Whole-Herd Elephant Pose Estimation from Drone Data for Collective Behavior Analysis
Abstract: This research represents a pioneering application of automated pose estimation from drone data to study elephant behavior in the wild, utilizing video footage captured from Samburu National Reserve, Kenya. The study evaluates two pose estimation workflows: DeepLabCut, known for its application in laboratory settings and emerging wildlife fieldwork, and YOLO-NAS-Pose, a newly released pose estimation model not previously applied to wildlife behavioral studies. These models are trained to analyze elephant herd behavior, focusing on low-resolution ($\sim$50 pixels) subjects to detect key points such as the head, spine, and ears of multiple elephants within a frame. Both workflows demonstrated acceptable quality of pose estimation on the test set, facilitating the automated detection of basic behaviors crucial for studying elephant herd dynamics. For the metrics selected for pose estimation evaluation on the test set -- root mean square error (RMSE), percentage of correct keypoints (PCK), and object keypoint similarity (OKS) -- the YOLO-NAS-Pose workflow outperformed DeepLabCut. Additionally, YOLO-NAS-Pose exceeded DeepLabCut in object detection evaluation. This approach introduces a novel method for wildlife behavioral research, including the burgeoning field of wildlife drone monitoring, with significant implications for wildlife conservation.
- The ties that bind: genetic relatedness predicts the fission and fusion of social groups in wild african elephants. Proceedings of the Royal Society B: Biological Sciences, 273(1586):513–522, 2006.
- Efficient Pipeline for Camera Trap Image Review, 2019a.
- Efficient pipeline for camera trap image review. CoRR, abs/1907.06772, 2019b.
- Terrestrial mammalian wildlife responses to unmanned aerial systems approaches. Scientific reports, 9(1):2142, 2019.
- The pascal visual object classes (voc) challenge. International journal of computer vision, 88:303–338, 2010.
- Multi-person pose estimation using an orientation and occlusion aware deep learning network. Sensors, 20(6):1593, 2020.
- First guidelines and suggested best protocol for surveying african elephants (loxodonta africana) using a drone. koedoe, 63(1):1–9, 2021.
- ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation, 2022.
- Quantifying the movement, behaviour and environmental context of group-living animals using drones and computer vision. J. Anim. Ecol., 92(7):1357–1371, 2023.
- Human vs. machine: Detecting wildlife in camera trap images. Ecological Informatics, 72:101876, 2022.
- DeepLabCut: markerless pose estimation of user-defined body parts with deep learning. Nat. Neurosci., 21(9):1281–1289, 2018.
- Deep learning tools for the measurement of animal behavior in neuroscience. Curr. Opin. Neurobiol., 60:1–11, 2020.
- Terrestrial megafauna response to drone noise levels in ex situ areas. Drones, 6(11):333, 2022.
- Benchmarking and error diagnosis in multi-instance pose estimation. In Proceedings of the IEEE international conference on computer vision, pages 369–378, 2017.
- A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Machine Learning and Knowledge Extraction, 5(4):1680–1716, 2023.
- Deep cosine metric learning for person re-identification. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 748–756. IEEE, 2018.
- Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), pages 3645–3649. IEEE, 2017.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.