Systems and methods for pitch determination

Patent metadata

Field	Value
Publication number	US-2025166300-A1
Application number	US-202519030528-A
Country	US
Kind code	A1
Filing date	Jan 17, 2025
Priority date	Aug 26, 2020
Publication date	May 22, 2025
Grant date	—

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

1 . (canceled)

2 . A method of implemented by a system of one or more computers, the method comprising:
providing access to an image depicting a structure, the structure having a plurality of planar elements comprising at least a roof facet and one or more walls; providing the image as input to a neural network, wherein the neural network outputs, at least, a surface normal associated with the roof facet and a surface normal associated with a particular wall of the one or more walls; adjusting each surface normal based on a transform, wherein the transform adjusts at least the surface normal associated with the particular wall to be substantially orthogonal to a vertical orientation; and extracting a pitch of the roof facet based on the adjusted surface normal associated with the roof facet and a vertical vector.

3 . The method of claim 2 , wherein a second neural network outputs the vertical vector.

4 . The method of claim 2 , further comprising identifying the vertical vector based on a vanishing point coordinate system.

5 . The method of claim 4 , wherein identifying the vertical vector based on the vanishing point coordinate system comprises:
determining the vanishing point coordinate system by extending lines associated with the structure to determine intersections of the lines associated with the structure; and identifying the vertical vector based on a first axis of the vanishing point system.

6 . The method of claim 2 , further comprising determining the vertical vector based on a feature associated with the particular wall.

7 . The method of claim 2 , wherein the neural network comprises a convolutional neural network trained to segment the planar elements into at least the roof facet or the one or more walls.

8 . The method of claim 7 , 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.

9 . 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:
provide access to an image depicting a structure, the structure having a plurality of planar elements comprising at least a roof facet and one or more walls; provide the image as input to a neural network, wherein the neural network outputs, at least, a surface normal associated with the roof facet and a surface normal associated with a particular wall of the one or more walls; adjust each surface normal based on a transform, wherein the transform adjusts at least the surface normal associated with the particular wall to be substantially orthogonal to a vertical orientation; and extract a pitch of the roof facet based on the adjusted surface normal associated with the roof facet and a vertical vector.

10 . The system of claim 9 , wherein a second neural network outputs the vertical vector.

11 . The system of claim 9 , wherein the instructions further cause the one or more processors to identify the vertical vector based on a vanishing point coordinate system.

12 . The system of claim 11 , wherein to identify the vertical vector based on the vanishing point coordinate system, the instructions cause the one or more processors to:
determine the vanishing point coordinate system by extending lines associated with the structure to determine intersections of the lines associated with the structure; and identify the vertical vector based on a first axis of the vanishing point system.

13 . The system of claim 9 , wherein the instructions further cause the one or more processors to determine the vertical vector based on a feature associated with the particular wall.

14 . The system of claim 9 , wherein the neural network comprises a convolutional neural network trained to segment the planar elements into at least the roof facet or the one or more walls.

15 . The system of claim 14 , 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.

16 . 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 perform operations comprising:
providing access to an image depicting a structure, the structure having a plurality of planar elements comprising at least a roof facet and one or more walls; providing the image as input to a neural network, wherein the neural network outputs, at least, a surface normal associated with the roof facet and a surface normal associated with a particular wall of the one or more walls; adjusting each surface normal based on a transform, wherein the transform adjusts at least the surface normal associated with the particular wall to be substantially orthogonal to a vertical orientation; and extracting a pitch of the roof facet based on the adjusted surface normal associated with the roof facet and a vertical vector.

17 . The non-transitory computer storage media of claim 16 , wherein a second neural network outputs the vertical vector.

18 . The non-transitory computer storage media of claim 16 , wherein the instructions further cause the one or more processors to perform operations comprising identifying the vertical vector based on a vanishing point coordinate system.

19 . The non-transitory computer storage media of claim 18 , identifying the vertical vector based on the vanishing point coordinate system comprises:
determining the vanishing point coordinate system by extending lines associated with the structure to determine intersections of the lines associated with the structure; and identifying the vertical vector based on a first axis of the vanishing point system.

20 . The non-transitory computer storage media of claim 16 , wherein the neural network comprises a convolutional neural network trained to segment the planar elements into at least the roof facet or the one or more walls.

21 . The non-transitory computer storage media of claim 20 , 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.

Assignees

• Hover Inc

Inventors

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

Classifications

• G06T7/70

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

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06N3/08

  Learning methods · CPC title

• G06T2207/20092

  Interactive image processing based on input by user · CPC title

• G06T7/10

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