This document explains how to use the Building Change Detection deep learning model available on ArcGIS Living Atlas of the World. The model detects change in buildings by analyzing high-resolution imagery from two different time periods.
Detecting and monitoring changes in buildings is crucial for urban development, safety, and environmental sustainability. It enables city planners to track growth, ensure compliance with zoning laws, update property records, and detect illegal constructions. Monitoring changes can help assess the impact of urbanization on infrastructure and natural resources, and the impact of any natural disaster on the urban development. Using deep learning models, with high resolution aerial or drone imagery, can greatly improve this process by automating large-scale detection, and identifying subtle changes that human inspectors might miss. This can enhance accuracy, reduce manual labor, and support data-driven urban planning decisions.
Use this model to detect changes in buildings and produce a continuous change magnitude raster instead of a simple binary raster, indicating probability of change at each pixel.
License requirements
To complete this workflow, the following are the license requirements:
- ArcGIS Desktop—ArcGIS Image Analyst extension for ArcGIS Pro
- ArcGIS Enterprise—ArcGIS Image Server
- ArcGIS Online—ArcGIS Pro or Professional Plus user type
Model details
This model has the following characteristics:
- Input— Raster, mosaic dataset, or image service (10-20 centimeters spatial resolution). Both before and after rasters should be accurately aligned with no relief displacement.
- Output—Raster representing probability of change for each pixel.
- Compute—This workflow is compute intensive, and a GPU with minimum CUDA compute capability of 6.0 is recommended.
- Applicable geographies— The model is expected to work well in urban areas with low-rise, freestanding buildings.
- Architecture—This model is based upon Changen, a GAN-based Generative Probabilistic Change Model (GPCN) by Z. Zheng et. al.
Access and download the model
Download the Building Change Detection pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro, or consume it in ArcGIS Image for ArcGIS Online.
- Browse to ArcGIS Living Atlas of the World.
- Sign in with your ArcGIS Online credentials.
- Search for Building Change Detection and open the item page from the search results.
- Click the Download button to download the model.
You can use the downloaded .dlpk file directly in ArcGIS Pro, or upload and use it in ArcGIS Enterprise. Additionally, you can fine-tune the pretrained model if necessary.
Release notes
The following are the release notes:
| Date | Description |
|---|---|
| October 2024 | First release of Building Change Detection |