This topic explains how to use the GroundingDINO pretrained model available on ArcGIS Living Atlas of the World. The model is used to detect objects in an image using a prompt.
GroundingDINO is an open-source sample model that can be prompted using free-form text prompts to extract features of various kinds. It is an open-set object detector that can find objects using a text prompt. The model outputs bounding boxes, which are converted to polygons and returned as GIS features. These features, which are described by the input text prompts, can be any object of interest such as vehicles, swimming pools, ships, airplanes, solar panels, and so on.
The following are the license requirements to complete this workflow:
- 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—The model has 8-bit, 3-band RGB imagery.
- Output—The feature class contains masks of various objects in the image.
- Compute—This workflow is computationally intensive, and a GPU with minimum CUDA compute capability of 6.0 is recommended. The model requires a GPU with at least 8 GB of GPU memory.
- Applicable geographies—The model is expected to work globally.
- Architecture—The model is based on the open-source Grounding DINO by IDEA-Research (The International Digital Economy Academy). You can review the source code of this sample deep learning package for additional information.
Access and download the model
Download the GroundingDINO pretrained model from ArcGIS Living Atlas of the World. Alternatively, access the model directly from ArcGIS Pro, or use it in ArcGIS Image for ArcGIS Online.
- Browse to ArcGIS Living Atlas of the World.
- Sign in with your ArcGIS Online credentials.
- Search for GroundingDINO 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 it 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 |
|---|---|
| August 2024 |
First release of GroundingDINO |