Automatic fish counting from underwater video images: performance estimation and evaluation

Authors

  • S. Marini
  • E. Azzurro
  • S. Coco
  • Joaquín del Río Fernandez
  • S. Enguídanos
  • E. Fanelli
  • Marc Nogueras Cervera
  • Valerio Sbragaglia
  • Daniel Toma
  • Jacopo Aguzzi

Abstract

Cabled observatories offer new opportunities to monitor species abundances at frequencies and durations never attained before. When nodes bear cameras, these may be transformed into the first sensor capable of quantifying biological activities at individual, populational, species, and community levels, if automation image processing can be sufficiently implemented. Here, we developed a binary classifier for the fish automated recognition based on Genetic Programming tested on the images provided by OBSEA EMSO testing site platform located at 20 m of depth off Vilanova i la Gertrú (Spain). The performance evaluation of the automatic classifier resulted in a 78% of accuracy compared with the manual counting. Considering the huge dimension of data provided by cabled observatories and the difficulty of manual processing, we consider this result highly promising also in view of future implementation of the methodology to increase the accuracy.

Downloads

Issue

No. 19 (2016)

Section

Articles

License

Universitat Politècnica de Catalunya has joined the Berlin Declaration on Open Access to Knowledge in the Sciences and Humanities. This declaration proposes the universal acces to the results of scientific and technical research.

All papers presented at Martech will be published in both the UPCommons and the Martech organization web sites, the former being the institutional digital deposit of Universitat Politècnica de Catalunya (https://upcommons.upc.edu). This difussion will be made through the Creative Commons License Attribution-NonCommercial-NoDerivs 2.5 or similar (http://creativecommons.org/licenses/by-nc-nd/2.5/deed.en).

When sending the final paper, the author must agree to the conference having non-exclusive rights on this operation. The author will maintain his/her right to diffuse the paper elsewhere.