Abstract: A computer-implemented method for identifying property changes by analyzing differences between old and new imagery. In one embodiment, an administrator begins by creating a project with links to old and new imagery and uploading a file with parcel boundaries. The application may then divide the project into smaller batches and then automatically classify each batch. Analysts may then review these batches and reject those that are insufficiently accurate. For rejected batches, analysts may manually classify the parcels. Analysts may then review these batches again. In one embodiment, once all batches are accepted, the project may be marked as complete and suitable reports may be generated and sent. These reports may include a customer report which may include overall project statistics, a breakdown of changes by type, a heatmap showing which areas are changing fastest, and/or an estimated tax impact of the identified changes.

Abstract: A computer-implemented method for identifying property changes by analyzing differences between old and new imagery. In one embodiment, an administrator begins by creating a project with links to old and new imagery and uploading a file with parcel boundaries. The application may then divide the project into smaller batches and then automatically classify each batch. Analysts may then review these batches and reject those that are insufficiently accurate. For rejected batches, analysts may manually classify the parcels. Analysts may then review these batches again. In one embodiment, once all batches are accepted, the project may be marked as complete and suitable reports may be generated and sent. These reports may include a customer report which may include overall project statistics, a breakdown of changes by type, a heatmap showing which areas are changing fastest, and/or an estimated tax impact of the identified changes.

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.

Abstract: A computer-implemented method for identifying property changes by analyzing differences between old and new imagery. In one embodiment, an administrator begins by creating a project with links to old and new imagery and uploading a file with parcel boundaries. The application may then divide the project into smaller batches and then automatically classify each batch. Analysts may then review these batches and reject those that are insufficiently accurate. For rejected batches, analysts may manually classify the parcels. Analysts may then review these batches again. In one embodiment, once all batches are accepted, the project may be marked as complete and suitable reports may be generated and sent. These reports may include a customer report which may include overall project statistics, a breakdown of changes by type, a heatmap showing which areas are changing fastest, and/or an estimated tax impact of the identified changes.

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.