Correction: Fudala, K. and Bialik, R.J. Breeding Colony Dynamics of Southern Elephant Seals at Patelnia Point, King George Island, Antarctica. Remote Sensing 2020, 12, 2964

Fudala, Katarzyna; Bialik, Robert J.

doi:10.3390/rs12223727

Cited by 1 publication

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to known colonies, our study also shows that RPAS are useful tools to detect new colonies of seabirds. The global population size of the Antarctic shag is estimated to be approximately 12,191 breeding pairs nesting in c. 175 breeding colonies (Fudala and Bialik, 2023) that are often located on rocky slopes (Harrison et al, 2021, Oosthuizen et al, 2020. The need for an evaluation of the status of the population was highlighted by Schrimpf et al (2018); since then, two new colonies have been inventoried at Ryder Bay (Phillips et al 2019) and at Cape Melville (Fudala and Bialik, 2023).…”

Section: Discussionmentioning

confidence: 99%

Using machine learning to count Antarctic shag (Leucocarbo bransfieldensis) nests on images captured by Remotely Piloted Aircraft Systems

Cusick,

Fudala,

Storożenko

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Using 51 orthomosaics of 11 breeding locations of the Antarctic shag, we propose a method for automating counting of shag nests. This is achieved by training an object detection model based on the YOLO architecture and identifying nests on sections of the orthomosaic, which are later combined with predictions for the entire orthomosaic. Our results show that the current use of Remotely Piloted Aircraft Systems (RPAS) to collect images of areas with shag colonies, combined with machine learning algorithms, can provide reliable and fast estimates of shag nest counts (F1 score > 0.95). By using data from only two shag colonies for training, we show that models can be obtained that generalise well to images of both spatially and temporally distinct colonies. The proposed practical application opens the possibility of using aerial imagery to perform large-scale surveys of Antarctic islands in search of undiscovered shag colonies. We discuss the conditions for optimal performance of the model as well as its limitations. The code, data and trained model allowing for full reproducibility of the results are available athttps://github.com/Appsilon/Antarctic-nests.

show abstract