Machine Vision-Assisted In-Situ Ichthyoplankton Imaging System Computer Vision Technology for High-Throughput Specimen Recognition in the New In-Situ Ichthyoplankton Imaging System

Current technologies available for the study of plankton remain limited in comparison to the spatial-temporal resolution and data acquisition rate available for physical oceanographic measurements. Specifically, plankton measurements are made primarily by use of net collections, as opposed to the high-speed digital output possible for physical sampling. Though net technology has become quite sophisticated (e.g., the multiple opening/closing net and environmental sensing system), enabling vertical resolution coupled with detailed physical data, net samples still require manual processing, which is a time consuming and costly effort. Furthermore, nets integrate organisms over the sampling distance and depth, significantly reducing sample resolution. To address this problem, a high-resolution towed plankton imaging system, the In-Situ Ichthyoplankton Imaging System (ISIIS), was built, capable of True Positive % False Positive % Copepod Fish larvae Chaetognath Larvacean Trichodesnium