Statistical point pattern matching technique
AssigneeEagle View Technologies, Inc.
InventorChristopher Albert Ciarcia
Life of this patent
Estimating the term…
Abstract
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.
Claims16
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.
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.
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.
Dependencies are inferred from the claim text.