FasterRCNN-Great-Barrier-Reef

Introduction

he goal of creating a FastRCNN based object detection model was to accurately identify starfish in real-time, trained on underwater videos of coral reefs. Australia's stunningly beautiful Great Barrier Reef is the world’s largest coral reef and home to 1,500 species of fish, 400 species of corals, 130 species of sharks, rays, and a massive variety of other sea life. Unfortunately, the reef is under threat, in part because of the overpopulation of one particular starfish – the coral-eating crown-of-thorns starfish (or COTS for short). The model can accurately identify COTS from video footage and output coordinates of a "bounding box" with the location of the COTS.

About data

This notebook is a part of Kaggle Contest TensorFlow - Help Protect the Great Barrier Reef. Detect crown-of-thorns starfish in underwater image data.

Background

Australia's stunningly beautiful Great Barrier Reef is the world’s largest coral reef and home to 1,500 species of fish, 400 species of corals, 130 species of sharks, rays, and a massive variety of other sea life.

Unfortunately, the reef is under threat, in part because of the overpopulation of one particular starfish – the coral-eating crown-of-thorns starfish (or COTS for short). Scientists, tourism operators and reef managers established a large-scale intervention program to control COTS outbreaks to ecologically sustainable levels.

Author

Ayush Anand

References

Research Dataset Sourced from:

@misc{liu2021csiro,
title={The CSIRO Crown-of-Thorn Starfish Detection Dataset},
author={Jiajun Liu and Brano Kusy and Ross Marchant and Brendan Do and Torsten Merz and Joey Crosswell and Andy Steven and Nic Heaney and Karl von Richter and Lachlan Tychsen-Smith and David Ahmedt-Aristizabal and Mohammad Ali Armin and Geoffrey Carlin and Russ Babcock and Peyman Moghadam and Daniel Smith and Tim Davis and Kemal El Moujahid and Martin Wicke and Megha Malpani},
year={2021},
eprint={2111.14311},
archivePrefix={arXiv},
primaryClass={cs.CV}
}