IP Library Granted Patent US 11,670,046
Granted Patent B2
US 11,670,046 · App. 17/583,546 · Granted Jun 6, 2023

3D building analyzer

Inventors: Derek Halliday (Oakland, CA); Antonio Carlos Marques da Silva Junior (Concord, CA); Roberto Klein (Oakland, CA); Adam J. Altman (San Francisco, CA)
Assignee: Hover Inc.
G06T17/00G06F3/14G06F30/13G06F30/23G06T15/04G06T15/20G06T17/05G06T19/003G06T19/20G06V20/176G06V20/653G06T2200/08G06T2200/24G06T2207/10028G06T2210/04G06T2210/56G06T2219/004G06T2219/2008G06T2219/2016
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,670,046
App. No.
17/583,546
Granted
Jun 6, 2023
Kind
B2
Abstract

The scale of modeled building objects from collected imagery is determined by identifying architectural elements within building object imagery, determining a scale of the identified architectural elements by matching them to known industry standard architectural element based on dimensional ratio comparisons and deriving an average scaling factor based on scale of the identified architectural elements. A three dimensional model of the building object is scaled according to the average scaling. Scaled architecture elements within a relative error can be used for scaling the model according to an updated scale factor.

Claims (30)

1. A method of scaling a multi-dimensional building model, the method comprising:

receiving the multi-dimensional building model, wherein the multi-dimensional building model is constructed based on building object imagery;

extracting a dimensional ratio for a plurality of architectural elements within the building object imagery;

averaging the dimensional ratios associated with the plurality of architectural elements;

assigning a scale of the plurality of architectural elements by matching the average dimensional ratio to an externally referenced known industry standard architectural element based on a closest dimensional ratio; and

scaling the multi-dimensional building model based on the scale.

2. The method of claim 1 , wherein the plurality of architectural elements are within a planar surface of the building object imagery.

3. The method of claim 1 , wherein matching based on the closest dimensional ratio further comprises matching within a threshold.

4. The method of claim 3 , wherein the threshold is less than five percent of a dimensional ratio of the externally referenced known industry standard architectural element.

5. The method of claim 3 , wherein the threshold is less than one percent of a dimensional ratio of the externally referenced known industry standard architectural element.

6. The method of claim 1 , wherein matching the average dimensional ratio to the externally referenced known industry standard architectural element further comprises:

comparing the average dimensional ratio to a plurality of dimensional ratios of externally referenced known industry standard architectural elements;

selecting a dimensional ratio that is closest to a dimensional ratio of the plurality of dimensional ratios of the externally referenced known industry standard elements.

7. The method of claim 1 , wherein the scale is assigned based on a relative error of the average dimensional ratio to a dimensional ratio of the externally referenced known industry standard architectural element.

8. The method of claim 7 , wherein scaling the multi-dimensional building model is further based on the relative error.

9. One or more non-transitory computer readable medium storing instructions that, when executed, cause a processor to execute operations comprising:

receiving the multi-dimensional building model, wherein the multi-dimensional building model is constructed based on building object imagery;

extracting a dimensional ratio for a plurality of architectural elements within the building object imagery;

averaging the dimensional ratios associated with the plurality of architectural elements;

assigning a scale of the plurality of architectural elements by matching the average dimensional ratio to an externally referenced known industry standard architectural element based on a closest dimensional ratio; and

scaling the multi-dimensional building model based on the scale.

10. The one or more non-transitory computer readable medium of claim 9 , wherein the plurality of architectural elements are within a planar surface of the building object imagery.

11. The one or more non-transitory computer readable medium of claim 9 , wherein matching based on the closest dimensional ratio further comprises matching within a threshold.

12. The one or more non-transitory computer readable medium of claim 11 , wherein the threshold is less than five percent of a dimensional ratio of the externally referenced known industry standard architectural element.

13. The one or more non-transitory computer readable medium of claim 11 , wherein the threshold is less than one percent of a dimensional ratio of the externally referenced known industry standard architectural element.

14. The one or more non-transitory computer readable medium of claim 9 , wherein matching the average dimensional ratio to the externally referenced known industry standard architectural element further comprises:

comparing the average dimensional ratio to a plurality of dimensional ratios of externally referenced known industry standard architectural elements;

selecting a dimensional ratio that is closest to a dimensional ratio of the plurality of dimensional ratios of the externally referenced known industry standard elements.

15. The one or more non-transitory computer readable medium of claim 9 , wherein the scale is assigned based on a relative error of the average dimensional ratio to a dimensional ratio of the externally referenced known industry standard architectural element.

16. The method of claim 15 , wherein scaling the multi-dimensional building model is further based on the relative error.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 31, 2022
From: HALLIDAY, DEREK; MARQUES DA SILVA JUNIOR, ANTONIO CARLOS; KLEIN, ROBERTO; ALTMAN, ADAM J.
To: HOVER INC.
Reel/Frame 058830/0486 →
Continuity (7)
Continuation 17127994 · Dec 18, 2020
Continuation 16998564 · Aug 20, 2020
Continuation 15411226 · Jan 20, 2017
Continuation In Part 15255807 · Sep 2, 2016
Continuation 14339127 · Jul 23, 2014
Provisional Application 61857302 · Jul 23, 2013
Related Publication 20220147662A1 · May 12, 2022
Cited By (1)
US 12,657,826