Summary of Sharktrack: An Accurate, Generalisable Software For Streamlining Shark and Ray Underwater Video Analysis, by Filippo Varini et al.
SharkTrack: an accurate, generalisable software for streamlining shark and ray underwater video analysis
by Filippo Varini, Joel H. Gayford, Jeremy Jenrette, Matthew J. Witt, Francesco Garzon, Francesco Ferretti, Sophie Wilday, Mark E. Bond, Michael R. Heithaus, Danielle Robinson, Devon Carter, Najee Gumbs, Vincent Webster, Ben Glocker
First submitted to arxiv on: 30 Jul 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper presents SharkTrack, a semi-automatic underwater video analysis software designed to facilitate the monitoring of elasmobranch (shark and ray) populations. Elasmobranchs are crucial components of marine ecosystems, but their populations are declining globally, making effective monitoring essential for conservation. The software uses Convolutional Neural Networks (CNN) and Multi-Object Tracking to automatically detect and track elasmobranchs, providing an annotation pipeline for manual species classification and computation of the standard metric ssMaxN, which measures relative abundance. The model achieved 89% accuracy on unseen BRUVS footage, requiring only two minutes of manual classification per hour of video. SharkTrack applications extend beyond BRUVS, enabling research and conservation organizations to analyze underwater stationary videos more efficiently. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SharkTrack is a new tool that helps scientists study sharks and rays better. It uses special computer algorithms to look at underwater videos and find the animals in them. This makes it much faster than if humans had to do it by hand. The tool is very good at finding these animals, even when they’re in different places or with different species. This will help conservationists take better care of sharks and rays and their homes. |
Keywords
» Artificial intelligence » Classification » Cnn » Object tracking
