The optical tracking system (OTS) plays a vital role in the computer-assisted surgical navigation process, whereas the performance of the commonly used binocular stereo vision is affected by the line-of-sight problem and limited workspace. Thus, this article proposed a prior knowledge-based multicamera reconstruction model (PKRM) to both expand the tracking workspace and improve the tracking robust and computational efficiency of OTS when working in unstructured clinical conditions. This reconstruction model inherits the advantages of the geometrical method, data-driven method, and gating technique (GT). First, we added the geometric principle as the prior knowledge to optimize the training of the multicamera OTS reconstruction model through the Lagrange multiplier method; hence, the prior knowledge feedforward NN (PKFNN) was built. Second, besides the training features, the state of camera (SOC) was extracted in advance to determine the NN structure using GT. According to the SOC feature, the OTS can be self-adaptive to the changing field of view (FOV) caused by optical occlusion, which is frequently occurred in surgery. Furthermore, experiments were carried out to verify the performance of the proposed model, whose accuracy and runtime performed 0.4627 mm and 0.0016 ms, respectively. Results demonstrate that the proposed reconstruction model can achieve higher accuracy and computational efficiency than both the geometrical model and the data-driven model. Especially, by considering SOC as the state prior knowledge, the tracking robustness is enhanced when one or two of the four cameras are not working properly. Note to Practitioners—The original motivation for this article derives from both the line-of-sight limitation and robust demand for optical tracking of surgical instruments. The performance of the multicamera optical tracking system (OTS) depends on its reconstruction model. However, the geometric reconstruction model requires more calculation to obtain high accuracy, which will enlarge the latency and reduce the update rate. In our previous work, the reconstruction model based on the neural network (NN) has achieved accurate tracking in real-time, while the training of the model tends into local optimal values. Hence, we proposed the prior knowledge feedforward NN model to improve the accuracy and computational efficiency. Moreover, to guarantee the line-of-sight in the optical occlusion, the state of camera combining with the gating technique enables the OTS to be self-adaptive for changing the field of view, which greatly ensures the robust tracking process with larger workspace in case of line-of-sight obstructions.

中文翻译：

---

基于先验知识的多相机光学跟踪系统重构模型优化方法


光学跟踪系统（OTS）在计算机辅助手术导航过程中起着至关重要的作用，而常用的双目立体视觉的性能受到视线问题和有限工作空间的影响。因此，本文提出了一种基于先验知识的多相机重建模型（PKRM），以扩大跟踪工作空间并提高 OTS 在非结构化临床条件下工作时的跟踪鲁棒性和计算效率。该重建模型继承了几何方法、数据驱动方法和门控技术（GT）的优点。首先，加入几何原理作为先验知识，通过拉格朗日乘数法优化多摄像机OTS重建模型的训练；因此，建立了先验知识前馈神经网络（PKFNN）。其次，除了训练特征外，还预先提取相机状态（SOC），以确定使用 GT 的 NN 结构。根据SOC的特点，OTS可以自适应手术中经常发生的光学遮挡引起的视场（FOV）变化。此外，还进行了实验来验证所提出模型的性能，其精度和运行时间分别为0.4627 mm和0.0016 ms。结果表明，所提出的重建模型比几何模型和数据驱动模型能够实现更高的精度和计算效率。特别是，通过将SOC视为状态先验知识，当四个摄像头中的一个或两个无法正常工作时，跟踪鲁棒性得到增强。 从业者须知——本文的最初动机源于视线限制和对手术器械光学跟踪的强劲需求。多相机光学跟踪系统（OTS）的性能取决于其重建模型。然而，几何重建模型需要更多的计算才能获得高精度，这会增大延迟并降低更新率。在我们前期的工作中，基于神经网络（NN）的重建模型实现了实时精确跟踪，同时模型的训练趋于局部最优值。因此，我们提出了先验知识前馈神经网络模型来提高精度和计算效率。此外，为了保证光学遮挡下的视线，相机的状态结合门控技术使OTS能够自适应改变视野，这极大地保证了在更大工作空间下的鲁棒跟踪过程。视线障碍物的情况。