Image capture for a multi-dimensional building model

Patent metadata

Field	Value
Publication number	US-11538219-B2
Application number	US-202017012835-A
Country	US
Kind code	B2
Filing date	Sep 4, 2020
Priority date	May 29, 2015
Publication date	Dec 27, 2022
Grant date	Dec 27, 2022

Abstract

A process for creating, responsive to a desired analysis, estimate information from received imagery by determining whether the imagery meets a minimum criterion for creating a multi-dimensional model that can address the desired analysis and building an aggregate set of images meeting the minimum criterion from which a multi-dimensional model is then built and an estimate responsive to the desired analysis is derived. The multi-dimensional model, and the responsive estimate, may be refined as additional images are provided to the aggregate set. Desired analyses may include dimensions such as square footage of a roof for building objects.

First claim

What is claimed is:

1. A method of processing imagery comprising:
receiving a plurality of input camera images comprising imagery of a building object;
receiving a desired estimate analysis related to the building object within the imagery, wherein the desired estimate analysis comprises a requested dimension of the building object;
determining, for each of the received input cameras images, whether a minimum criterion is met, wherein the minimum criterion indicates applicability for constructing a multi-dimensional building model based on the desired estimate analysis;
aggregating an image set comprising each of the input camera images meeting the minimum criterion;
constructing a base multi-dimensional building model of the building object from the aggregated image set; and
returning a responsive estimate based on the constructed base multi-dimensional building model, wherein the responsive estimate comprises the requested dimension of the building object.

2. The method of claim 1 , wherein the requested dimension is a square footage estimate of a surface of the building object.

3. The method of claim 2 , wherein the square footage estimate of the surface of the building object further includes a replacement materials report comprising replacement costs of a replacement material based on the square footage estimate.

4. The method of claim 2 , wherein the surface of the building object is a roof surface.

5. The method of claim 1 , wherein the minimum criterion comprises detecting at least one specific feature.

6. The method of claim 5 , wherein the detecting the at least one specific feature comprises detecting a corner of the building object.

7. The method of claim 1 , wherein the base multi-dimensional model comprises a multi-dimensional building model constructed from a threshold number of images from the aggregated image set to derive the responsive estimate.

8. The method of claim 1 , wherein the responsive estimate comprises a calculated dimension from at least one measurement of the base multi-dimensional building model.

9. The method of claim 1 , wherein constructing the base multi-dimensional model further comprises applying a scale to the base multi-dimensional model.

10. The method of claim 9 , wherein the responsive estimate comprises a calculated dimension based on at least one scaled measurement of the base multi-dimensional building model.

11. The method of claim 9 , wherein the scale is based on geo-referenced spatial information.

12. The method of claim 9 , wherein the scale is based on architectural features of the base multi-dimensional model.

13. The method of claim 1 , further comprising updating the base multi-dimensional building model with additional ones of input cameras images exceeding a threshold number of images from the aggregated image set to derive the responsive estimate.

14. The method of claim 13 , further comprising calculating a refined responsive estimate based on at least one measurement from the updated base multi-dimensional building model.

15. A non-transitory computer readable medium storing instructions that, upon execution, cause a computing system to perform operations including:
receiving a plurality of input camera images comprising imagery of a building object;
receiving a desired estimate analysis related to the building object within the imagery, wherein the desired estimate analysis comprises a requested dimension of the building object;
determining, for each of the received input cameras images whether a minimum criterion is met, wherein the minimum criterion indicates applicability for constructing a multi-dimensional building model based on the desired estimate analysis;
aggregating an image set comprising each of the input camera images meeting the minimum criterion;
constructing a base multi-dimensional building model of the building object from the aggregated image set; and
returning a responsive estimate based on the constructed base multi-dimensional building model, wherein the responsive estimate comprises the requested dimension of the building object.

16. The non-transitory computer readable medium of claim 15 , wherein the requested dimension is a square footage estimate of a surface of the building object.

17. The non-transitory computer readable medium of claim 16 , wherein the square footage estimate of the surface of the building object further includes a replacement materials report comprising replacement costs of a replacement material based on the square footage estimate.

18. The non-transitory computer readable medium of claim 16 , wherein the surface of the building object is a roof surface.

19. The non-transitory computer readable medium of claim 15 , wherein the minimum criterion comprises detecting at least one specific feature.

20. The non-transitory computer readable medium of claim 19 , wherein the detecting the at least one specific feature comprises detecting a corner of the building object.

21. The non-transitory computer readable medium of claim 15 , wherein the base multidimensional model comprises a multi-dimensional building model constructed from a threshold number of images from the aggregated image set to derive the responsive estimate.

22. The non-transitory computer readable medium of claim 15 , wherein the responsive estimate comprises a calculated dimension from at least one measurement of the base multi-dimensional building model.

23. The non-transitory computer readable medium of claim 15 , wherein constructing the base multi-dimensional model further comprises applying a scale to the base multi-dimensional model.

24. The non-transitory computer readable medium of claim 23 , wherein the responsive estimate comprises a calculated dimension based on at least one scaled measurement of the base multidimensional building model.

25. The non-transitory computer readable medium of claim 23 , wherein the scale is based on geo-referenced spatial information.

26. The non-transitory computer readable medium of claim 23 , wherein the scale is based on architectural features of the base multi-dimensional model.

27. The non-transitory computer readable medium of claim 15 , further comprising updating the base multi-dimensional building model with additional ones of input cameras images exceeding a threshold number of images from the aggregated image set to derive the responsive estimate.

28. The non-transitory computer readable medium of claim 27 , further comprising calculating a refined responsive estimate based on at least one measurement from the updated base multi-dimensional building model.

Assignees

• Hover Inc

Inventors

• Upendran Manish
• Castillo William
• Mishra Ajay
• Altman Adam J

Classifications

• G06T7/60

  Analysis of geometric attributes · CPC title

• G06T17/00 Primary

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

• H04N23/64

  Computer-aided capture of images, e.g. transfer from script file into camera, check of taken image quality, advice or proposal for image composition or decision on when to take image · CPC title

• H04N23/63

  by using electronic viewfinders · CPC title

• G06T7/55

  from multiple images · CPC title