Determining confidence of object identification

• US 8,468,111 B1
• Filed: 11/30/2010
• Issued: 06/18/2013
• Est. Priority Date: 11/30/2010
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Tgavalekos, Nora T., Scannell, Brian J., Nelson, Kenric P., Begin, Elizabeth M., Adams, George C., Rosenthal, Samuel H., Gittler, Seanna J., Scheid, Eric, Johnson, Arthur B.
• Primary Examiner(s): VINCENT, DAVID ROBERT
• Application Number:
  US12/956,515
• Time in Patent Office: 931 Days
• Field of Search: 706/12, 706/20, 706/45, 706/62
• US Class Current: 706/45
• CPC Class Codes: G01S 13/726 Multiple target tracking
• CPC Class Codes: G01S 7/003 Transmission of data between radar, sonar or lidar systems and remote stations
• CPC Class Codes: G01S 7/411 Identification of targets based on measurements of radar reflectivity G01S7/415 takes precedence
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data

Abstract

The technology described herein includes a system and/or a method for determining confidence of object identification. The technology includes selecting at least one confidence rule from a plurality of confidence rules based on a first discrimination identification and a second discrimination identification. The technology further includes generating an object confidence weight based on one or more first identification parameters, one or more second identification parameters, and the selected at least one confidence rule. The technology further includes fusing the received set of data based on an alpha parameter, a beta parameter, and the object confidence weight. The technology further includes generating a probability of identification of a classification of the object based on the fused data.

Claims

1. A system for determining confidence of object identification, the system comprising:

a communication module configured to receive a first object identification of an object, the first object identification comprising first discrimination identification and one or more first identification parameters;

an object identification module configured to generate a second object identification of the object based on a received set of data, the second object identification comprising second discrimination identification and one or more second identification parameters;

a confidence rules module configured to select at least one confidence rule from a plurality of confidence rules based on the first discrimination identification and the second discrimination identification;

an object confidence module configured to generate an object confidence weight based on the one or more first identification parameters, the one or more second identification parameters, and the selected at least one confidence rule;

a data fusion module configured to fuse the received set of data based on an alpha parameter, a beta parameter, and the object confidence weight, the alpha parameter associated with a fusion function and the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object; and

a probability of identification module configured to generate a probability of identification of the classification of the object based on the fused data.

2. The system of claim 1, further comprising the data fusion module further configured to fuse the received set of data based on a second alpha parameter, a second beta parameter, the object confidence weight, the probability of identification, and the first object identification, the second alpha parameter associated with a fusion function and the second beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with the classification of the object.

3. The system of claim 1, further comprising the object identification module further configured to generate an object identification based on the first discrimination identification, the second discrimination identification, and the probability of identification.

4. The system of claim 1, further comprising the confidence rules module further configured to generate the plurality of confidence rules based on the first object identification, the second object identification, one or more pre-defined relationships between the first object identification and the second object identification, or any combination thereof.

5. The system of claim 1, further comprising a confidence rules storage module configured to store the plurality of confidence rules.

6. The system of claim 5, wherein the plurality of confidence rules are pre-defined.

7. The system of claim 5, wherein the plurality of confidence rules are modifiable.

8. The system of claim 1, wherein the one or more identification parameters for each of the object identifications is indicative of a characteristic of an object associated with the first object identification, the second object identification, or any combination thereof.

9. The system of claim 8, wherein the characteristics of the object comprises a physical characteristic of the object.

10. The system of claim 1, wherein the object confidence weight is indicative of the discrimination identification for each of the object identification accurately identifying an object associated with the first object identification, the second object identification, or any combination thereof.

11. A method for determining confidence of object identification, the method comprising:

receiving a first object identification of an object, the first object identification comprising first discrimination identification and one or more first identification parameters;

generating a second object identification of the object based on a received set of data, the second object identification comprising second discrimination identification and one or more second identification parameters;

selecting at least one confidence rule from a plurality of confidence rules based on the first discrimination identification and the second discrimination identification;

generating an object confidence weight based on the one or more first identification parameters, the one or more second identification parameters, and the selected at least one confidence rule;

fusing the received set of data based on an alpha parameter, a beta parameter, and the object confidence weight, the alpha parameter associated with a fusion function and the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object; and

generating a probability of identification of the classification of the object based on the fused data.

12. The method of claim 11, further comprising fusing the received set of data based on a second alpha parameter, a second beta parameter, the object confidence weight, the probability of identification, and the first object identification, the second alpha parameter associated with a fusion function and the second beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with the classification of the object.

13. The method of claim 11, further comprising generating an object identification based on the one or more first identification parameters, the one or more second identification parameters, and the selected at least one confidence rule.

14. The method of claim 11, further comprising generating the plurality of confidence rules based on the first object identification, the second object identification, one or more pre-defined relationships between the first object identification and the second object identification, or any combination thereof.

15. The method of claim 11, further comprising:

generating the first object identification based on a first discrimination function; and

generating the second object identification based on a second discrimination function.

16. The method of claim 11, wherein the object confidence weight is indicative of the discrimination identification for each of the object identification accurately identifying an object associated with the first object identification and the second object identification.

17. A computer program product, tangibly embodied in an information carrier, the computer program product including instructions being operable to cause a data processing apparatus to:

receive a first object identification of an object, the first object identification comprising first discrimination identification and one or more first identification parameters;

generate a second object identification of the object based on a received set of data, the second object identification comprising second discrimination identification and one or more second identification parameters;

select at least one confidence rule from a plurality of confidence rules based on the first discrimination identification and the second discrimination identification;

generate an object confidence weight based on the one or more first identification parameters, the one or more second identification parameters, and the selected at least one confidence rule;

fuse the received set of data based on an alpha parameter, a beta parameter, and the object confidence weight, the alpha parameter associated with a fusion function and the beta parameter associated with a degree of expected independence of a received set of data and the received set of data comprising information associated with a classification of the object; and

generate a probability of identification of the classification of the object based on the fused data.