Method and system for geometry extraction, 3D visualization and analysis using arbitrary oblique imagery

• US 8,422,825 B1
• Filed: 11/05/2008
• Issued: 04/16/2013
• Est. Priority Date: 11/05/2008
• Status: Active Grant

• Current Assignee: Hover Inc. (Tucows Incorporated)
• Original Assignee: Hover Inc. (Tucows Incorporated)
• Inventors: Neophytou, Neophytos, Herbert, Marc L., Pittel, James L.
• Primary Examiner(s): ZARKA, DAVID PETER
• Application Number:
  US12/265,656
• Time in Patent Office: 1,623 Days
• Field of Search: 382/294
• US Class Current: 382/294
• CPC Class Codes: G06F 3/14 Digital output to display device ; Cooperation and interconnection of the display device with other functional units
• CPC Class Codes: G06T 15/04 Texture mapping
• CPC Class Codes: G06T 15/20 Perspective computation
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 17/05 Geographic models
• CPC Class Codes: G06T 19/003 Navigation within 3D models or images
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2210/04 Architectural design, interior design
• CPC Class Codes: G06T 2210/56 Particle system, point based geometry or rendering
• CPC Class Codes: G06T 2219/2008 Assembling, disassembling
• CPC Class Codes: G06V 20/176 Urban or other man-made structures
• CPC Class Codes: G06V 20/653 by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces

Abstract

Embodiments of the invention relate to the visualization of geographical information and the combination of image information to generate geographical information. Specifically, embodiments of the invention relate to a process and system for correlating oblique images data and terrain data without extrinsic information about the oblique imagery. Embodiments include a visualization tool to allow simultaneous and coordinated viewing of the correlated imagery. The visualization tool may also provide distance and measuring, three-dimensional lens, structure identification, path finding, visibility and similar tools to allow a user to determine distance between imaged objects.

Claims

1. A method of operation of a computer system comprising:

receiving a set of tie points for a first image captured by a camera;

iterating through sets of camera parameters for the first image;

calculating a least squares fit value for each of the sets of camera parameters;

selecting a set of camera parameters from the sets with a least error in the least squares fit value;

calculating two-dimensional coordinates for the pixel of the first image based on an overlapping area of an orthorectified image; and

calculating a geo-location for a pixel of the first image using the selected set of camera parameters for constructing a three-dimensional image on a display;

wherein the fist image is an oblique image.

2. The method of claim 1, further comprising:

calculating three-dimensional coordinates for the pixel of the first image based on the two-dimensional coordinates and the set of camera parameters.

3. The method of claim 1, further comprising:

adjusting a tie point automatically to a nearest corner.

4. The method of claim 1, further comprising:

reverse-projecting a terrain model corresponding to the first image by a graphics processor unit.

5. The method of claim 1, further comprising:

texture-mapping a portion of the first image onto an orthogonal image that is draped over a three-dimensional terrain model.

6. The method of claim 1, further comprising:

matching a pattern identified in the first image in one other image by transforming the pattern to the image space of the one other image and comparing a texture of the pattern with the one other image.

7. The method of claim 1, further comprising:

identifying a set of walls for a structure in the first image based on an identified rooftop.

8. The method of claim 1, further comprising:

providing rooftop identification tools including line drawing, circle drawing and rectangle drawing.

9. A non-transitory computer-readable medium having a set of instructions stored therein which when executed cause a machine to perform a set of operations comprising:

receiving a set of tie points for a first image;

iterating through sets of camera parameters for the first image;

calculating a least squares fit value for each of the sets plurality of camera parameters;

selecting a set of camera parameters from the sets with a least error in the least squares fit value; and

calculating two-dimensional coordinates for the pixel of the first image based on an overlapping area of an orthorectified image;

calculating a geo-location for a pixel of the first image using the selected set of camera parameters;

wherein the first image is an oblique image.

10. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

calculating three-dimensional coordinates for the pixel of the first image based on the two-dimensional coordinates and the set of camera parameters.

11. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

adjusting a tie point automatically to a nearest corner.

12. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

reverse-projecting a terrain model corresponding to the first image by a graphics processor unit.

13. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

texture-mapping a portion of the first image onto an orthogonal image that is draped over a three-dimensional terrain model.

14. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

matching a pattern identified in the first image in one other image by transforming the pattern to the image space of the one other image and comparing a texture of the pattern with the one other image.

15. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

identifying a set of walls for a structure in the first image based on an identified rooftop.

16. The machine readable medium of claim 9, having further instructions stored therein, which when executed cause the machine to perform the set of operations further comprising:

providing rooftop identification tools including line drawing, circle drawing and rectangle drawing.

17. A non-transitory storage system including software modules, comprising:

a visualization tool implemented on the non-transitory storage system for receiving a set of tie points for a first image, the first image being an oblique image;

a camera solver component implemented on the non-transitory storage system for;

iterating through a plurality of camera parameters for the first image,

calculating a least squares fit value for each of the plurality of camera parameters, and

selecting a set of camera parameters with a least error in the least squares fit value; and

pixel mapping component implemented on the non-transitory storage system for;

calculating a geo-location for a pixel of the first image using the set of camera parameters, and

calculating two-dimensional coordinates for the pixel of the first image based on an overlapping area of an orthorectified image.

18. A geocoding and visualization apparatus for constructing a 3D map on a display device from camera captured images, comprising:

means for receiving a set of tie points for a first image, the first image being an oblique image;

means for iterating through a plurality of camera parameters for the first image;

means for calculating a least squares fit value for each of the plurality of camera parameters;

means for selecting a set of camera parameters with a least error in the least squares fit value;

means for calculating a geo-location for a pixel of the first image using the set of camera parameters; and

means for calculating two-dimensional coordinates for the pixel of the first image based on an overlapping area of an orthorectified image.