Artificial intelligence for automated detection of large mammals creates path to upscale drone surveys

• Published in: Scientific reports 2023-01, Vol.13 (1), p.947-13, Article 947
• Main Authors: Lenzi, Javier, Barnas, Andrew F., ElSaid, Abdelrahman A., Desell, Travis, Rockwell, Robert F., Ellis-Felege, Susan N.
• Format: Article
• Language: English
• Subjects: 631/114; 631/114/2397; 631/158; 631/601; 639/166; 704/158; Animals; Artificial Intelligence; Automation; Cattle; Humanities and Social Sciences; Mammals; multidisciplinary; Neural networks; Neural Networks, Computer; Photogrammetry; Rangifer tarandus; Reindeer; Science; Science (multidisciplinary); Software; Surveys; Unmanned Aerial Devices; Wildlife
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-28240-9

Imagery from drones is becoming common in wildlife research and management, but processing data efficiently remains a challenge. We developed a methodology for training a convolutional neural network model on large-scale mosaic imagery to detect and count caribou ( Rangifer tarandus ), compare model performance with an experienced observer and a group of naïve observers, and discuss the use of aerial imagery and automated methods for large mammal surveys. Combining images taken at 75 m and 120 m above ground level, a faster region-based convolutional neural network (Faster-RCNN) model was trained in using annotated imagery with the labels: “ adult caribou ”, “ calf caribou ”, and “ ghost caribou ” (animals moving between images, producing blurring individuals during the photogrammetry processing). Accuracy, precision, and recall of the model were 80%, 90%, and 88%, respectively. Detections between the model and experienced observer were highly correlated (Pearson: 0.96–0.99, P value