Systems and methods for situational feature set selection for target classification

• US 7,714,714 B2
• Filed: 11/07/2006
• Issued: 05/11/2010
• Est. Priority Date: 11/07/2006
• Status: Active Grant

• Current Assignee: Ollnova Technologies Limited (Atlantic IP Services Limited)
• Original Assignee: Harris Corporation (L3Harris Technologies, Inc.)
• Inventors: Jordan, Michael D., Cloutier, Scott J., Voglewede, Paul Edward
• Primary Examiner(s): Mehmood; Jennifer
• Application Number:
  US11/593,835
• Publication Number:
  US 20080106402A1
• Time in Patent Office: 1,281 Days
• Field of Search: 340/500, 340/501, 340/539.1, 340/539.11, 340/539.26, 340/690, 702/14, 702/15, 702/17, 702/16, 702/18
• US Class Current: 340/539.26
• CPC Class Codes: H04Q 9/00 Arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station, in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom

Abstract

Certain embodiments of the present invention provide a system for improved signal processing within a remote sensor system. The system includes a detection component and a classification component. The detection component is adapted to detect an event. The classification component is adapted to classify the event based at least in part on a situation. Certain embodiments of the present invention provide a method for improved signal processing within a remote sensor system. The system includes determining a situation, detecting an event, and classifying the event based at least in part on a situation.

Claims

1. A system for improved signal processing within a remote sensor system, the system including:

a selection component configured to select a situation from a plurality of selectable situations;

a detection component configured to detect an event; and

a classification component configured to;

select at least one feature set from a plurality of selectable feature sets based at least in part on the selected situation, wherein the at least one feature set indicates at least one measurement type, and

classify the detected event based at least in part on the selected feature set, wherein the classification of the detected event provides a decision value indicating whether the classified detected event is related to the selected situation.

2. The system of claim 1, wherein the detection component includes at least one of a seismic detector, an acoustic detector, a magnetic detector, and a passive infra-red detector.

3. The system of claim 1, wherein the situation includes at least one of a target type, an environment, and a dynamic environmental condition.

4. The system of claim 1, wherein the situation is selected by a user.

5. The system of claim 1, wherein the situation is selected automatically by the selection component.

6. The system of claim 1, wherein the detection component is configured to generate a signal based at least in part on the detected event.

7. The system of claim 6, further including an analysis component configured to analyze the signal based at least in part on the selected at least one feature set.

8. The system of claim 6, further including an analysis component configured to analyze the signal in a plurality of domains.

9. The system of claim 6, further including a processing component configured to determine an envelope of the signal and an analysis component configured to analyze the envelope of the signal in a plurality of domains.

10. The system of claim 1, wherein the detection component is configured to generate a plurality of signals based at least in part on the detected event.

11. The system of claim 10, wherein the classification component is configured to classify the event based at least in part on the plurality of signals.

12. A method for improved signal processing within a remote sensor system, the system including:

using at least one computing device to perform the steps of;

selecting a situation from a plurality of selectable situations;

detecting an event;

selecting at least one feature set from a plurality of selectable feature sets based at least in part on the selected situation, wherein the at least one feature set indicates at least one measurement type; and

classifying the event based at least in part on the selected at least one feature set, wherein classification provides a decision value indicating whether the classified event is related to the selected situation.

13. The method of claim 12, further including generating a signal based at least in part on the event and analyzing the signal based at least in part on the selected at least one feature set.

14. The method of claim 12, further including generating a signal based at least in part on the event and analyzing the signal in a plurality of domains.

15. The method of claim 12, further including generating a signal based at least in part on the event, processing the signal to determine an envelope of the signal, and analyzing the envelope of the signal in a plurality of domains.

16. The method of claim 12, further including generating a plurality of signals based at least in part on the event and classifying the event based at least in part on the plurality of signals.

17. A computer readable storage medium including a set of instructions for execution on a computer, the set of instructions including:

a situation selection routine configured to select a situation from a plurality of selectable situations;

a detection routine configured to detect an event;

a feature set selection routine configured to select at least one feature set from a plurality of selectable feature sets based at least in part on the selected situation, wherein the at least one feature set indicates at least one measurement type; and

a classification routine configured to classify the event based at least in part on the selected at least one feature set, wherein the classification routine provides a decision value indicating whether the classified event is related to the selected situation.

18. The set of instructions of claim 17, wherein the detection routine is configured to generate a signal.

19. The set of instructions of claim 18, further including an analysis routine configured to analyze the signal based at least in part on the selected at least one feature set.

20. The set of instructions of claim 18, further including an analysis routine configured to analyze the signal in a plurality of domains.

21. The set of instructions of claim 18, further including a processing routine configured to determine an envelope of the signal and an analysis routine configured to analyze the envelope of the signal in a plurality of domains.

22. The set of instructions of claim 18, wherein the detection routine is configured to generate a plurality of signals and wherein the classification routine is configured to classify the event based at least in part on the plurality of signals.