# Using Deep Learning to Count Albatrosses from Space

## TL;DR

This study demonstrates that deep learning, specifically a U-Net model with Focal Loss, can effectively count Wandering Albatrosses in satellite images, achieving accuracy comparable to human observers and aiding conservation efforts.

## Contribution

The paper introduces a novel application of deep learning for automatic bird counting in satellite imagery, addressing class imbalance and validating performance against human labels.

## Key findings

- Achieved approximately 80% precision and recall in bird detection.
- Model accuracy is comparable to inter-observer variability.
- Method enables more efficient monitoring of conservation-sensitive species.

## Abstract

In this paper we test the use of a deep learning approach to automatically count Wandering Albatrosses in Very High Resolution (VHR) satellite imagery. We use a dataset of manually labelled imagery provided by the British Antarctic Survey to train and develop our methods. We employ a U-Net architecture, designed for image segmentation, to simultaneously classify and localise potential albatrosses. We aid training with the use of the Focal Loss criterion, to deal with extreme class imbalance in the dataset. Initial results achieve peak precision and recall values of approximately 80%. Finally we assess the model's performance in relation to inter-observer variation, by comparing errors against an image labelled by multiple observers. We conclude model accuracy falls within the range of human counters. We hope that the methods will streamline the analysis of VHR satellite images, enabling more frequent monitoring of a species which is of high conservation concern.