AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild
This dataset addresses a problem for researchers in ecology, neuroscience, robotics, biomechanics, and computer vision by enabling the study of animal agility, though it is incremental as it builds on existing markerless pose estimation methods.
The authors tackled the challenge of quantifying whole-body 3D kinematic data for cheetahs in the wild by presenting AcinoSet, a dataset with 119,490 frames of multi-view video and 7,588 human-annotated frames, and provided baseline models for 3D pose estimation.
Animals are capable of extreme agility, yet understanding their complex dynamics, which have ecological, biomechanical and evolutionary implications, remains challenging. Being able to study this incredible agility will be critical for the development of next-generation autonomous legged robots. In particular, the cheetah (acinonyx jubatus) is supremely fast and maneuverable, yet quantifying its whole-body 3D kinematic data during locomotion in the wild remains a challenge, even with new deep learning-based methods. In this work we present an extensive dataset of free-running cheetahs in the wild, called AcinoSet, that contains 119,490 frames of multi-view synchronized high-speed video footage, camera calibration files and 7,588 human-annotated frames. We utilize markerless animal pose estimation to provide 2D keypoints. Then, we use three methods that serve as strong baselines for 3D pose estimation tool development: traditional sparse bundle adjustment, an Extended Kalman Filter, and a trajectory optimization-based method we call Full Trajectory Estimation. The resulting 3D trajectories, human-checked 3D ground truth, and an interactive tool to inspect the data is also provided. We believe this dataset will be useful for a diverse range of fields such as ecology, neuroscience, robotics, biomechanics as well as computer vision.