3D Human Pose Estimation and Temporal Kinematic Constraints for Dynamic Occlusion in Basketball
American Journal of Artificial Intelligence and Neural Networks · 28.02.2026 · 7 (1) · 81-94
DOI: 10.71465/ajainn3589 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Artificial Intelligence and Neural Networks, online erschienen am 28.02.2026. Verfasst von James Anderson und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The accurate estimation of three-dimensional human poses in dynamic, multi-agent sports environments remains a significant challenge in computer vision. Basketball, characterized by rapid player movements, frequent inter-player contact, and severe dynamic occlusion, presents a uniquely difficult scenario for standard pose estimation frameworks. This paper introduces a novel methodology that integrates temporal kinematic constraints with deep learning-based pose estimation to mitigate the degradation of accuracy during occlusion events. By modeling the biomechanical limitations of human joint articulation and imposing temporal consistency across video frames, our approach reconstructs missing or noisy keypoint data with high fidelity. We employ a two-stage architecture that first lifts two-dimensional detections to a threedimensional space and subsequently refines these estimates using a temporal optimization modulegroundedinNewtonianmechanics.Experimental results on varying basketball datasets demonstrate that this method significantly reduces the Mean Per Joint Position Error (MPJPE) compared to state-of-the-art baseline methods,particularly in scenarios involving heavy defensive congestion. The integration of kinematic velocity and acceleration constraints ensures that the generated poses are not only visually plausible but physically valid.
Zitieren
APA
Anderson, J., & Miller, R. (2026). 3D Human Pose Estimation and Temporal Kinematic Constraints for Dynamic Occlusion in Basketball. American Journal of Artificial Intelligence and Neural Networks, 7(1), 81-94. https://doi.org/10.71465/ajainn3589
Vancouver
Anderson J, Miller R. 3D Human Pose Estimation and Temporal Kinematic Constraints for Dynamic Occlusion in Basketball. American Journal of Artificial Intelligence and Neural Networks. 2026;7(1):81-94. doi:10.71465/ajainn3589
BibTeX
@article{Anderson2026,
author = {Anderson, James and Miller, Robert},
title = {3D Human Pose Estimation and Temporal Kinematic Constraints for Dynamic Occlusion in Basketball},
journal = {American Journal of Artificial Intelligence and Neural Networks},
year = {2026},
volume = {7},
number = {1},
pages = {81--94},
doi = {10.71465/ajainn3589}
}
EUVIMED