Underway Shadowgraphic Imaging for Plankton Detection and Classification

Abstract

Technological advances in hardware and software have enabled the development of novel in situ plankton imaging systems to investigate the spatial and temporal distribution of plankton communities. State-of-the-art machine learning approaches have been applied for automated image classification, effectively handling the complex and highly variable morphology of plankton while maintaining high accuracy. Despite these advances, few instruments can acquire zooplankton images autonomously in a continuous underway mode, which is essential for large-scale oceanographic surveys conducted aboard research vessels or ships of opportunity. Here, we present SiMFlux, an underway shadowgraphic imaging system developed at the University of São Paulo, and report results from the Orient Expedition. Observations were conducted aboard an 80-foot sailing vessel navigating across the Indian and Atlantic Oceans. A total of 193 videos were analyzed from daily route segments, yielding over 1.2 million regions of interest (ROIs) containing organisms and detrital particles. Particles were automatically classified and subsequently validated by plankton experts.

Bibliographic Information