Computer vision-based estimation of invertebrate biomass

TL;DR

This paper introduces computer vision methods to estimate invertebrate biomass from images, enabling scalable, non-destructive biodiversity monitoring with high accuracy using novel predictors and deep learning models.

Contribution

It presents two innovative approaches—linear models with novel predictors and deep neural networks—for automatic invertebrate biomass estimation from images, without manual effort.

Findings

Median percentage error of 10-20% for individual biomass estimates

Effective use of area and sinking speed as predictors

Deep learning models outperform traditional methods

Abstract

The ability to estimate invertebrate biomass using only images could help scaling up quantitative biodiversity monitoring efforts. Computer vision-based methods have the potential to omit the manual, time-consuming, and destructive process of dry weighing specimens. We present two approaches for dry mass estimation that do not require additional manual effort apart from imaging the specimens: fitting a linear model with novel predictors, automatically calculated by an imaging device, and training a family of end-to-end deep neural networks for the task, using single-view, multi-view, and metadata-aware architectures. We propose using area and sinking speed as predictors. These can be calculated with BIODISCOVER, which is a dual-camera system that captures image sequences of specimens sinking in an ethanol column. For this study, we collected a large dataset of dry mass measurement and image sequence pairs to train and evaluate models. We show that our methods can estimate specimen dry mass even with complex and visually diverse specimen morphologies. Combined with automatic taxonomic classification, our approach is an accurate method for group-level dry mass estimation, with a median percentage error of 10-20% for individuals. We highlight the importance of choosing appropriate evaluation metrics, and encourage using both percentage errors and absolute errors as metrics, because they measure different properties. We also explore different optimization losses, data augmentation methods, and model architectures for training deep-learning models.