Dynamic process for identifying objects in multi-dimensional data

• US 20040022414A1
• Filed: 03/07/2003
• Published: 02/05/2004
• Est. Priority Date: 10/22/1999
• Status: Active Grant

• Current Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Original Assignee: Lockheed Martin Corporation (Martin Marietta Corporation)
• Inventors: Phillips, Ronald William
• Granted Patent: US 6,850,627 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes

Abstract

A method for identifying a detected object in multi-dimensional imagery data is disclosed. The method includes, (a) providing (1) a set of comparative feature values associated with one or more known objects in one or more specified observation conditions and (2) a set of observation-related values including (i) a set of feature values for one or more features of an object as observed in an environment, (ii) a set of condition values for one or more conditions of the observation, including one or more of an orientation value, a depression value, a resolution value, and an obscuration value; and (b) generating one or more identification values for the object by comparing the set of feature values to the set of comparative feature values, including compensating for the set of condition values.

Claims

1. A method for identifying an object in observation-related data of an object in a surrounding environment comprising:

(a) providing (1) a set of comparative feature values associated with one or more known objects in one or more specified observation conditions and (2) a set of observation-related values including (i) a set of feature values for one or more features of an object as observed in an environment, (ii) a set of condition values for one or more conditions of the observation, including one or more of an orientation value, a depression value, a resolution value, and an obscuration value; and

(b) generating one or more identification values for the object by comparing the set of feature values to the set of comparative feature values, including compensating for the set of condition values.

2. The method of claim 1, wherein compensating for the set of condition values includes modifying at least one feature value to an expected value to compensate for the obscuration value.

3. The method of claim 1, wherein the set of comparative feature values includes one or more feature membership functions and the compensation modifies one or more of the membership functions.

4. The method of claim 1, wherein the compensation correlates the comparative feature values to the set of condition values.

5. The method of claim 1, wherein the compensation modifies the set of feature values to a set of expected feature values.

6. The method of claim 5, wherein the expected feature values comprise a range of values.

7. The method of claim 1, wherein generating one or more identification values further includes establishing a confidence in the accuracy of one or more of the feature values in view of one or more of the condition values and weighting the importance of the comparison based on the confidence.

8. The method of claim 3 wherein generating one or more identification values includes executing a fuzzy logic process that utilizes one or more membership functions.

9. The method of claim 1, wherein the observation-related data includes three dimensional LADAR pixel data.

20. A program storage device encoded with computer readable instructions for performing the operations recited in a specified one of claims 1 through 19.

10. A method for identifying an object in multi-dimensional imagery data comprising:

(a) providing multi-dimensional imagery data, including (1) a feature value of an object, (2) a condition value, (3) a feature membership function for a potential identification; and

(b) comparing the feature value to the feature membership function to identify the object, including compensating for the condition value by modifying either or both the feature value and feature membership function.

11. The method of claim 10, wherein the compensation includes establishing comparative feature values in view of one or more condition values and modifying the feature membership function based on these comparative feature values.

12. The method of claim 10, wherein the compensation includes establishing a confidence in the accuracy of the feature value in view of one or more condition values and weighting the importance of the comparison based on the confidence.

13. The method of claim 10, wherein the compensation includes executing a fuzzy logic process utilizing the modified feature membership function.

14. The method of claim 10, wherein the multi-dimensional imagery data includes three dimensional LADAR pixel data.

15. A method for identifying an object in multi-dimensional imagery data comprising:

(a) Providing multi-dimensional imagery data, including (1) a feature value of an object, (2) a condition value, (3) feature membership parameters for a potential identification; and

(b) Comparing the feature value to the feature membership function to identify the object, including selecting the feature membership parameters based on the condition value.

16. The method of claim 15, wherein comparing the feature value to the feature membership function to identify the object further includes weighting the importance of the comparison based on the condition value.

17. The method of claim 15, wherein comparing the feature value to the feature membership function to identify the object further includes executing a fuzzy logic process utilizing the feature membership parameters.

18. The method of claim 15, wherein the multi-dimensional imagery data includes three dimensional LADAR pixel data.

19. A method employing fuzzy logic for identifying an object in LADAR data, the method comprising:

(a) providing (1) a feature value of the object, (2) a condition value including one or more of object orientation value, depression value, resolution value, and obscuration value, and (3) a membership function for a corresponding feature of a potential identification;

(b) comparing the feature value to the membership function using a fuzzy logic process including a rulebase, the comparison including;

(1) weighting at least one rule in the rulebase according to the condition value;

(2) modifying the membership function responsive to the condition value;

(c) executing the fuzzy logic process to obtain an indication of whether the object corresponds to the potential identification; and

(d) identifying the object.