Fusing Multi-Sensor Data Sets According To Relative Geometrical Relationships

• US 20110172962A1
• 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 8,290,741 B2
• Time in Patent Office: Days
• US Class Current: 702/181
• CPC Class Codes: G06F 18/253 of extracted features

Abstract

In particular embodiments, fusing multi-sensor data sets includes receiving a first sensor data set and a second sensor data set generated in response to sensing a structure. The sensor data sets describe structural features of the structure. First delta vector sets are generated for the first sensor data set, and second delta vector sets are generated for the second sensor data set. Each delta vector set comprises delta vectors indicating relative geometrical relationships between a structural feature and other structural features. Association scores are determined for delta pairs comprising a first delta vector set and a second delta vector set. Same feature delta pairs are identified according to the association scores. A same feature delta vector set comprises a delta pair corresponding to the same structural feature.

Claims

1. A method comprising:

receiving a first sensor data set and a second sensor data set generated in response to sensing one or more structures, the sensor data sets describing a plurality of structural features of the structures;

generating a plurality of first delta vector sets for the first sensor data set and a plurality of second delta vector sets for the second sensor data set, each delta vector set comprising one or more delta vectors for a structural feature, a delta vector indicating one or more relative geometrical relationships between the structural feature and one or more other structural features of the each sensor data set; and

determining a plurality of association scores for a plurality of delta pairs, a delta pair comprising a first delta vector set and a second delta vector set; and

identifying a plurality of same feature delta pairs according to the association scores, a same feature delta vector set comprising a delta pair corresponding to the same structural feature.

2. The method of claim 1, further comprising:

assigning one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs.

3. The method of claim 1, the determining the plurality of association scores further comprising performing the following for one or more iterations:

determining an association score for each delta pair; and

identifying a plurality of candidate pairs for an iteration according to the association scores, a candidate pair indicating a most likely mapping of a first feature to a second feature for the iteration.

4. The method of claim 1, the determining the plurality of association scores further comprising performing the following for one or more iterations:

identifying a plurality of candidate pairs for an iteration according to the association scores, a candidate pair indicating a mapping of a first feature to a second feature for the iteration; and

rotating the first delta vector sets with respect to the second delta vector sets.

5. The method of claim 1, the determining the plurality of association scores further comprising:

determining a plurality of candidate vector pair combinations, a candidate vector pair combination mapping one or more first features to one or more second features; and

determining a plurality of candidate scores for the candidate vector pair combinations, a candidate score for a pair indicating a likelihood that the candidate vector pair combination correctly maps the first features to the second features.

6. The method of claim 1:

the determining the plurality of association scores further comprising;

determining a plurality of candidate scores for a plurality of candidate vector pair combinations from the association scores, a candidate score indicating a likelihood that a candidate vector pair combination correctly maps the first features to the second features; and

the identifying the plurality of same feature delta pairs further comprising;

identifying the same feature delta pairs according to the candidate scores.

7. The method of claim 1, the determining the plurality of association scores further comprising performing the following for one or more iterations:

determining an association score for each delta pair;

identifying a plurality of candidate delta pairs according to the association scores; and

applying a function to the association scores of the candidate delta pairs to calculate a candidate score.

8. The method of claim 1, each sensor data set indicating a location of each feature of the each sensor data set.

9. The method of claim 1, further comprising:

assigning one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs;

fusing the features of the first sensor data set assigned to the features of the second sensor data set; and

generating a layout of the one or more structures from the fused features.

10. An apparatus comprising:

a memory configured to store a first sensor data set and a second sensor data set generated in response to sensing one or more structures, the sensor data sets describing a plurality of structural features of the structures;

one or more processors coupled to the memory and configured to;

generate a plurality of first delta vector sets for the first sensor data set and a plurality of second delta vector sets for the second sensor data set, each delta vector set comprising one or more delta vectors for a structural feature, a delta vector indicating one or more relative geometrical relationships between the structural feature and one or more other structural features of the each sensor data set;

determine a plurality of association scores for a plurality of delta pairs, a delta pair comprising a first delta vector set and a second delta vector set;

identify a plurality of same feature delta pairs according to the association scores, a same feature delta vector set comprising a delta pair corresponding to the same structural feature; and

assign one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs.

11. The apparatus of claim 10, the processors configured to:

assign one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs.

12. The apparatus of claim 10, the processors configured to determine the plurality of association scores by performing the following for one or more iterations:

determining an association score for each delta pair; and

identifying a plurality of candidate pairs for an iteration according to the association scores, a candidate pair indicating a most likely mapping of a first feature to a second feature for the iteration.

13. The apparatus of claim 10, the processors configured to determine the plurality of association scores by performing the following for one or more iterations:

identifying a plurality of candidate pairs for an iteration according to the association scores, a candidate pair indicating a mapping of a first feature to a second feature for the iteration; and

rotating the first delta vector sets with respect to the second delta vector sets.

14. The apparatus of claim 10, the processors configured to determine the plurality of association scores by:

determining a plurality of candidate vector pair combinations, a candidate vector pair combination mapping one or more first features to one or more second features; and

determining a plurality of candidate scores for the candidate vector pair combinations, a candidate score for a pair indicating a likelihood that the candidate vector pair combination correctly maps the first features to the second features.

15. The apparatus of claim 10, the processors configured to:

determine the plurality of association scores by;

determining a plurality of candidate scores for a plurality of candidate vector pair combinations from the association scores, a candidate score indicating a likelihood that a candidate vector pair combination correctly maps the first features to the second features; and

identify the plurality of same feature delta pairs by;

identifying the same feature delta pairs according to the candidate scores.

16. The apparatus of claim 10, the processors configured to determine the plurality of association scores by performing the following for one or more iterations:

determining an association score for each delta pair;

identifying a plurality of candidate delta pairs according to the association scores; and

applying a function to the association scores of the candidate delta pairs to calculate a candidate score.

17. The apparatus of claim 10, each sensor data set indicating a location of each feature of the each sensor data set.

18. The apparatus of claim 10, the processors configured to:

assign one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs;

fuse the features of the first sensor data set assigned to the features of the second sensor data set; and

generate a layout of the one or more structures from the fused features.

19. One or more computer readable storage media storing logic executable by a processor, the logic configured to:

store a first sensor data set and a second sensor data set generated in response to sensing one or more structures, the sensor data sets describing a plurality of structural features of the structures;

generate a plurality of first delta vector sets for the first sensor data set and a plurality of second delta vector sets for the second sensor data set, each delta vector set comprising one or more delta vectors for a structural feature, a delta vector indicating one or more relative geometrical relationships between the structural feature and one or more other structural features of the each sensor data set;

determine a plurality of association scores for a plurality of delta pairs, a delta pair comprising a first delta vector set and a second delta vector set;

identify a plurality of same feature delta pairs according to the association scores, a same feature delta vector set comprising a delta pair corresponding to the same structural feature; and

assign one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs.

20. The media of claim 19, the logic configured to:

assign one or more first features of the first sensor data set to one or more second features of the second sensor data set according to the same feature delta pairs.