Share Email Print
cover

Proceedings Paper

An automatic identification and monitoring system for coral reef fish
Author(s): Joseph Wilder; Chetan Tonde; Ganesh Sundar; Ning Huang; Lev Barinov; Jigesh Baxi; James Bibby; Andrew Rapport; Edward Pavoni; Serena Tsang; Eri Garcia; Felix Mateo; Tanya M. Lubansky; Gareth J. Russell
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

To help gauge the health of coral reef ecosystems, we developed a prototype of an underwater camera module to automatically census reef fish populations. Recognition challenges include pose and lighting variations, complicated backgrounds, within-species color variations and within-family similarities among species. An open frame holds two cameras, LED lights, and two ‘background’ panels in an L-shaped configuration. High-resolution cameras send sequences of 300 synchronized image pairs at 10 fps to an on-shore PC. Approximately 200 sequences containing fish were recorded at the New York Aquarium’s Glover’s Reef exhibit. These contained eight ‘common’ species with 85–672 images, and eight ‘rare’ species with 5–27 images that were grouped into an ‘unknown/rare’ category for classification. Image pre-processing included background modeling and subtraction, and tracking of fish across frames for depth estimation, pose correction, scaling, and disambiguation of overlapping fish. Shape features were obtained from PCA analysis of perimeter points, color features from opponent color histograms, and ‘banding’ features from DCT of vertical projections. Images were classified to species using feedforward neural networks arranged in a three-level hierarchy in which errors remaining after each level are targeted by networks in the level below. Networks were trained and tested on independent image sets. Overall accuracy of species-specific identifications typically exceeded 96% across multiple training runs. A seaworthy version of our system will allow for population censuses with high temporal resolution, and therefore improved statistical power to detect trends. A network of such devices could provide an ‘early warning system’ for coral ecosystem collapse.

Paper Details

Date Published: 15 October 2012
PDF: 15 pages
Proc. SPIE 8499, Applications of Digital Image Processing XXXV, 84991H (15 October 2012); doi: 10.1117/12.928860
Show Author Affiliations
Joseph Wilder, Rutgers, The State Univ. of New Jersey (United States)
Chetan Tonde, Rutgers, The State Univ. of New Jersey (United States)
Ganesh Sundar, Rutgers, The State Univ. of New Jersey (United States)
Ning Huang, Rutgers, The State Univ. of New Jersey (United States)
Lev Barinov, Rutgers, The State Univ. of New Jersey (United States)
Jigesh Baxi, Rutgers, The State Univ. of New Jersey (United States)
James Bibby, Rutgers, The State Univ. of New Jersey (United States)
Andrew Rapport, Rutgers, The State Univ. of New Jersey (United States)
Edward Pavoni, Rutgers, The State Univ. of New Jersey (United States)
Serena Tsang, Rutgers, The State Univ. of New Jersey (United States)
Eri Garcia, Union City High School (United States)
Felix Mateo, Union City High School (United States)
Tanya M. Lubansky, New Jersey Institute of Technology (United States)
Gareth J. Russell, New Jersey Institute of Technology (United States)


Published in SPIE Proceedings Vol. 8499:
Applications of Digital Image Processing XXXV
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top