Version 1
: Received: 23 January 2024 / Approved: 23 January 2024 / Online: 23 January 2024 (08:40:08 CET)
How to cite:
Choi, J.; Ha, E.; Kim, J. Comparative and Improvement Study of 3D Human Pose Estimation Algorithms using Monocular Cameras. Preprints2024, 2024011668. https://doi.org/10.20944/preprints202401.1668.v1
Choi, J.; Ha, E.; Kim, J. Comparative and Improvement Study of 3D Human Pose Estimation Algorithms using Monocular Cameras. Preprints 2024, 2024011668. https://doi.org/10.20944/preprints202401.1668.v1
Choi, J.; Ha, E.; Kim, J. Comparative and Improvement Study of 3D Human Pose Estimation Algorithms using Monocular Cameras. Preprints2024, 2024011668. https://doi.org/10.20944/preprints202401.1668.v1
APA Style
Choi, J., Ha, E., & Kim, J. (2024). Comparative and Improvement Study of 3D Human Pose Estimation Algorithms using Monocular Cameras. Preprints. https://doi.org/10.20944/preprints202401.1668.v1
Chicago/Turabian Style
Choi, J., Eunju Ha and Jong-Wook Kim. 2024 "Comparative and Improvement Study of 3D Human Pose Estimation Algorithms using Monocular Cameras" Preprints. https://doi.org/10.20944/preprints202401.1668.v1
Abstract
Human Pose Estimation (HPE) is a technique in computer vision and AI for detecting and tracking human body parts and poses from images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods using monocular cameras are highly versatile due to their applicability in standard video and CCTV footage. These methods have evolved from 2D to 3D pose estimation. However, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges such as limited training data, depth perception ambiguity, left/right switching, and issues with occlusions when applied in real-world environments. This study compares two representative 3D HPE methods by assessing their strengths and weaknesses with real-world videos. Then, we propose data processing techniques to eliminate and correct anomalies like left/right inversion and false detections of joint positions in daily life motions. Finally, we obtain joint angle trajectories using an optimization method based on a 3D humanoid simulator, taking as input the joint coordinate data corrected by applying the proposed human joint data processing technique. The efficacy of the proposed 3D HPE method is verified by applying it to three-dimensional freehand gymnastics exercises and comparing the joint angle trajectories during the motion.
Keywords
human pose estimation; monocular camera; MediaPipe Pose; HybrIK; outlier; optimization; humanoid model
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
