Computer vision-based estimation of invertebrate biomass
🤖 AI Summary
Traditional dry-weight measurements of invertebrates are labor-intensive, time-consuming, and destructive, posing significant limitations for large-scale biodiversity monitoring. This study proposes a non-destructive, high-throughput method for estimating individual dry weight by leveraging a custom dual-camera system, BIODISCOVER, to automatically capture image sequences of specimens settling in ethanol. For the first time, settling velocity and projected area are employed as key predictors in both a linear model and a deep neural network that fuses multi-view metadata. The approach achieves median percentage errors of 10–20% across morphologically diverse invertebrate taxa and enables accurate biomass estimation at the taxonomic group level when integrated with automated classification. The work further underscores the necessity of jointly evaluating model performance using both absolute and relative error metrics.
Application Category
📝 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.
Problem
Research questions and friction points this paper is trying to address.
invertebrate biomass
dry mass estimation
computer vision
biodiversity monitoring
image-based estimation
Innovation
Methods, ideas, or system contributions that make the work stand out.
computer vision
biomass estimation
deep learning
sinking speed
BIODISCOVER
🔎 Similar Papers
No similar papers found.
