Abstract
Understanding and monitoring wildlife behaviour is crucial in ecology and biomechanics, yet challenging due to the limitations of current methods. To address this issue, we introduce two motion capture system specifically tailored for free-ranging wildlife observation. These systems combine multiple sensors from low-cost cameras to a solid-state LiDAR to capture both 2D videos and 3D point cloud data, thereby allowing researchers to observe high-fidelity animal morphometrics, behaviour and interactions in a completely remote manner. Field trials conducted in Kgalagadi Transfrontier Park have successfully demonstrated the ability to quantify morphological features of different species, accurately track the 3D movements of a springbok herd over time and observe the respiratory patterns of a distant lion. By using machine learning-based methods in the post-processing, our method marks a significant leap forward in ecological and biomechanical studies, offering new possibilities for conservation efforts and animal welfare, and enriching the prospects for interdisciplinary research.
Speaker Bio
As a PhD student in Electrical Engineering at the University of Cape Town, I specialize in computer vision and machine learning. My work, published in several international conferences and journals, aims to deepen our understanding of animal motion through the development of innovative measurement systems. By integrating technological advancements with ecological insights, my research offers novel perspectives on animal biomechanics.