21 000 birds in 4.5 h: efficient large‐scale seabird detection with machine learning. Issue 3 (25th March 2021)

• Record Type: Journal Article
• Authors: Kellenberger, Benjamin; Veen, Thor; Folmer, Eelke; Tuia, Devis
• Editors: Horning, Ned; Scales, Kylie
• Is Part Of: Remote sensing in ecology and conservation. Volume 7:Issue 3(2021)
• Page Start: 445
• Page End: 460
• Publication Date: 2021-03-25
• Subjects: coastal birds -- convolutional neural network -- deep learning -- remote sensing -- unmanned aerial vehicle -- wildlife census; Remote sensing -- Periodicals; Ecology -- Research -- Periodicals; Ecology -- Methodology -- Periodicals; Ecology -- Remote sensing -- Periodicals; Nature conservation -- Methodology -- Periodicals; 577.0723
• DOI: 10.1002/rse2.200
• Languages: English
• ISSNs: 2056-3485

Abstract

Abstract: We address the task of automatically detecting and counting seabirds in unmanned aerial vehicle (UAV) imagery using deep convolutional neural networks (CNNs). Our study area, the coast of West Africa, harbours significant breeding colonies of terns and gulls, which as top predators in the food web function as important bioindicators for the health of the marine ecosystem. Surveys to estimate breeding numbers have hitherto been carried out on foot, which is tedious, imprecise and causes disturbance. By using UAVs and CNNs that allow localizing tens of thousands of birds automatically, we show that all three limitations can be addressed elegantly. As we employ a lightweight CNN architecture and incorporate prior knowledge about the spatial distribution of birds within the colonies, we were able to reduce the number of bird annotations required for CNN training to just 200 examples per class. Our model obtains good accuracy for the most abundant species of royal terns (90% precision at 90% recall), but is less accurate for the rarer Caspian terns and gull species (60% precision at 68% recall, respectively 20% precision at 88% recall), which amounts to around 7% of all individuals present. In sum, our results show that we can detect and classify the majority of 21 000 birds in just 4.5 h, start to finish, as opposed to about 3 weeks of tediously identifying and labelling all birds by hand. Abstract : We propose a deep learning‐based pipeline to detect high‐density coastal seabird colonies in UAV imagery. In our work, we work towards reducing the tedium of manually annotating the tens of thousands of birds present in such colonies, by incorporating a lightweight, deep learning‐based model architecture, flexible annotation scheme, and prior knowledge through a Markov random field. Experiments show that our model can detect 21 000 birds in just 4.5 h, from image annotation to the final result, while only requiring 30 min of manual annotation time.