Roof condition assessment using machine learning

Patent metadata

Field	Value
Publication number	US-11776104-B2
Application number	US-202016893090-A
Country	US
Kind code	B2
Filing date	Jun 4, 2020
Priority date	Sep 20, 2019
Publication date	Oct 3, 2023
Grant date	Oct 3, 2023

Abstract

Systems and methods for roof condition assessment from digital images using machine learning are disclosed, including receiving an image of a structure having roof characteristic(s), first pixel values depicting the structure, second pixel values outside of the structure depicting a background surrounding the structure, and first geolocation data; generating a synthetic shape image of the structure from the image using machine learning, including pixel values forming a synthetic outline shape, and having second geolocation data; mapping the synthetic shape onto the image, based on the first and second geolocation data, and changing the second pixel values so as to not depict the background; assessing roof characteristic(s) based on the first pixel values with a second machine learning algorithm resulting in a plurality of probabilities, each for a respective roof condition classification category, and determining a composite probability based upon the plurality of probabilities so as to classify the roof characteristic(s).

First claim

What is claimed is:

1. A non-transitory computer readable medium storing computer executable code that when executed by a processor cause the processor to:
receive a mask image of a structure, the structure having a roof with one or more characteristic, the mask image having pixels with first pixel values depicting the structure and second pixel values outside of the structure depicting a background, the first pixel values being original pixel values depicting real world captured pixels of the structure and the second pixel values being altered from their original pixel values so as to not represent real world captured pixels of the background outside of the structure; and,
assess one or more characteristic of the roof based at least in part on the first pixel values with a machine learning algorithm and resulting in a classification of the one or more characteristic of the roof.

2. The non-transitory computer readable medium of claim 1 , wherein assessing one or more characteristic of the roof based at least in part on the first pixel values includes the machine learning algorithm determining a probability that the roof depicted in the first pixel values for multiple roof classification categories, and combining the probabilities for the multiple roof classification categories into a composite probability indicative of the one or more characteristic of the roof.

3. The non-transitory computer readable medium storing computer executable code of claim 2 , wherein the one or more characteristic includes a roof condition.

4. The non-transitory computer readable medium of claim 2 , wherein the one or more characteristic includes one or more of a roof architecture and a roof material.

5. The non-transitory computer readable medium of claim 2 , wherein the one or more characteristic includes a roof tree coverage.

6. The non-transitory computer readable medium of claim 2 , wherein the one or more characteristic includes a roof solar panel coverage.

7. The non-transitory computer readable medium of claim 2 , wherein the mask image has a pixel resolution between one to nine inches per pixel.

8. The non-transitory computer readable medium of claim 7 , wherein the machine learning algorithm has been trained with truth pairs including a test masked image and a truth roof classification.

9. The non-transitory computer readable medium of claim 1 , wherein the mask image is indicative of an entirety of the roof, and wherein the classification is indicative of an entirety of the roof.

Assignees

• Pictometry Int Corp

Inventors

• Strong Shadrian

Classifications

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G06F16/29

  Geographical information databases · CPC title

• G06F18/2155

  characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling · CPC title

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G06N20/00

  Machine learning · CPC title