Computer implemented sensor data analysis

• US 8,331,195 B1
• Filed: 10/20/2009
• Issued: 12/11/2012
• Est. Priority Date: 10/20/2008
• Status: Active Grant

• Current Assignee: United States Secretary of the Army
• Original Assignee: The United States Of America As Represented By The Secretary Of The Army
• Inventors: Mellini, Mark, Schumer, Sean
• Primary Examiner(s): LOBO, IAN J
• Application Number:
  US12/582,071
• Time in Patent Office: 1,148 Days
• Field of Search: 367/136, 340/566
• US Class Current: 367/136
• CPC Class Codes: G01P 13/00 Indicating or recording presence, absence, or direction, of movement electric switches H01H; counting moving objects G06M7/00

Abstract

A computer implemented method, program and system utilizing a number of field-deployed sensors to accurately detect and classify objects/events (targets) of interest within a sensor field including the detection/classification of human beings travelling on-foot or with vehicles and their direction(s) of travel. In particular, the method, computer program and system are operable to determine whether a detected target is an animal, human or vehicle via analysis of received acoustic and sensor data. The analyses performed include comparison/correlation of the sensor data to known seismic cyclostationary signatures, acoustic and seismic characteristics of human footsteps and travel tendencies, and acoustic and seismic characteristics of non-human (animal) footsteps and travel tendencies.

Claims

1. A computer implemented method for detecting and classifying targets within a sensor field comprising the steps of:

detecting the presence of a target within the sensor field;

collecting data associated with the target, said data including seismic data and acoustic data;

classifying the data through the effect of a footstep classifier, a seismic cyclostationary classifier and an acoustic classifier;

determining a classification for the target based upon the footstep classification, the cyclostationary classification and the acoustic classification; and

providing an indication of the target classification to a user.

2. The method of claim 1 wherein said detecting step is performed in a low power operational mode and said collecting, classifying, determining and providing steps are performed in a high power operational mode.

3. The method of claim 2, further comprising the step of:

returning to the low power operational mode after providing the indication of the target classification to the user.

4. The method of claim 1, wherein said data collection step further includes collection of magnetic data and infrared data.

5. The method of claim 1, wherein said determining step determines whether the target is a human.

6. The method of claim 5, wherein said determining step determines whether the target is a vehicle.

7. The method of claim 6, further comprising the step of:

determining the direction of travel of the target within the sensor field.

8. The method of claim 1, further comprising:

an anti-loitering determination step wherein movement of the target within the sensor is analyzed to determine whether the targets movement is characteristic of a human or non-human.

9. A computer program recorded on a computer-readable recording medium said program causing the computer to detect and classify targets within a sensor field by executing the steps of:

detecting the presence of a target within the sensor field;

collecting data associated with the target, said data including seismic data and acoustic data;

classifying the data through the effect of a footstep classifier, a seismic cyclostationary classifier and an acoustic classifier;

determining a classification for the target based upon the footstep classification, the cyclostationary classification and the acoustic classification; and

providing an indication of the target classification to a user.

10. The computer program of claim 9, wherein said detecting step is performed in a low power operational mode and said collecting, classifying, determining and providing steps are performed in a high power operational mode.

11. The computer program of claim 10, further causing the computer to execute the steps of:

returning to the low power operational mode after providing the indication of the target classification to the user.

12. The computer program of claim 10, further causing the computer to execute the step of:

performing an anti-loitering determination analysis wherein movement of the target within the sensor is analyzed to determine whether the targets movement is characteristic of a human or non-human.

13. The computer program of claim 9, further causing the computer to execute said data collection step further including the collection of magnetic data and infrared data.

14. The computer program of claim 9, wherein said determining step determines whether the target is a human.

15. The computer program of claim 14, wherein said determining step determines whether the target is a vehicle.

16. The computer program of claim 15, further causing the computer to execute the step of:

determining the direction of travel of the target within the sensor field.

17. A system for detecting and classifying targets within a sensor field comprising:

a plurality of sensors for detecting the presence of a target within the sensor field, said sensors being positioned within the sensor field and including one or more seismic sensors and one or more acoustic sensors;

a footstep classifier for classifying seismic data generated by the one or more seismic sensors;

a seismic cyclostationary classifier for classifying seismic data generated by the one or more seismic sensors;

an acoustic classifier for classifying acoustic data generated by the one or more acoustic sensors; and

a fuser for determining a classification for the targets from the footstep classification, the seismic cyclostationary classification and the acoustic classification.

18. The system of claim 17, further comprising:

a plurality of magnetic sensors; and

a plurality of infrared sensors,

wherein said fuser determines a classification for the targets from the footstep classification, the seismic cyclostationary classification and the acoustic classification.

19. The system of claim 17, further comprising a means for providing an indication of the target classification to a user of the system.

20. The system of claim 17, further comprising means for determining whether the target is a human.

21. The system of claim 17, further comprising means for determining whether the target is a vehicle.

22. The system of claim 17, further comprising means for determining the direction of travel of the target within the sensor field.

23. The system of claim 17, further comprising an ant-loitering determination means operable to determine whether the targets movement is characteristic of a human or non-human.