STANDOFF DETECTION SYSTEMS AND METHODS

• US 20070286460A1
• Filed: 06/07/2007
• Published: 12/13/2007
• Est. Priority Date: 06/08/2006
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Doretto, Gianfranco, Sebastian, Thomas Baby, Ashe, Jeffrey Michael, Tu, Peter Henry, Thomenius, Kai Erik, Krahnstoever, Nils Oliver, Rittscher, Jens, Hill, John Charles
• Granted Patent: US 7,885,429 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• 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: G06V 2201/05 Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs

Abstract

Embodiments of the invention include a system and a method for determining whether a person is carrying concealed contraband, such as an improvised explosives device or other weapon. The system includes a people tracking video subsystem, a people tracking decisioning subsystem, a concealed contraband detection aiming subsystem, and a concealed contraband detection decisioning subsystem.

Claims

1. A system for detecting concealed contraband at a distance, comprising:

a people tracking video subsystem for creating video of one or more persons;

a people tracking decisioning subsystem for segmenting a targeted person from the one or more persons;

a concealed contraband detection aiming subsystem for obtaining greater information regarding the targeted person; and

a concealed contraband detection decisioning subsystem for ascertaining whether the targeted person has a concealed weapon.

2. The system of claim 1, wherein said people tracking video subsystem comprises a network of video cameras, each transmitting video to said people tracking decisioning subsystem.

3. The system of claim 2, wherein said video cameras comprise digital video cameras.

4. The system of claim 2, wherein said people tracking decisioning subsystem comprises a calibrator for calibrating each of the video cameras in three-dimensional space, wherein a three-dimensional location of the targeted person can be ascertained.

5. The system of claim 1, wherein said people tracking decisioning subsystem comprises a crowd segmenter for segmenting individuals out of a crowd of people.

6. The system of claim 1, wherein said people tracking decisioning subsystem comprises a tracker for tracking the targeted person.

7. The system of claim 1, wherein said concealed contraband detection aiming subsystem comprises a network of imagers, said network of imagers including at least two modalities of imaging.

8. The system of claim 7, wherein said network of imagers comprises a millimeter wave imager and at least one of a video camera and a thermal imager.

9. The system of claim 1, wherein said concealed contraband detection aiming subsystem comprises a network of non-imaging detectors.

10. The system of claim 9, wherein said network of non-imaging detectors comprises a plurality of passive detectors.

11. The system of claim 10, wherein said plurality of passive detectors comprise at least two modalities from the group consisting of passive millimeter wave single and low pixel-count radiometer detectors and passive terahertz radiometer detectors.

12. The system of claim 9, wherein said network of non-imaging detectors comprises a plurality of active detectors.

13. The system of claim 12, wherein said plurality of active detectors comprise at least two modalities from the group consisting of active radars, active millimeter wave radiometer detectors, active terahertz radiometer detectors, and lasers.

14. The system of claim 1, wherein said concealed contraband detection decisioning subsystem comprises a model fitter for creating articulated images of body parts of the targeted person.

15. The system of claim 14, wherein said concealed contraband detection decisioning subsystem comprises a concealed contraband detector for creating feature vectors extracted from imagery associated with the targeted person.

16. The system of claim 15, wherein said concealed contraband detection decisioning subsystem comprises a threat analyzer for classifying the feature vectors as being a concealed weapon of as not being a concealed weapon.

17. A method for detecting concealed contraband at a distance, comprising:

tracking a person of interest;

obtaining a first set of data about the person of interest through video surveillance;

obtaining a second set of data about the person of interest through surveillance of the person of interest with at least another modality;

fusing said first set of data with said second set of data to form feature vectors; and

passing the feature vectors through a threat analyzer to ascertain whether the person of interest is carrying concealed contraband.

18. The method of claim 17, wherein said tracking a person of interest comprises tracking the person of interest with at least one video camera.

19. The method of claim 18, wherein said obtaining a first set of data comprises obtaining at least a three-dimensional location of the person of interest.

20. The method of claim 19, wherein the three-dimensional location of the person of interest is obtained through calibrating the at least one video camera.

21. The method of claim 17, wherein said obtaining a second set of data comprises obtaining the second set of data through imaging surveillance of the person of interest.

22. The method of claim 21, wherein said imaging surveillance comprises surveillance of the person of interest with at least one from the group consisting of video cameras, terahertz imagers, thermal imagers, and millimeter wave imagers.

23. The method of claim 17, wherein said obtaining a second set of data comprises obtaining the second set of data through non-imaging detectors.

24. The method of claim 23, wherein said non-imaging detectors comprise at least one passive detector.

25. The method of claim 24, wherein said at least one passive detector comprises a passive millimeter wave single or low pixel-count radiometer detector and a passive terahertz radiometer detector.

26. The method of claim 23, wherein said non-imaging detectors comprise at least one active detector.

27. The method of claim 26, wherein said at least one active detector comprises an active millimeter wave detector, an active terahertz detector, and a laser.

28. The method of claim 17, wherein said fusing comprises fusing body part segmentation images of the person of interest with three-dimensional location data of the person of interest to obtain information on the three-dimensional location of various body parts of the person of interest.