Computer processing through distance-based quality score method in geospatial-temporal semantic graphs

1. A computer-implemented method of improving processing of overhead image data by a processor using a distance-based quality score in a geospatial-temporal semantic graph, the computer-implemented method comprising:

specifying, by the processor, a subgraph search template in the geospatial-temporal semantic graph, wherein the subgraph search template includes nodes and edges, and wherein the nodes include both a required set of nodes and an optional set of nodes;

defining, by the processor, an allowable range for each attribute in the subgraph search template;

defining, by the processor, a preferred range for each attribute in the subgraph search template;

executing, by the processor, a search of the geospatial-temporal semantic graph using the allowable range;

comparing, by the processor, for each match, attribute values of each match element against the preferred range and the allowable range to compute a corresponding distance of each match attribute from the subgraph search template;

converting, by the processor, the corresponding distance to a corresponding required quality score for each match element in the required set of nodes, wherein each corresponding required quality score comprises a corresponding first distance-based quality score;

converting, by the processor, the corresponding distance to a corresponding optional quality score for each match element in the optional set of nodes, wherein each corresponding optional quality score comprises a corresponding second distance-based quality score;

determining, by the processor, a corresponding overall match quality score for each match from the subgraph search template, wherein determining the corresponding overall match qualities is performed using the corresponding required quality score and the corresponding optional quality score;

sorting, by the processor, all corresponding overall match quality scores into an ordered list; and

displaying, on a display device, the ordered list.

2. The computer-implemented method of claim 1 wherein determining the corresponding overall match quality score is performed using an equation defined as:

q match =( w required q required )+ q required [(1− w required ) q optional ]

where W required is a user specified weighting factor that indicates a relative importance of the required set of nodes and the optional set of nodes, where q required is the corresponding required quality score, and where q optional is the corresponding optional quality score.

3. The computer-implemented method of claim 1 further comprising:

augmenting allowable constraints employed by the search by declaring preferred cardinality limits; and

using these limits to compute the required quality score and optional quality score.

4. The computer-implemented method of claim 1 further comprising:

sorting match nodes of a given type in order of decreasing quality, such that required nodes receive the highest scores, and early optional nodes receive next highest scores.

5. The computer-implemented method of claim 1 further comprising:

defining spoke ensembles in an image from which the required and optional quality scores are computed based on total area rather than by cardinality.

6. The computer-implemented method of claim 1 further comprising:

identifying, by the processor, an object of interest by selecting an object having a highest overall quality score on the ordered list.

7. The computer-implemented method of claim 1 further comprising:

rejecting, from the ordered list, match elements that have overall quality scores below a threshold.

8. The computer-implemented method of claim 1 further comprising:

using different allowable range limits to control execution of the search, where the different allowable range limits to control search are a narrower subset of the allowable limits used in calculating the quality score.

9. The computer-implemented method of claim 1 wherein a given quality score is defined by: quality=1/(1+distance).

10. The computer-implemented method of claim 1 further comprising:

estimating a quality variation range associated with each corresponding quality score.

11. A computer comprising:

a processor; and

a memory connected to the processor, the memory storing computer code which, when executed by the processor, performs a computer-implemented method of improving processing of overhead image data by a processor using a distance-based quality score in a geospatial-temporal semantic graph, the computer code comprising:

computer code for specifying, by the processor, a subgraph search template in the geospatial-temporal semantic graph, wherein the subgraph search template includes nodes and edges, and wherein the nodes include both a required set of nodes and an optional set of nodes;

computer code for defining, by the processor, an allowable range for each attribute in the subgraph search template;

computer code for defining, by the processor, a preferred range for each attribute in the subgraph search template;

computer code for executing, by the processor, a search of the geospatial-temporal semantic graph using the allowable range;

computer code for comparing, by the processor, for each match, attribute values of each match element against the preferred range and the allowable range to compute a corresponding distance of each match attribute from the subgraph search template;

computer code for converting, by the processor, the corresponding distance to a corresponding required quality score for each match element in the required set of nodes, wherein each corresponding required quality score comprises a corresponding first distance-based quality score;

computer code for converting, by the processor, the corresponding distance to a corresponding optional quality score for each match element in the optional set of nodes, wherein each corresponding optional quality score comprises a corresponding second distance-based quality score;

computer code for determining, by the processor, a corresponding overall match quality score for each match from the subgraph search template, wherein determining the corresponding overall match qualities is performed using the corresponding required quality score and the corresponding optional quality score;

computer code for sorting, by the processor, all corresponding overall quality scores into an ordered list; and

computer code for displaying, on a display device, the ordered list.

12. The computer of claim 11 wherein the code for determining the corresponding overall match quality score is executed using computer code defined an equation defined as:

q match =( w required q required )+ q required [(1− w required ) q optional ]

where W required is a user specified weighting factor that indicates a relative importance of the required set of nodes and the optional set of nodes, where g required is the corresponding required quality score, and where q optional is the corresponding optional quality score.

13. The computer of claim 11 wherein the computer code further comprises:

computer code for augmenting allowable constraints employed by the search by declaring preferred cardinality limits, and using these limits to compute the required quality score and optional quality score.

14. The computer of claim 11 wherein the computer code further comprises:

computer code for sorting match nodes of a given type in order of decreasing quality, such that required nodes receive the highest scores, and the early optional nodes receive the next highest scores.

15. The computer of claim 11 wherein the computer code further comprises:

computer code for defining spoke ensembles in an image from which the required and optional quality scores are computed based on total area rather than by cardinality.

16. A non-transitory computer recordable storage medium storing computer code which, when executed by a processor, performs a computer-implemented method of improving processing of image data by a processor using a distance-based quality score in a geospatial-temporal semantic graph, the computer code comprising:

computer code for specifying, by the processor, a subgraph search template in the geospatial-temporal semantic graph, wherein the subgraph search template includes nodes and edges, and wherein the nodes include both a required set of nodes and an optional set of nodes;

computer code for defining, by the processor, an allowable range for each attribute in the subgraph search template;

computer code for defining, by the processor, a preferred range for each attribute in the subgraph search template;

computer code for executing, by the processor, a search of the geospatial-temporal semantic graph using the allowable range;

computer code for comparing, by the processor, for each match, attribute values of each match element against the preferred range and the allowable range to compute a corresponding distance of each match attribute from the subgraph search template;

computer code for converting, by the processor, the corresponding distance to a corresponding required quality score for each match element in the required set of nodes, wherein each corresponding required quality score comprises a corresponding first distance-based quality score;

computer code for converting, by the processor, the corresponding distance to a corresponding optional quality score for each match element in the optional set of nodes, wherein each corresponding optional quality score comprises a corresponding second distance-based quality score;

computer code for determining, by the processor, a corresponding overall match quality score for each match from the subgraph search template, wherein determining the corresponding overall match qualities is performed using the corresponding required quality score and the corresponding optional quality score;

computer code for sorting, by the processor, all corresponding overall quality scores into an ordered list; and

computer code for displaying, on a display device, the ordered list.

17. The non-transitory computer recordable storage medium of claim 16 wherein the computer code for determining the corresponding overall match quality score is executed using computer code defined an equation defined as:

q match =( w required q required )+ q required [(1− w required ) q optional ]

where W required is a user specified weighting factor that indicates a relative importance of the required set of nodes and the optional set of nodes, where q required is the corresponding required quality score, and where q optional is the corresponding optional quality score.

18. The non-transitory computer recordable storage medium of claim 16 wherein the computer code further comprises:

computer code for augmenting allowable constraints employed by the search by declaring preferred cardinality limits, and using these limits to compute the required quality score and optional quality score.

19. The non-transitory computer recordable storage medium of claim 16 wherein the computer code further comprises:

computer code for sorting match nodes of a given type in order of decreasing quality, such that required nodes receive the highest scores, and early optional nodes receive next highest scores.

20. The non-transitory computer recordable storage medium of claim 16 wherein the computer code further comprises:

computer code for defining spoke ensembles in an image from which the required and optional quality scores are computed based on total area rather than by cardinality.