Automated system and methodology for feature extraction

• US 10,796,189 B2
• Filed: 08/22/2019
• Issued: 10/06/2020
• Est. Priority Date: 02/15/2016
• Status: Active Grant

• Current Assignee: Pictometry International Corporation (Eagleview Technologies, Inc. /Wa/)
• Original Assignee: Pictometry International Corporation (Eagleview Technologies, Inc. /Wa/)
• Inventors: Wang, Yandong, Giuffrida, Frank
• Primary Examiner(s): Bayat, Ali
• Application Number:
  US16/548,219
• Publication Number:
  US 20190377966A1
• Time in Patent Office: 411 Days
• Field of Search: 382201
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06F 2218/12 Classification; Matching
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/30184 Infrastructure
• CPC Class Codes: G06T 7/50 Depth or shape recovery
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/44 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 Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G06V 10/763 Non-hierarchical techniques, e.g. based on statistics of modelling distributions
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

Automated methods and systems for feature extraction are disclosed, including automated methods performed by at least one processor running computer executable instructions stored on at least one non-transitory computer readable medium, comprising determining and isolating an object of interest within a point cloud; forming a modified point cloud having one or more data points with first location coordinates of the object of interest; and generating a boundary outline having second location coordinates of the object of interest using spectral analysis of at least one section of at least one image identified with the first location coordinates and depicting the object of interest.

Claims

1. An automated computerized system, comprising:

a computer system executing image display and analysis software reading;

at least one image having corresponding location data indicative of position and orientation of an image capturing device used to capture the image, the image depicting an object of interest; and

,

at least one database storing data points of a point cloud of the object of interest; and

wherein the image display and analysis software executed by the computer system determines and isolates the object of interest within the point cloud forming a modified point cloud having one or more data points with first location coordinates of the object of interest;

generates a boundary outline having second location coordinates of the object of interest using spectral analysis of at least one section of the at least one image identified with the first location coordinates;

identifies, catalogues, and stores characteristics of the object of interest within the at least one database; and

generates an inventory report compiling stored characteristics of the object of interest.

2. The automated computer system of claim 1, wherein the image display and analysis software determines and classifies the object of interest as a man-made structure.

3. The automated computer system of claim 1, wherein the image display and analysis software determines and classifies the object of interest as a non-man-made structure.

4. The automated computer system of claim 1, wherein the image display and analysis software spatially catalogues and stores the object of interest within the at least one database.

5. The automated computer system of claim 1, wherein at least one characteristic is color.

6. An automated method performed by at least one processor running computer executable instructions stored on at least one non-transitory computer readable medium, comprising:

determining and isolating an object of interest within a point cloud;

forming a modified point cloud having one or more data points with first location coordinates of the object of interest;

generating a boundary outline having second location coordinates of the object of interest using spectral analysis of at least one section of at least one image identified with the first location coordinates and depicting the object of interests;

identifying, cataloguing, and storing characteristics of the object of interest within at least one database; and

generating an inventory report compiling stored characteristics of the object of interest.

7. The automated method of claim 6, further comprising classifying the object of interest as a man-made structure.

8. The automated method of claim 6, further comprising classifying the object of interest as a non-man-made structure.

9. The automated method of claim 6, further comprising spatially cataloguing and storing the object of interest within at least one database.

10. The automated method of claim 6, wherein at least one characteristic is color.

11. 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:

determine and isolate an object of interest within a point cloud;

form a modified point cloud having one or more data points with first location coordinates of the object of interest;

generate a boundary outline having second location coordinates of the object of interest using spectral analysis of at least one section of at least one image identified with the first location coordinates and depicting the object of interests;

identify, catalogue, and store characteristics of the object of interest within at least one database; and

generate an inventory report compiling stored characteristics of the object of interest.

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 11, that when executed cause the one or more computer systems to determine and classify the object of interest as a man-made structure.

13. 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 11, that when executed cause the one or more computer systems to determine and classify the object of interest as a non-man-made structure.

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 11, that when executed cause the one or more computer systems to spatially catalogue and store the object of interest within at least one database.

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 11, wherein at least one characteristic is color.