two different points in time, of an object hypothesized to be on a particular trajectory.

8. The method of claim 1 wherein said at least one parameter is independent of any characteristic of the trajectories of said hypothesis.

9. The method of claim 1 wherein the generating generates said plurality of hypotheses from at least one video image of said area under surveillance and wherein said parameter is a function of a relationship between a) regions of said image that appear to represent moving objects and b) regions of said image that have been identified, based on their appearance, as being objects belonging to a particular class of objects.

10. The method of claim 1 wherein said parameter is a function of a foreground hypothesis coverage of said hypothesis.

11. The method of claim 10 wherein said foreground hypothesis coverage is a measure of the extent to which regions of said image that appear to represent moving objects are covered by regions of said image corresponding to the terminating objects of the trajectories in said hypothesis.

12. The method of claim 9 wherein said parameter is a function of a measure of the compactness of said hypothesis.

13. The method of claim 12 wherein said compactness is a measure of the overlapping areas between regions of the image corresponding to the terminating objects of the trajectories in said hypothesis.

14. The method of claim 1 wherein said each connection probability is a further function of spatial relationships between the positions of objects along the trajectories of the associated hypothesis.

15. An electronic surveillance system adapted to carry out the method defined by claim 1.

16. A tangible medium on which are stored instructions that are executable by a processor to carry out the method defined by claim 1.