Click on any node or arrow to see details.
A 20MP, 3-band RGB drone image is uploaded to an AWS S3 bucket.
An AWS Step Function initiates the segmentation job.
The job runs on an EC2 instance, pulling the custom Docker image.
The Python script loads the trained model and input image.
The model processes the image to generate object masks.
Masks are combined and refined to create a single output.
The final single-band JPEG mask is saved to a designated S3 bucket.