As democratization, availability, and acquisition of data is increasing, privacy is becoming a concern. Regulations such as GDPR have been introduced to address the privacy rights of users. To help maintain privacy, this model can be used to prevent the identification of vehicles by automatically blurring the license plates.
Disclaimer: This model is trained to blur license plates in images recorded with sensors that are typically used in autonomous vehicles. It does not work on low-quality or grayscale images and other extreme camera configurations such as fish-eye.
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 Image for ArcGIS Online
This model has the following characteristics:
- Input—High-resolution, 3-band street-level imagery/oriented imagery, in a compatible image format, as per the Classify Pixels Using Deep Learning tool.
- Output—Image with blurred license plates.
- Compute—This workflow is compute intensive and a GPU with compute capability of 6.0 or higher is recommended
- Architecture—Open-source Anonymizer model by understand.ai.
Access and download the model
Download the License Plate Blurring 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 License Plate Blurring 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.
The following are the release notes: