Vanyi Chao Ankhzaya Jamsrandorj Yin May Oo Mun, Kyung-Ryoul Kim, Jin wook 2024-01-12T02:44:41Z 2024-01-12T02:44:41Z 2023-11-28 2023-10-17 https://pubs.kist.re.kr/handle/201004/76361 https://ieeexplore.ieee.org/document/10312079 3D ball location in sports can be advantageous and has many applications such as automatic scoring system, ball trajectory highlight and offside detection system for football game. Currently, this task can be solved through the use of costly multi-view approaches or the legacy physics-based methods that require complicated setups and human intervention. In this paper, we propose a method to reconstruct the 3D ball trajectory of the basketball projectile shot by using only a single view. The method relies on accurate camera calibration and 2D ball detection of sequence images. Extra information in the 3D world also plays an important role in improving the 3D reconstruction. The experimental result illustrates the accurately reconstructed 3D trajectory when enough information is given. IEEE Industrial Electronics Society 3D Ball Trajectory Reconstruction of a Ballistic Shot from a Monocular Basketball Video Conference 10.1109/IECON51785.2023.10312079 1 IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society SI Singapore, Singapore 2023-10-16 Proceedings of IECON 2023