Automated Visual Monitoring of Nocturnal Insects with Light-based Camera Traps

TL;DR

This paper introduces datasets and a prototype system for automated visual monitoring of nocturnal insects, especially moths, using light-based camera traps, aiming to aid insect decline research.

Contribution

It provides two new datasets of nocturnal insects, including species annotations, and presents a prototype automated monitoring system with initial detection and classification baselines.

Findings

Two datasets of nocturnal insects with species annotations.

A prototype system for automated insect monitoring.

Initial detection and classification baselines established.

Abstract

Automatic camera-assisted monitoring of insects for abundance estimations is crucial to understand and counteract ongoing insect decline. In this paper, we present two datasets of nocturnal insects, especially moths as a subset of Lepidoptera, photographed in Central Europe. One of the datasets, the EU-Moths dataset, was captured manually by citizen scientists and contains species annotations for 200 different species and bounding box annotations for those. We used this dataset to develop and evaluate a two-stage pipeline for insect detection and moth species classification in previous work. We further introduce a prototype for an automated visual monitoring system. This prototype produced the second dataset consisting of more than 27,000 images captured on 95 nights. For evaluation and bootstrapping purposes, we annotated a subset of the images with bounding boxes enframing nocturnal insects. Finally, we present first detection and classification baselines for these datasets and encourage other scientists to use this publicly available data.