Systems and methods for detecting, extracting, and categorizing structure data from imagery
Systems and methods for detecting, extracting, and categorizing structure data from aerial imagery following a major weather event are provided. The system processes digital images and weather data to automatically detect, extract, and categorize structure data following a major weather event. After receiving an indication of a region of interest (“ROI”) from a user, the system retrieves weather mapping data for the ROI and retrieves information related to attributes of structures within the ROI from a machine learning subsystem. The system then cross-references the property data, the weather data, and the structure attributes and assigns a risk rating to the structures within the ROI. Finally, the system generates and delivers a data package to the user.
1 . A method for predicting damage to a structure, comprising:
receiving at a computer system an indication of a geospatial region of interest from a user;
retrieving by the computer system one or more aerial images associated with the region of interest from an aerial image database;
processing the one or more aerial images using a machine learning algorithm executed by the computer system to extract one or more attributes of a structure within the region of interest;
retrieving by the computer system weather data associated with the region of interest from a weather database;
determining by the computer system a likelihood of damage to the structure based on the one or more extracted attributes and the weather data associated with the region of interest;
transmitting a data package from the computer system which includes the likelihood of damage to the structure; and
displaying a project map which includes a plurality of user-selectable display layers that can be toggled on and off, wherein at least one of the user-selectable display layers includes a graphical depiction of a weather event overlaid on the property.
2 . The method of claim 1 , wherein geospatial region of interest is indicated by latitude and longitude coordinates.
3 . The method of claim 1 , wherein the geospatial region of interest is indicated by a bounded polygon displayed on a computer display.
4 . The method of claim 3 , wherein the bounded polygon is determined by one or more of a postal address, property survey data, or a selection made by a user in a geospatial mapping interface.
5 . The method of claim 1 , wherein the one or more aerial images comprises one or more of a satellite image, an image captured by an unmanned aerial vehicle (UAV), a photographic aerial image, a scanned image, or a LIDAR image.
6 . The method of claim 1 , wherein the weather data includes data relating to one or more of hail storms, wind, and hurricanes.
7 . The method of claim 1 , wherein the machine learning algorithm extracts attributes relating to a roof of a structure including one or more of a roof type, a roof area, a slope, a roof material, or an eave height.
8 . The method of claim 1 , further comprising calculating by the computer system a risk rating level correlated to the likelihood of damage and including the risk rating level in the data package.
9 . The method of claim 1 , further comprising processing the data package to generate a visualization of damage and displaying the visualization to a user.
10 . The method of claim 1 , further comprising detecting, extracting, and categorizing structure data from one or more of a wildfire, lightning, arson, hurricanes, hailstorms, tornadoes, and non-weather-related data.
11 . A system for predicting damage to a structure, comprising:
a memory storing one or more aerial images; and
a processor in communication with the memory, the processor:
receiving an indication of a geospatial region of interest from a user;
retrieving one or more aerial images associated with the region of interest from the memory;
processing the one or more aerial images using a machine learning algorithm to extract one or more attributes of a structure within the region of interest;
retrieving weather data associated with the region of interest from a weather database;
determining a likelihood of damage to the structure based on the one or more extracted attributes and the weather data associated with the region of interest; and
transmitting a data package which includes the likelihood of damage to the structure; and
displaying a project map which includes a plurality of user-selectable display layers that can be toggled on and off, wherein at least one of the user-selectable display layers includes a graphical depiction of a weather event overlaid on the property.
12 . The system of claim 11 , wherein geospatial region of interest is indicated by latitude and longitude coordinates.
13 . The system of claim 11 , wherein the geospatial region of interest is indicated by a bounded polygon displayed on a computer display.
14 . The system of claim 13 , wherein the bounded polygon is determined by one or more of a postal address, property survey data, or a selection made by a user in a geospatial mapping interface.
15 . The system of claim 11 , wherein the one or more aerial images comprises one or more of a satellite image, an image captured by an unmanned aerial vehicle (UAV), a photographic aerial image, a scanned image, or a LIDAR image.
16 . The system of claim 11 , wherein the weather data includes data relating to one or more of hail storms, wind, and hurricanes.
17 . The system of claim 11 , wherein the machine learning algorithm extracts attributes relating to a roof of a structure including one or more of a roof type, a roof area, a slope, a roof material, or an eave height.
18 . The system of claim 11 , wherein the processor calculates a risk rating level correlated to the likelihood of damage and includes the risk rating level in the data package.
19 . The system of claim 11 , wherein the processor detects, extracts, and categorizes structure data from one or more of a wildfire, lightning, arson, hurricanes, hailstorms, tornadoes, and non-weather-related data.