AMagPoseNet

Traditional magnetic tracking approaches based on mathematical models and optimization algorithms are computationally intensive, depend on initial guesses, and do not guarantee convergence to a global optimum. Although fully-supervised data-driven deep learning can solve the above issues, the demand for a comprehensive dataset hampers its applicability in magnetic tracking. Thus, we propose an annular magnet pose estimation network (called AMagPoseNet) based on dual-domain few-shot learning from a prior mathematical model, which consists of two sub-networks: PoseNet and CaliNet. PoseNet learns to estimate the magnet pose from the prior mathematical model, and CaliNet is designed to narrow the gap between the mathematical model domain (MMD) and the real-world domain (RWD). Experimental results reveal that AMagPoseNet outperforms the optimization-based method regarding localization accuracy (1.87±1.14 mm, 1.89±0.81°), robustness (non-dependence on initial guesses), and computational latency (2.08±0.02 ms). In addition, the six degrees of freedom (6-DoF) pose of the magnet could be estimated when discriminative magnetic field features are provided. With the assistance of the mathematical model, AMagPoseNet requires only a few real-world samples and has excellent performance, showing great potential for practical biomedical and industrial applications.

传统的基于数学模型和优化算法的磁性追踪方法，计算量大，依赖于初始猜测，且无法确保收敛至全局最优解。尽管完全监督的数据驱动深度学习可以解决上述问题，但对于全面数据集的需求阻碍了其在磁性追踪中的应用。因此，我们提出了一种基于先验数学模型的双域少样本学习的环状磁体姿态估计网络（称为AMagPoseNet），该网络由两个子网络组成：PoseNet和CaliNet。PoseNet学习从先验数学模型中估计磁体的姿态，而CaliNet旨在缩小数学模型域（MMD）与现实世界域（RWD）之间的差距。实验结果表明，AMagPoseNet在定位精度（1.87±1.14毫米，1.89±0.81度）、鲁棒性（不依赖于初始猜测）和计算延迟（2.08±0.02毫秒）方面优于基于优化的方法。此外，当提供具有区分性的磁场特征时，可以估计磁体的六自由度（6-DoF）姿态。在数学模型的辅助下，AMagPoseNet仅需少量现实世界样本，并表现出卓越的性能，显示出在生物医学和工业应用中的巨大潜力。