21 000 birds in 4.5 h: efficient large‐scale seabird detection with machine learning

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.

Perspectives in machine learning for wildlife conservation

“…Recent studies have shown the promise of UAVs and deep learning for posture tracking [74][75][76] , semi-automatic detection of large mammals 42,77 , birds 78 , and, in low-altitude flight, even identification of individuals 79 . Drones are agile platforms that can be deployed rapidly-theoretically on demand-and with limited cost.…”

“…As an example, large mammal detection in the Kuzikus reserve in 2014 was improved significantly by improving the detection methodologies, from a recall rate of 20% 35 to 80% 37 (for a common 75% precision rate). Finally, studies involving human operators demonstrated that ML enabled massive speedups in complex tasks such as individual and species recognition 38,39 and large-scale tasks such as animal detection in drone surveys 40 . Recent advances in ML methodology could accelerate and enhance various stages of the traditional ecological research pipeline (see Fig.…”

Automatic analysis of digital aerial surveys : a roadmap for the short, medium and long term

“…Alternatively, one can attempt to process the entire image using a deep network and try to predict the density of animals or probability of finding animals within subregions of the image. This approach was taken by Kellenberger et al (2021) where they predict probability maps for seabirds within input images using a variant of the ResNet architecture. These maps are then processed to localize individual seabirds within the image.…”

Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images

“…Nowadays, aerial surveys are among the standard non-invasive approaches for tracking the marine mega fauna [6][7][8][9][10]. Those surveys consist of flight sessions over the…”

“…Obtaining models which 102 are robust to such kind of noise is one of the most difficult challenges in marine 103 animal detection. Due to the complexity of detecting marine animals in those various scenarios, 105 research studies in the literature often limit their scope to the detection of a single animal 106 species [7,9] and/or to images with high density of animal instances [8,10]. For instance, 107 in the early work of [7], the authors tackle the detection of dugongs in aerial images 108 by combining an unsupervised region proposal method with a classification CNN.…”