Systems and methods for pitch determination

Patent metadata

Field	Value
Publication number	US-11847739-B2
Application number	US-202117445939-A
Country	US
Kind code	B2
Filing date	Aug 25, 2021
Priority date	Aug 26, 2020
Publication date	Dec 19, 2023
Grant date	Dec 19, 2023

Abstract

Systems and methods are provided for pitch determination. An example method includes obtaining an image depicting a structure, the image being captured via a user device positioned proximate to the structure. The image is segmented to identify, at least, a roof facet of the structure. An eave vector and a rake vector which are associated with the roof facet are determined. A normal vector of the roof facet is calculated based on the eave vector and the rake vector, and compared to a vector indicating a vertical direction such as gravity. The angle made out by the normal and a gravity vector may be utilized to calculate the pitch of the roof facet.

First claim

What is claimed is:

1. A method implemented by a system of one or more computers, the method comprising:
obtaining an image depicting a structure, the image being captured via a user device positioned proximate to the structure, the structure having a plurality of planar elements;
providing the image as input to a neural network, wherein a forward pass through the neural network is computed, and wherein the neural network outputs, at least, a surface normal associated with a roof facet depicted in the image, and wherein the neural network is trained to output a surface normal associated with at least one of the plurality of planar elements of the structure; and
adjusting the surface normal associated with the roof facet based on the surface normal associated with the at least one of the plurality of planar elements being transformed to have substantially zero elevation.

2. The method of claim 1 , wherein the neural network comprises a convolutional neural network trained to assign at least one of the planar elements as the roof facet.

3. The method of claim 2 , wherein the neural network further comprises one or more fully-connected layers which receive output from the convolutional neural network, and wherein the fully-connected layers are trained to output individual surface normals associated with individual planar elements.

4. The method of claim 1 , wherein the neural network is trained to determine individual surface normals for individual planar elements of the structure, and wherein the a roof facet is identified from the plurality of planar elements.

5. The method of claim 1 , further comprising determining a plurality of surface normals corresponding to a plurality of roof facets.

6. The method of claim 1 , wherein the image was captured below a height of the structure.

7. The method of claim 1 , wherein a pitch of the roof facet is determined based on the adjusted surface normal associated with the roof facet and a gravity vector.

8. A system comprising one or more processors and non-transitory computer-readable media storing instructions which, when executed by the one or more processors, cause the one or more processors to:
obtain an image depicting a structure, the image being captured via a user device positioned proximate to the structure, the structure having a plurality of planar elements;
provide the image as input to a neural network, wherein a forward pass through the neural network is computed, and wherein the neural network outputs, at least, a surface normal associated with a roof facet depicted in the image, and wherein the neural network is trained to output a surface normal associated with at least one of the plurality of planar elements of the structure; and
adjust an orientation of the surface normal associated with the roof facet based on the surface normal associated with the at least one of the plurality of planar elements being transformed to have substantially zero elevation.

9. The system of claim 8 , wherein the neural network comprises a convolutional neural network trained to assign at least one of the planar elements as the roof facet, wherein the neural network further comprises one or more fully-connected layers which receive output from the convolutional neural network, and wherein the fully-connected layers are trained to output individual surface normals associated with individual planar elements.

10. The system of claim 8 , wherein the neural network is trained to determine individual surface normals for individual planar elements of the structure, and wherein the instructions further cause the one or more processors to identify the roof facet from the plurality of planar elements.

11. The system of claim 8 , wherein the instructions further cause the one or more processors to determine a plurality of surface normals corresponding to a plurality of roof facets.

12. The system of claim 8 , wherein the image was captured below a height of the structure.

13. The system of claim 8 , wherein a pitch of the roof facet is determined based on the adjusted surface normal and a gravity vector.

14. Non-transitory computer storage media storing instructions that when executed by a system of one or more processors cause the one or more processors to:
obtain an image depicting a structure, the image being captured via a user device positioned proximate to the structure, the structure having a plurality of planar elements;
provide the image as input to a neural network, wherein a forward pass through the neural network is computed, and wherein the neural network outputs, at least, a surface normal associated with a roof facet depicted in the image, and wherein the neural network is trained to output a surface normal associated with at least one of the plurality of planar elements of the structure; and
adjust an orientation of the surface normal associated with the roof facet based on the surface normal associated with the at least one of the plurality of planar elements being transformed to have substantially zero elevation.

15. The computer storage media of claim 14 , wherein the neural network comprises a convolutional neural network trained to assign at least one of the planar elements as the roof facet.

16. The computer storage media of claim 15 , wherein the neural network further comprises one or more fully-connected layers which receive output from the convolutional neural network, and wherein the fully-connected layers are trained to output individual surface normals associated with individual planar elements.

17. The computer storage media of claim 14 , wherein the neural network is trained to determine surface normal for a plurality of planar elements of the structure, and wherein the instructions further cause the one or more processors to identify the roof facet from the plurality of planar elements.

18. The computer storage media of claim 14 , wherein the instructions further cause the one or more processors to determine a plurality of surface normals corresponding to a plurality of roof facets.

19. The computer storage media of claim 14 , wherein the image was captured below a height of the structure.

20. The computer storage media of claim 14 , wherein a pitch of the roof facet is determined based on the surface normal and a gravity vector.

Assignees

• Hover Inc

Inventors

• Castillo William
• Murali Giridhar
• Scott Brandon
• Jia Kai
• Sommers Jeffrey
• Rethage Dario

Classifications

• G06T17/00 Primary

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

• G06N3/08

  Learning methods · CPC title

• G06T7/10

  Segmentation; Edge detection (motion-based segmentation G06T7/215) · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title