Fish species discrimination in turbid water: possible with DIDSON generated acoustic shadows?

This study addresses a fish species discrimination based on normalized elliptic fourier descriptors applied to acoustic shadows derived by a Dual-frequency Identification Sonar (DIDSON). Acoustic shadows of stainless steel templates (20 cm, 30 cm, 40 cm and 50 cm) and living fish of four species respectively were projected on a plane in an experimental setup and tested on suitability for shape-based species discrimination. 20 cm templates were correctly classified in 97,5 % of the cases, indicating a size threshold. The larger templates reached values of 100 % correct classification based on a cross-validated discriminant function analysis. It was also demonstrated that it is possible to classify moving fish based on screenshots of their acoustic shadows with a certainty of 83,9 %. Further work in extended field tests is required to evaluate the method to be used in practical monitoring applications in multi-species river environments.