Abstract: A system utilizing artificial intelligence use and AI module to process roof data that includes image data and non-imagery data to generate at least one image input vector data structure and at least one imagery input vector data structure associated with the roof, the system comparing the at least one image input vector data structure and the at least one imagery input vector data structure to preexisting at least one preexisting imagery input vector data structure and at least one preexisting non-imagery input vector data structure to determine if a change has occurred to the roof or determine an age of the roof.

Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.

Abstract: A system utilizing artificial intelligence use and AI model to process property data that includes image data and non-imagery data to generate AI attributes associated with the property and receiving data from a plurality of different data sources, the system normalizing the AI attributes and the data from a plurality of different data sources and using them to automatically make decisions relating to underwriting and claims adjustments based on comparison to underwriting or adjustment rules.

Abstract: A system and method for viewing aerial imagery and derived content on a web-based imagery browser that can be accessed by at least two users simultaneously. In addition, a system for interactively generating 3D geometry data for a location imaged from multiple viewpoints.

Abstract: Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

Abstract: A system utilizing artificial intelligence use and AI module to process roof data that includes image data and non-imagery data to generate at least one image input vector data structure and at least one imagery input vector data structure associated with the roof, the system comparing the at least one image input vector data structure and the at least one imagery input vector data structure to preexisting at least one preexisting imagery input vector data structure and at least one preexisting non-imagery input vector data structure to determine if a change has occurred to the roof or determine an age of the roof.

Abstract: A system and a method for generating semantic predictions corresponding to pixels of an input image by providing a first Convolutional Neural Network (CNN) and a second CNN, the first CNN having a selected sampling factor, s, and defining a mask that corresponds to a grid of pixels positioned s pixels apart from each other and centered on a single pixel of the grid of pixels, with an input image crop size based on the extent of the mask, and processing mage data shaped according to the input image crop to generate semantic predictions for pixels corresponding to the grid of pixel locations of the mask. The second CNN receives input image and generates semantic predictions for the input image that is at a higher pixel density than the mask.

Abstract: Methods, non-transitory computer-readable media, and property analysis systems are disclosed that extract vegetation location information from overhead and LIDAR images associated with a geographic location. The images are aligned based on the extracted vegetation information. Models are applied to the aligned images based on vegetation height information extracted from the LIDAR images. A graph is then generated based on a result of the application of the models. The graph represents a relationship between vegetation, one or more buildings, and one or more fire pathways associated with the geographic location. A wildfire risk score generated based on the graph is then output for the buildings via a GUI. Thus, the disclosed technology applies wildfire spread models and graphs to vegetation and buildings identified in aligned overhead and LIDAR imagery to provide relatively accurate wildfire risk assessment to insurers and homeowners and thereby facilitate informed decision-making and preventative measures.

Abstract: This application discloses methods, systems, and computer-implemented virtualization software applications and computer-implemented graphical user interface tools for remote virtual visualization of structures. Images are captured by an imaging vehicle of a structure and the captured images are transmitted to a remote server via a communication network. Using virtual 3D digital modeling software the server, using the images received from the imaging vehicle, generates a virtual 3D digital model of the structure and stores it in a database. This virtual 3D digital model can be accessed by remote users, using virtualization software applications, and used to view images of the structure. The user is able to manipulate the images and to view them from various perspectives and compare the before-the-damage images with images taken after damage have occurred. Based on all this the user is enabled to remotely communicate with an insurance agent and/or file an insurance claim.

Abstract: This application discloses methods, systems, and computer-implemented virtualization software applications and computer-implemented graphical user interface tools for remote virtual visualization of structures. Images are captured by an imaging vehicle of a structure and the captured images are transmitted to a remote server via a communication network. Using virtual 3D digital modeling software the server, using the images received from the imaging vehicle, generates a virtual 3D digital model of the structure and stores it in a database. This virtual 3D digital model can be accessed by remote users, using virtualization software applications, and used to view images of the structure. The user is able to manipulate the images and to view them from various perspectives and compare the before-the-damage images with images taken after damage have occurred. Based on all this the user is enabled to remotely communicate with an insurance agent and/or file an insurance claim.

Abstract: Methods, non-transitory computer readable media, and roof analysis systems are disclosed that preprocess overhead images in imagery data obtained based on a request comprising a geographic location. The overhead images depict a building at different historical points in time identified in the imagery data. A neural network is applied to input data structures into which the overhead images are converted. The neural network is trained to extract relationships between features from the input data structures indicating changes in a roof of the building and generate an output data structure representing the changes. Patterns in the output data structure are analyzed to determine instances of change of the roof. A roof age is then output via a user interface in response to the request. The roof age is generated based on a likelihood of the instances of change or a time interval between the overhead images and a current time.

Abstract: A computer-implemented method for generating roof reports. In one embodiment, a user begins by entering an address into an application and clicking a “request” button. A 3D model of the structure at the address is prepared. The application may then proceed with manual or automatic roof extraction. For manual roof extraction, an analyst may outline roof facets to create a roof model. For automatic roof extraction, the application may use machine learning or another technique to automatically extract and then simplify roof facets. In either case, the application may then present the roof model to a reviewer for inspection. The reviewer may then accept or reject the roof model. If the reviewer rejects the roof model, an analyst may correct the roof model and resuming it for review. Once the roof model passes a review, the application may then proceed with converting the roof model into a roof report.