Abstract—In fish farming, maintaining the number of fish is important from the viewpoint of stock management, feed volume adjustment, and so on. In this study, we evaluated the use of multiple scanning sonars to estimate the number of fish in a cage. To estimate fish counts based on coordinate information obtained from multiple sonars, we applied a hierarchical clustering method. The fundamental performance of our fish counting system was evaluated using a simulation approach by changing the number of fish, number of sonars, and size of fish. Our system can successfully estimate the number of fish with an error of 1 % or less in certain conditions.

 

Index Terms—Scanning sonar, fish counting, clustering, group average method, simulation

Cite: Yoshiaki Taniguchi and Kansei Oki, “Simulation Study of Fish Counting by Multiple Scanning Sonars in a Fish Farm,”Journal of Communications vol. 15, no. 2, pp. 164-170, February 2020. Doi: 10.12720/jcm.15.2.164-170

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.