This project is meant to take in images from ip-cameras via FTP and detecting objects from AI Model
Download the below model and add it to eval-worker/models
directory
- RetinaNet (Size = 145 mb, high performance and accuracy, with longer detection time)
Serve application
docker-compose up --build
Then vist http://localhost:3030
or http://<system-ip-address>:3030
To hook up your ip-cameras, get your systems IP address (perferably static-ip) and add it to your ip-camera's ftp service. Make sure to specifc port 22
- RetinaNet (Size = 145 mb, high performance and accuracy, with longer detection time)
- YOLOv3 (Size = 237 mb, moderate performance and accuracy, with a moderate detection time)
- TinyYOLOv3 (Size = 34 mb, optimized for speed and moderate performance, with fast detection time)