Computer Vision Pipeline for Automated Antarctic Krill Analysis

TL;DR

This paper presents an automated computer vision pipeline that uses deep learning for accurate krill detection, segmentation, and measurement, aiding Antarctic biomass estimation and environmental monitoring.

Contribution

It introduces a novel automated system combining web-based annotation and deep learning models for krill analysis, improving efficiency and accuracy over manual methods.

Findings

Achieved 77.28% AP in krill instance segmentation

Estimated krill maturity stage with 62.99% accuracy

Measured krill length with an average error of 1.98mm

Abstract

British Antarctic Survey (BAS) researchers launch annual expeditions to the Antarctic in order to estimate Antarctic Krill biomass and assess the change from previous years. These comparisons provide insight into the effects of the current environment on this key component of the marine food chain. In this work we have developed tools for automating the data collection and analysis process, using web-based image annotation tools and deep learning image classification and regression models. We achieve highly accurate krill instance segmentation results with an average 77.28% AP score, as well as separate maturity stage and length estimation of krill specimens with 62.99% accuracy and a 1.98mm length error respectively.