Tracking and triangulating firefly flashes in field recordings

TL;DR

This paper introduces a neural network-based method for accurately identifying firefly flashes in natural videos, enabling reliable 3D reconstruction of flashes without calibration, advancing ecological monitoring techniques.

Contribution

The paper provides a new dataset and trained neural networks for firefly flash classification, improving accuracy over traditional intensity thresholding methods and enabling calibration-free 3D tracking.

Findings

Neural network outperforms traditional thresholding in flash detection

Provides a new dataset of labeled firefly images

Enables calibration-free 3D flash reconstruction

Abstract

Identifying firefly flashes from other bright features in nature images is complicated. I provide a training dataset and trained neural networks for reliable flash classification. The training set consists of thousands of cropped images (patches) extracted by manual labeling from video recordings of fireflies in their natural habitat. The trained network appears as considerably more reliable to differentiate flashes from other sources of light compared to traditional methods relying solely on intensity thresholding. This robust tracking enables a new calibration-free method for the 3D reconstruction of flash occurrences from stereoscopic 360-degree videos, which I also present here.