Fusing Structures From Multi-Sensor Data

• US 20110172971A1
• Filed: 01/13/2010
• Published: 07/14/2011
• Est. Priority Date: 01/13/2010
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: Otts, Daniel W.
• Granted Patent: US 8,271,224 B2
• Time in Patent Office: Days
• US Class Current: 703/1
• CPC Class Codes: G06F 18/25 Fusion techniques

Abstract

In particular embodiments, fusing structures includes receiving sensor data sets generated by sensors in response to sensing a structure system. Each sensor data set describes structures of the structure system. Structure pairs are generated, where a structure pair comprises a first structure from a first sensor data set and a second structure from a second sensor data set. A relational vector set is defined for each structure pair, and a relational vector score is calculated for each structure pair according to the relational vector set of the structure pair. An association score is calculated for each structure pair according to the relational vector score of the structure pair. The association score of the structure pair indicates a likelihood that the structure pair is fusable.

Claims

1. A method comprising:

receiving a plurality of sensor data sets generated by a plurality of sensors in response to sensing one or more structure systems, a first sensor data set generated by a first sensor, a second sensor data set generated by a second sensor, each sensor data set describing a plurality of structures of the structure systems;

generating a plurality of structure pairs, a structure pair comprising a first structure from the first sensor data set and a second structure from the second sensor data set;

defining a relational vector set for each structure pair, the relational vector set comprising a plurality of vectors from a plurality of first points of the first structure to one or more second points of the second structure, each relational vector being the shortest vector from a first point to a second point;

calculating a relational vector score for each structure pair according to the relational vector set of the structure pair; and

calculating an association score for each structure pair according to the relational vector score of the structure pair, the association score of the structure pair indicating a likelihood that the structure pair is fusable.

2. The method of claim 1, further comprising:

identifying one or more structure pairs to fuse according to the association scores of the structure pairs.

3. The method of claim 8, further comprising identifying one or more structure pairs to fuse according to the association scores of the structure pairs by:

starting from higher confidence to lower confidence, selecting one or more association scores that satisfy an association score threshold; and

identifying the one or more structure pairs associated with the one or more selected association scores to fuse.

4. The method of claim 1:

further comprising;

determining a slope test score for each structure pair, the slope test score indicating a likelihood that the structure pair is fusable; and

the calculating an association score further comprising;

calculating an association score for each structure pair according the relational vector score and the slope test score of the structure pair.

5. The method of claim 1, further comprising performing a slope test for each structure pair by:

determining a first slope of the first structure of the structure pair;

determining a second slope of the second structure of the structure pair;

calculating a difference between the first slope and a second sloped; and

calculating a slope test score according to the difference, the slope test score indicating a likelihood that the structure pair is fusable.

6. The method of claim 1, the defining a relational vector set for each structure pair further comprising:

defining a plurality of equally spaced first points along the first structure; and

generating a shortest vector from each first point to a point of the second structure closest to the first point.

7. The method of claim 1, the calculating a relational vector score for each structure pair further comprising:

calculating a vector magnitude score from a plurality of magnitudes of the vectors;

calculating a vector angle score from a plurality of angles, an angle between a vector and a slope of the second structure; and

calculating the relational vector score according to the vector magnitude score and the vector angle score.

8. The method of claim 1, the calculating a relational vector score for each structure pair further comprising:

calculating a vector magnitude score from a root-sum-square of the vectors.

9. The method of claim 1, the calculating a relational vector score for each structure pair further comprising:

calculating a plurality of angles between the vectors and a slope of the second structure;

calculating an average of the plurality of angles; and

determining a vector angle score that indicates a likelihood that the structure pair is fusable according to the average.

10. The method of claim 9, the determining a vector angle score further comprising:

if the average is approximately zero or ninety degrees, determining a vector angle score that indicates a higher likelihood that the structure pair is fusable; and

otherwise, determining a vector angle score that indicates a lower likelihood that the structure pair is fusable.

11. The method of claim 1, the first structure shorter than or equal to the second structure.

12. One or more computer readable media storing logic, the logic when executed by a processor configured to:

receive a plurality of sensor data sets generated by a plurality of sensors in response to sensing one or more structure systems, a first sensor data set generated by a first sensor, a second sensor data set generated by a second sensor, each sensor data set describing a plurality of structures of the structure systems;

generate a plurality of structure pairs, a structure pair comprising a first structure from the first sensor data set and a second structure from the second sensor data set;

define a relational vector set for each structure pair, the relational vector set comprising a plurality of vectors from a plurality of first points of the first structure to one or more second points of the second structure, each relational vector being the shortest vector from a first point to a second point;

calculate a relational vector score for each structure pair according to the relational vector set of the structure pair; and

calculate an association score for each structure pair according to the relational vector score of the structure pair, the association score of the structure pair indicating a likelihood that the structure pair is fusable.

13. The computer readable media of claim 12, the logic further configured to:

identify one or more structure pairs to fuse according to the association scores of the structure pairs.

14. The computer readable media of claim 12, the logic further configured to identify one or more structure pairs to fuse according to the association scores of the structure pairs by:

starting from higher confidence to lower confidence, selecting one or more association scores that satisfy an association score threshold; and

identifying the one or more structure pairs associated with the one or more selected association scores to fuse.

15. The computer readable media of claim 12, the logic further configured to:

determine a slope test score for each structure pair, the slope test score indicating a likelihood that the structure pair is fusable; and

calculate an association score by;

calculating an association score for each structure pair according the relational vector score and the slope test score of the structure pair.

16. The computer readable media of claim 12, the logic further configured to perform a slope test for each structure pair by:

determining a first slope of the first structure of the structure pair;

determining a second slope of the second structure of the structure pair;

calculating a difference between the first slope and a second sloped; and

calculating a slope test score according to the difference, the slope test score indicating a likelihood that the structure pair is fusable.

17. The computer readable media of claim 12, the logic further configured to define a relational vector set for each structure pair by:

defining a plurality of equally spaced first points along the first structure; and

generating a shortest vector from each first point to a point of the second structure closest to the first point.

18. The computer readable media of claim 12, the logic further configured to calculate a relational vector score for each structure pair by:

calculating a vector magnitude score from a plurality of magnitudes of the vectors;

calculating a vector angle score from a plurality of angles, an angle between a vector and a slope of the second structure; and

calculating the relational vector score according to the vector magnitude score and the vector angle score.

19. The computer readable media of claim 12, the logic further configured to calculate a relational vector score for each structure pair by:

calculating a vector magnitude score from a root-sum-square of the vectors.

20. The computer readable media of claim 12, the logic further configured to calculate a relational vector score for each structure pair by:

calculating a plurality of angles between the vectors and a slope of the second structure;

calculating an average of the plurality of angles; and

determining a vector angle score that indicates a likelihood that the structure pair is fusable according to the average.

21. The computer readable media of claim 20, the logic further configured to determine a vector angle score by:

if the average is approximately zero or ninety degrees, determining a vector angle score that indicates a higher likelihood that the structure pair is fusable; and

otherwise, determining a vector angle score that indicates a lower likelihood that the structure pair is fusable.

22. The computer readable media of claim 12, the first structure shorter than or equal to the second structure.