Fish identification from videos captured in uncontrolled underwater environments. (18th July 2016)

• Record Type: Journal Article
• Authors: Shafait, Faisal; Mian, Ajmal; Shortis, Mark; Ghanem, Bernard; Culverhouse, Phil F.; Edgington, Duane; Cline, Danelle; Ravanbakhsh, Mehdi; Seager, James; Harvey, Euan S.
• Is Part Of: ICES journal of marine science. Volume 73:Number 10(2016)
• Page Start: 2737
• Page End: 2746
• Publication Date: 2016-07-18
• Subjects: computer vision -- fish classification -- fish identification -- image analysis -- image sets -- species recognition.; Ocean -- Periodicals; Fisheries -- Periodicals; Fishes -- Periodicals; Marine biology -- Bibliography -- Periodicals; 551.4605
• DOI: 10.1093/icesjms/fsw106
• Languages: English
• ISSNs: 1054-3139

Abstract

Abstract : There is an urgent need for the development of sampling techniques which can provide accurate and precise count, size, and biomass data for fish. This information is essential to support the decision-making processes of fisheries and marine conservation managers and scientists. Digital video technology is rapidly improving, and it is now possible to record long periods of high resolution digital imagery cost effectively, making single or stereo-video systems one of the primary sampling tools. However, manual species identification, counting, and measuring of fish in stereo-video images is labour intensive and is the major disincentive against the uptake of this technology. Automating species identification using technologies developed by researchers in computer vision and machine learning would transform marine science. In this article, a new paradigm of image set classification is presented that can be used to achieve improved recognition rates for a number of fish species. State-of-the-art image set construction, modelling, and matching algorithms from computer vision literature are discussed with an analysis of their application for automatic fish species identification. It is demonstrated that these algorithms have the potential of solving the automatic fish species identification problem in underwater videos captured within unconstrained environments.