Automated system and methodology for feature extraction

Patent metadata

Field	Value
Publication number	US-10402676-B2
Application number	US-201715428860-A
Country	US
Kind code	B2
Filing date	Feb 9, 2017
Priority date	Feb 15, 2016
Publication date	Sep 3, 2019
Grant date	Sep 3, 2019

Abstract

An automated method performed by at least one processor running computer executable instructions stored on at least one non-transitory computer readable medium, comprising: classifying first data points identifying at least one man-made roof structure within a point cloud and classifying second data points associated with at least one of natural structures and ground surface to form a modified point cloud; identifying at least one feature of the man-made roof structure in the modified point cloud; and generating a roof report including the at least one feature.

First claim

What is claimed is:

1. One or more non-transitory computer readable medium storing a set of computer executable instructions for running on one or more computer systems that when executed cause the one or more computer systems to:
classify at least one feature within an image as a man-made structure, wherein the man-made structure is a building having a roof, wherein classification of the feature as a man-made structure includes:
analyzing data points within a point cloud indicative of a man-made structure, a natural structure, and a ground structure to automatically classify certain of the data points within the point cloud representing the man-made structure as the man-made structure;
determining first information about the man-made structure by analyzing the data points classified as the man-made structure;
correlating the data points within the point cloud classified as the man-made structure with one or more images;

spectrally analyze image raster content of at least one section of the one or more images correlated with the data points within the point cloud that are classified as the man-made structure to generate second information in which the second information is an update of the first information; and
determine an estimated roof pitch by analyzing the one or more images.

2. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 1 , wherein the first information is a boundary of the building.

3. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 1 , wherein the second information is a boundary of the building.

4. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 1 , further comprising generating a roof report including one image showing the roof and the estimated roof pitch.

5. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 1 , wherein classification of man-made structures includes determination of shape of a grouping of data points.

6. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 5 , wherein determination of shape of the grouping of data points includes analyzing the grouping of data points to determine a variation of surface normal direction between data points.

7. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer system of claim 1 , further comprising spatially cataloguing location of data points associated with the image.

8. One or more non-transitory computer readable medium storing a set of computer executable instructions for running on one or more computer systems that when executed cause the one or more computer systems to:
classify at least one feature within an image as a man-made structure, wherein classification of the feature as a man-made structure includes:
analyzing data points within a point cloud indicative of a man-made structure, a natural structure, and a ground structure to automatically classify certain of the data points within the point cloud representing the man-made structure as the man-made structure, wherein the data points having a Z value above a first elevation are classified as at least one of the man-made structure and the natural structure;
determining first information about the man-made structure by analyzing the data points classified as the man-made structure, wherein the first information includes an outline of the man-made structure;
correlating the data points within the point cloud classified as the man-made structure with one or more images; and

spectrally analyze image raster content of at least one section of the one or more images correlated with the data points within the point cloud that are classified as the man-made structure to generate second information in which the second information is an update of the first information.

9. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 8 , wherein the outline is a first outline, and wherein the second information is a second outline of the man-made structure based upon the first outline.

10. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer system of claim 8 , wherein the man-made structure is a building having a roof.

11. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 10 , further comprising determining an estimated roof pitch by analyzing data points within the point cloud.

12. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 10 , further comprising determining an estimated roof pitch by analyzing the one or more images.

13. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer system of claim 10 , further comprising generating a roof report including one image showing the roof and an estimated roof pitch.

14. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 8 , wherein to classify at least one feature within the image as a man-made structure includes determination of shape of a grouping of data points.

15. The one or more non-transitory computer readable medium storing the set of computer executable instructions for running on one or more computer systems of claim 14 , wherein determination of shape of the grouping of data points includes analyzing the grouping of data points to determine a variation of surface normal direction between data points.

16. One or more non-transitory computer readable medium storing a set of computer executable instructions for running on one or more computer system that when executed cause the one or more computer systems to:
classify at least one feature within an image as a man-made structure, wherein classification of the feature as a man-made structure includes:
analyzing data points within a point cloud indicative of a man-made structure, a natural structure, and a ground structure to automatically classify certain of the data points within the point cloud representing the man-made structure as the man-made structure;
determining first information about the man-made structure by analyzing the data points classified as the man-made structure;
correlating the data points within the point cloud classified as the man-made structure with one or more images; and

spectrally analyze image raster content of at least one section of the one or more images correlated with the data points within the point cloud that are classified as the man-made structure, including grouping of data points based on one or more similar characteristics, to generate second information in which the second information is an update of the first information.

17. The one or more non-transitory computer reada

Assignees

• Pictometry Int Corp

Inventors

• Wang Yandong
• Giuffrida Frank

Classifications

• G06V10/763

  Non-hierarchical techniques, e.g. based on statistics of modelling distributions · CPC title

• G06F2218/12

  Classification; Matching · CPC title

• G06V20/64 Primary

  Three-dimensional [3D] objects · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06F18/2321

  using statistics or function optimisation, e.g. modelling of probability density functions · CPC title