Generating 3D building models with ground level and orthogonal images

US9437033B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9437033-B2
Application numberUS-201414339127-A
CountryUS
Kind codeB2
Filing dateJul 23, 2014
Priority dateNov 5, 2008
Publication dateSep 6, 2016
Grant dateSep 6, 2016

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A system and method is provided for generating textured 3D building models from ground-level and orthogonal imagery. Ground-level images for the sides of building objects are collected to form a 3D dense point cloud for identification of key architectural features, corresponding key façade geometry planes, and generation of a 3D building façade geometry. Orthogonal images are correlated to the 3D building model providing a properly geo-positioned, scaled and textured 3D building model.

First claim

Opening claim text (preview).

What is claimed is: 1. A method of generating a textured 3D building model, the method comprising: collecting, using a smartphone, a plurality of captured ground-level images for a plurality of sides of a building object, the collecting including capturing and storing in computer memory of the smartphone the plurality of captured ground-level images from multiple angles and distances as a user of the smartphone circumnavigates the building object; uploading and storing the plurality of captured ground-level images from the smartphone to computer memory of a remote server; processing the plurality of ground-level images using a computer system, the processing including: creating a point cloud from the collected, uploaded and stored plurality of captured ground-level images; outlining a plurality of vertices for defining edges of a plurality of single planar surfaces; selecting a plurality of data points from the created point cloud that represent the plurality of single planar surfaces within the created point cloud; creating simplified façade geometry for each of the plurality of sides; and texturing the simplified façade geometry with one or more of the collected plurality of captured ground-level images. 2. The method of claim 1 further comprising generating the textured 3D building model using textured ones of all of the plurality of sides. 3. The method of claim 2 further comprising: retrieving an orthogonal image for the building object; correlating the vertices of the orthogonal image with at least two of the plurality of vertices for each of the single planar surfaces; and reconstructing the textured 3D building model using at least the correlated vertices. 4. The method of claim 3 , wherein the reconstructing includes at least scaling of the textured 3D building model. 5. The method of claim 3 , wherein the reconstructing includes at least rotation of the textured 3D building model. 6. The method of claim 1 , wherein the plurality of captured ground-level images are captured from a plurality of perspectives. 7. The method of claim 6 , wherein the plurality of perspectives include at least the boundaries of the plurality of sides of the building object. 8. The method of claim 6 , wherein the plurality of perspectives include at least the boundaries of the plurality of sides of the building object. 9. A method of claim 1 further comprising identifying architectural geometric features of the point cloud. 10. A method of claim 1 , wherein the selection of the plurality of data points from the point cloud that represent a plurality of single planar surfaces is performed manually or semi-automatically. 11. A method of claim 1 , wherein the plurality of data points from the point cloud comprises two or more. 12. A method of claim 1 , wherein the outlining of the plurality of vertices is performed manually or semi-automatically. 13. A system for generating a textured 3D building model, the system comprising: a smartphone capture device for capturing and storing in computer memory a plurality of ground-level images of a building object while a user of the smartphone capture device circumnavigates the building object; an orthogonal image database for loading and retrieving an orthogonal image of the building object; an image processor for constructing a textured 3D building model of the building object from the captured plurality of ground-level images of the building object and reconstructing the textured 3D building model according to the retrieved orthogonal image; and a viewer device for displaying the reconstructed textured 3D building model. 14. The system of claim 13 further comprising a communications network for transmitting the captured plurality of ground-level images of the building object. 15. The system of claim 13 wherein the orthogonal image database retrieves an orthogonal image of the building object based on location information determined by the captured plurality of ground-level images of the building object. 16. The system of claim 15 , wherein the location information is global positioning system (GPS) or a user defined location. 17. The system of claim 15 , wherein the user defined location is an address or a location on a map selected by a user. 18. A method for generating a textured 3D building model, the method comprising: capturing, using a smartphone, a plurality of ground-level images of a plurality of façades of a building object, the capturing including, creating and storing in the smartphone, a plurality of the ground-level images captured from multiple angles and distances as a user circumnavigates the building object; uploading and storing the plurality of ground-level images from the smartphone to computer memory of a remote server; creating, using computer processing, a point cloud from the plurality of ground-level images retrieved from the remote server; creating a plurality of textured façades from the created point cloud, the plurality of textured façades including all sides of the building object; correlating the textured façade with a corresponding vertical edge of a retrieved orthogonal image; and creating the textured 3D building model of the building object from the correlated textured façade and orthogonal image.

Assignees

Inventors

Classifications

  • G06T15/04Primary

    Texture mapping · CPC title

  • Assembling, disassembling · CPC title

  • involving graphical user interfaces [GUIs] · CPC title

  • Three-dimensional [3D] modelling for computer graphics · CPC title

  • Navigation within 3D models or images · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9437033B2 cover?
A system and method is provided for generating textured 3D building models from ground-level and orthogonal imagery. Ground-level images for the sides of building objects are collected to form a 3D dense point cloud for identification of key architectural features, corresponding key façade geometry planes, and generation of a 3D building façade geometry. Orthogonal images are correlated to the …
Who is the assignee on this patent?
Hover Inc, Hover Inc
What technology area does this patent fall under?
Primary CPC classification G06T15/04. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Sep 06 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 2 related publications on this page (citations in our corpus or others sharing the same primary CPC).