Advancements towards selective barrier passage by automatic species identification: applications of deep convolutional neural networks on images of dewatered fish

Abstract

Abstract Invasive species negatively affect enterprises such as fisheries, agriculture, and international trade. In the Laurentian Great Lakes Basin, threats include invasive sea lamprey (Petromyzon marinus) and the four major Chinese carps. Barriers have proven to be an effective mechanism for managing invasive species but are detrimental in that they also limit the migration of desirable, native species. Fish passage technologies that selectively pass desirable species while blocking undesirable species are needed. Key to an automated selective barrier passage system is a high precision fish classifier to assign fish to be passed or blocked. Presented is an evaluation of two classifiers developed using images of partially dewatered fish captured from a commercial, high-speed camera array. For a lamprey vs. non-lamprey classification task, an ensemble prediction approach achieved near perfect accuracy on both a validation and test dataset. For a species classification task for 13 species found in the Great Lakes region, an ensemble prediction approach achieved accuracies of 96% and 97% on a validation and test dataset, respectively. Both prediction approaches were based on deep convolutional neural networks constructed using transfer learning and image augmentation. The study provides an important proof-of-concept for the viability in fully automated, selective fish passage systems.