# US 2014/0212026 A1 · Statistical point pattern matching technique

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2014/0212026 A1
- Document ID: US20140212026A1
- Status: Published application
- Kind: A1
- Application number: 13/844,572
- Filed: 2013-03-15
- Published: 2014-07-31
- Earliest claimed: 2013-01-31
- Assignees: Eagle View Technologies, Inc.
- Inventors: Christopher Albert Ciarcia
- Web page: https://patentgrep.com/patent/US20140212026A1

## CPC

- G06T 17/05: Geographic models
- G06T 7/55: from multiple images
- G06V 10/46: Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features (colour feature extraction G06V10/56)
- G06V 10/757: {Matching configurations of points or features}
- G06T 2200/08: involving all processing steps from image acquisition to 3D model generation
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/20076: Probabilistic image processing
- G06T 2207/30184: Infrastructure
- G06V 10/476: {using statistical shape modelling, e.g. point distribution models}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## 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.

## Claims

### Claim 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.

### Claim 2 (depends on 1)

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.

### Claim 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; and
determining a point match probability based on statistics of the occupancy table.
