Statistical point pattern matching technique
View Patent ↗A statistical point pattern matching technique is used to match corresponding points selected from two or more views of a roof of a building. The technique statistically selecting points from each of orthogonal and oblique aerial views of a roof. generating radial point patterns for each aerial view, calculating the origin of each point pattern, representing the shape of the point pattern as a radial function, and Fourier-transforming the radial function to produce a feature space plot. A feature profile correlation function can then be computed to relate the point match sets. From the correlation results, a vote occupancy table can be generated to help evaluate the variance of the point match sets, indicating, with high probability, which sets of points are most likely to match one another.
1. A microprocessor-based method in a point pattern matching computation machine, the method comprising:
obtaining orthogonal and oblique views of a structure, the views being in the form of digital images;
selecting representative points from each view for point matching;
performing a statistical method of point pattern matching to associate similar ones of the representative points from different views;
deriving height data from the points by performing a transform; and
generating a three-dimensional model from the points and the height data.
2. The microprocessor-based method of claim 1 wherein the statistical method of point pattern matching includes variational analysis to determine a probability that each one of a pair of matched points represents substantially the same location on the structure.
3. A microprocessor-based statistical method of point pattern matching, the method comprising:
generating radial point patterns for each image;
calculating an origin for each point pattern as a centroid of selected points;
generating angular variational data from each point pattern;
performing a Fourier transform of the angular variational data;
calculating a feature space correlation function relating Fourier transforms that correspond to the point patterns;
generating a vote occupancy table;
determining a point match probability based on statistics of the occupancy table; and
outputting a point match based on the determined point match probability.
4. A microprocessor-based statistical method of point pattern matching, the method comprising:
receiving a plurality of images, the images representing different views of a structure;
for each image of the plurality of images:
selecting a plurality of points on the image, the plurality of points relating to features of the structure depicted on the image,
generating a radial point pattern,
calculating an origin for each point pattern,
generating angular variational data from each point pattern, and
performing a transform of the angular variational data;
calculating a feature space correlation function relating the transforms that correspond to the point patterns for each of the images;
generating a vote occupancy table;
determining a point match probability based on statistics of the occupancy table; and
outputting the point match probability.
5. The method of claim 4 , wherein the transform is one of a Fourier or Fast-Fourier transform.
6. The method of claim 4 , wherein the origin for each point pattern is a centroid of the selected points.
7. The method of claim 4 , wherein the selecting of a plurality of points on the image in done in part by human intervention.
8. The method of claim 4 , wherein the structure is a roof of building.
9. The method of claim 8 , wherein the selected plurality of points relating to features of the structure depicted on the image include points at where roof lines of the structure converge.
10. The method of claim 4 , wherein the vote occupancy table includes rows sorted in order of the correlation probabilities.
11. The method of claim 4 , wherein the plurality of images includes at least one orthogonal and one oblique view of the structure.
12. The method of claim 4 , wherein the structure is the exterior of a building.
13. The method of claim 12 , wherein the selected plurality of points relating to features of the structure depicted on the image include points where the exterior edges of the structure converge.
14. The method of claim 12 , wherein the selected plurality of points relating to features of the structure depicted on the image include points identifying edges of external windows of the structure.
15. The method of claim 12 , wherein the selected plurality of points relating to features of the structure depicted on the image include points identifying edges of external doors of the structure.
16. The method of claim 12 , wherein the selected plurality of points relating to features of the structure depicted on the image include points identifying edges of balconies of the structure.