Technologies for using image data analysis to assess and classify hail damage
AssigneeRoofr Inc.
InventorsMarigona Bokshi-Drotar, Jing Wan, Sandra Kane, Yuntao Li
Life of this patent
Estimating the term…
Abstract
Systems and methods for analyzing image data to assess property damage are disclosed. According to certain aspects, a server may analyze segmented digital image data of a roof of a property using a convolutional neural network (CNN). The server may extract a set of features from a set of regions output by the CNN. Additionally, the server may analyze the set of features using an additional image model to generate a set of outputs indicative of a confidence level that actual hail damage is depicted in the set of regions.
Claims20
A method, comprising:
- inputting a first image of a first region corresponding to a roof into a hail damage detection model;
- extracting a set of features from an output of the hail damage detection model;
- utilizing a classification model to classify the first image of the first region corresponding to the roof, wherein a classification of the first image of the first region corresponding to the roof indicates actual hail damage or an absence of hail damage;
- and
- determining an estimated damage amount to the roof based in part on the classification of the first image of the first region corresponding to the roof.
A system, comprising:
- a processor configured to:
- input a first image of a first region corresponding to a roof into a hail damage detection model;
- extract a set of features from an output of the hail damage detection model;
- utilize a classification model to classify the first image of the first region corresponding to the roof, wherein a classification of the first image of the first region corresponding to the roof indicates actual hail damage or an absence of hail damage;
- and
- determine an estimated damage amount to the roof based in part on the classification of the first image of the first region corresponding to the roof;
- and
- a memory coupled to the processor and configured to provide the processor with instructions.
A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
- inputting a first image of a first region corresponding to a roof into a hail damage detection model;
- extracting a set of features from an output of the hail damage detection model;
- utilizing a classification model to classify the first image of the first region corresponding to the roof, wherein a classification of the first image of the first region corresponding to the roof indicates actual hail damage or an absence of hail damage;
- and
- determining an estimated damage amount to the roof based in part on the classification of the first image of the first region corresponding to the roof.
Dependencies are inferred from the claim text.