The CSIRO Crown-of-Thorn Starfish Detection Dataset

• DOI: 10.48550/arxiv.2111.14311
• Publication Date: 2021-01-01
• Authors: Jiajun Liu; Branislav Kusý; Ross Marchant; Brendan Do; Torsten Merz; Joseph R. Crosswell; Andy Steven; Nic Heaney; Karl von Richter; Lachlan Tychsen-S...; David Ahmedt‐Aris...; Mohammad Ali Armin; Geoffrey Carlin; Russell C. Babcock; Peyman Moghadam; D. J. B. Smith; Timothy A. Davis; Kemal El Moujahid; Martin Wicke; Megha Malpani
• Keywords: FOS: Computer and information sciences; Computer Science - Machine Learning; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computer Vision and Pattern Recognition (cs.CV); Computer Science - Computer Vision and Pattern Recognition; 0202 electrical engineering, electronic engineering, information engineering; 14. Life underwater; 02 engineering and technology; Machine Learning (cs.LG)

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance control programs underway in an attempt to manage COTS populations ecologically sustainable levels. We release large-scale, annotated underwater image dataset from outbreak area GBR, encourage research Machine Learning AI-driven technologies improve detection, monitoring, management at reef scale. The is released hosted Kaggle competition that challenges international community with task detection these images.