MBARI Benthic Supercategory Detector

Model Details

• Trained by researchers at CVisionAI and the Monterey Bay Aquarium Research Institute (MBARI).
• Detectron2 with ResNet backbone
• Object detection
• Fine tuned to detect 20 morphotaxonomic categories of benthic animals in the Greater Monterey Bay Area off the coast of Central California.

Intended Use

• Make real time detections on video feed from MBARI Remotely Operated Vehicles.
• Post-process video collected in the region by MBARI vehicles.

Factors

• Distribution shifts related to sampling platform, camera parameters, illumination, and deployment environment are expected to impact model performance.
• Evaluation was performed on an IID subset of available training data. Data to test out of distribution performance not currently available.

Metrics

• Confusion matrix evaluated at test time.

Training and Evaluation Data

• A combination of publicly available FathomNet and internal MBARI data

<!--

Deployment

In an environment running YOLOv5v6.2:

python classify/predict.py --weights best.pt --data data/images/

-->