Foreground Analysis Based on Tracking Information

• US 20120027248A1
• Filed: 07/27/2010
• Published: 02/02/2012
• Est. Priority Date: 07/27/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Feris, Rogerio S., Hampapur, Arun, Kjeldsen, Frederik C., Liu, Hao-Wei
• Granted Patent: US 8,483,481 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 11/20 Drawing from basic elements, e.g. lines or circles
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

Techniques for performing foreground analysis are provided. The techniques include identifying a region of interest in a video scene, applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest, and determining whether the static foreground object is abandoned or removed, wherein determining whether the static foreground object is abandoned or removed comprises performing a foreground analysis based on edge energy and region growing, and pruning one or more false alarms using one or more track statistics.

Claims

1. A method for performing foreground analysis, wherein the method comprises:

identifying a region of interest in a video scene;

applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest; and

determining whether the static foreground object is abandoned or removed, wherein determining whether the static foreground object is abandoned or removed comprises;

performing a foreground analysis based on edge energy and region growing; and

pruning one or more false alarms using one or more track statistics.

2. The method of claim 1, wherein identifying a region of interest in a video scene comprises enabling a user to manually draw a region of interest in a video scene.

3. The method of claim 1, wherein pruning one or more false alarms using one or more track statistics comprises using information from an object tracking algorithm.

4. The method of claim 1, further comprising determining whether a static foreground object determined to be abandoned meets user-defined criteria.

5. The method of claim 4, further comprising triggering an alarm if the static foreground object determined to be abandoned meets the user-defined criteria.

6. The method of claim 1, further comprising verifying the detection of a static foreground object determined to be abandoned using a tracker.

7. The method of claim 6, wherein using a tracker to verify the detection of a static foreground object determined to be abandoned comprises:

using the tracker to track each of one or more moving objects in the region of interest to produce one or more corresponding trajectories; and

querying the tracker with the static foreground object determined to be abandoned to retrieve one or more trajectories associated therewith.

8. The method of claim 7, further comprising using the tracker to determine if the static foreground object determined to be abandoned entered from outside the region of interest and travelled within a pre-determined range of speed.

9. The method of claim 8, further comprising using v to represent speed of the object computed from its trajectory over a period of W frames up to a current frame, and using bCross as a Boolean variable indicating whether the trajectory intersects a boundary of the region of interest, wherein an alarm is triggered if bCross=true and v≧

SpeedThr, a user defined threshold, and wherein the object is rejected as a candidate otherwise.

10. The method of claim 1, further comprising providing a system, wherein the system comprises one or more distinct software modules, each of the one or more distinct software modules being embodied on a tangible computer-readable recordable storage medium, and wherein the one or more distinct software modules comprise a background subtraction module and a static region detection module executing on a hardware processor.

11. A computer program product comprising a tangible computer readable recordable storage medium including computer useable program code for performing foreground analysis, the computer program product including:

computer useable program code for identifying a region of interest in a video scene;

computer useable program code for applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest; and

computer useable program code for determining whether the static foreground object is abandoned or removed, wherein the computer useable program code for determining whether the static foreground object is abandoned or removed comprises;

computer useable program code for performing a foreground analysis based on edge energy and region growing; and

computer useable program code for pruning one or more false alarms using one or more track statistics.

12. The computer program product of claim 11, wherein the computer useable program code for identifying a region of interest in a video scene comprises computer useable program code for enabling a user to manually draw a region of interest in a video scene.

13. The computer program product of claim 11, wherein the computer useable program code for pruning one or more false alarms using one or more track statistics comprises computer useable program code for using information from an object tracking algorithm.

14. The computer program product of claim 11, further comprising computer useable program code for verifying the detection of a static foreground object determined to be abandoned using a tracker.

15. The computer program product of claim 14, wherein the computer useable program code for using a tracker to verify the detection of a static foreground object determined to be abandoned comprises:

computer useable program code for using the tracker to track each of one or more moving objects in the region of interest to produce one or more corresponding trajectories; and

computer useable program code for querying the tracker with the static foreground object determined to be abandoned to retrieve one or more trajectories associated therewith.

16. The computer program product of claim 15, further comprising computer useable program code for using the tracker to determine if the static foreground object determined to be abandoned entered from outside the region of interest and travelled within a pre-determined range of speed.

17. The computer program product of claim 16, further comprising computer useable program code for using v to represent speed of the object computed from its trajectory over a period of W frames up to a current frame, and using bCross as a Boolean variable indicating whether the trajectory intersects a boundary of the region of interest, wherein an alarm is triggered if bCross=true and v≧

SpeedThr, a user defined threshold, and wherein the object is rejected as a candidate otherwise.

18. A system for performing foreground analysis, comprising:

a memory; and

at least one processor coupled to the memory and operative to;

identify a region of interest in a video scene;

apply a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest; and

determine whether the static foreground object is abandoned or removed, wherein the at least one processor coupled to the memory and operative to determine whether the static foreground object is abandoned or removed is further operative to;

perform a foreground analysis based on edge energy and region growing; and

prune one or more false alarms using one or more track statistics.

19. The system of claim 18, wherein the at least one processor coupled to the memory operative to identify a region of interest in a video scene is further operative to enable a user to manually draw a region of interest in a video scene.

20. The system of claim 18, wherein the at least one processor coupled to the memory operative to prune one or more false alarms using one or more track statistics is further operative to use information from an object tracking algorithm.

21. The system of claim 18, wherein the at least one processor coupled to the memory is further operative to verify the detection of a static foreground object determined to be abandoned using a tracker.

22. The system of claim 21, wherein the at least one processor coupled to the memory operative to use a tracker to verify the detection of a static foreground object determined to be abandoned is further operative to:

use the tracker to track each of one or more moving objects in the region of interest to produce one or more corresponding trajectories; and

query the tracker with the static foreground object determined to be abandoned to retrieve one or more trajectories associated therewith.

23. The system of claim 22, wherein the at least one processor coupled to the memory is further operative to use the tracker to determine if the static foreground object determined to be abandoned entered from outside the region of interest and travelled within a pre-determined range of speed.

24. The system of claim 23, wherein the at least one processor coupled to the memory is further operative to use v to represent speed of the object computed from its trajectory over a period of W frames up to a current frame, and using bCross as a Boolean variable to indicating whether the trajectory intersects a boundary of the region of interest, wherein an alarm is triggered if bCross=true and v≧

SpeedThr, a user defined threshold, and wherein the object is rejected as a candidate otherwise.

25. An apparatus for performing foreground analysis, the apparatus comprising:

means for identifying a region of interest in a video scene;

means for applying a background subtraction algorithm to the region of interest to detect a static foreground object in the region of interest; and

means for determining whether the static foreground object is abandoned or removed, wherein the means determining whether the static foreground object is abandoned or removed comprises;

means for performing a foreground analysis based on edge energy and region growing; and

means for pruning one or more false alarms using one or more track statistics.