Manually digitizing the track of an object can be a slow process. This model automates the object tracking process significantly, which speeds up motion imagery analysis workflows. It can be used in the Full Motion Video extension of ArcGIS Pro to track objects. See the detailed workflow and description of the object tracking capability in ArcGIS Pro.
You can use this model for applications such as object follower and surveillance of stationary objects. Its performance decreases if there are sudden camera shakes or abrupt scale changes.
License requirements
To complete this workflow, the following are the license requirements:
- ArcGIS Desktop—ArcGIS Image Analyst extension for ArcGIS Pro
Model details
This model has the following characteristics:
- Input—Object to track marked as a bounding box in 8-bit, three-band high-resolution full motion video or motion imagery. The recommended object size is greater than 15x15 pixels. See a sample video to try the Full Motion Video capability of the ArcGIS Image Analyst extension for ArcGIS Pro.
- Output—Bounding box depicting object location in successive frames.
- Compute—This workflow is compute intensive and a GPU with compute capability of 6.0 or higher is recommended.
- Applicable geographies—This model is designed to work well globally.
- Architecture—This model uses the SiamMask model architecture implemented in ArcGIS API for Python.
- Accuracy metrics—This model has a mIOU score of 0.853.
Access and download the model
Download the Object Tracking 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 Object Tracking 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.
Release notes
The following are the release notes:
| Date | Description |
|---|---|
| July 2021 |
|