Surgical registration that maps surgical space onto image space plays an important role in surgical navigation. Accurate surgical registration can help surgeons efficiently locate surgical instruments. The complicated marker-based surgical registration method is highly accurate, but it is time-consuming. Therefore, a marker-less surgical registration method with high-precision and high-efficiency is proposed without human intervention. Firstly, the surgical navigation system based on the multi-vision system is calibrated by using a specially-designed calibration board. When extracting the abdominal point cloud acquired by the structured light vision system, the constraint is constructed by using Computed Tomography (CT) image to filter out the points in irrelevant areas to improve the computational efficiency. The Coherent Point Drift (CPD) algorithm based on Gaussian Mixture Model (GMM) is applied in the registration of abdominal point cloud with lack of surface features. To enhance the efficiency of the CPD algorithm, firstly, the system calibration result is used in rough registration of the point cloud, and then the proper point cloud pretreatment method and its parameters are studied through experiments. Finally, the puncturing simulation experiments were carried out by using the abdominal phantom. The experimental results show that the proposed surgical registration method has high accuracy and efficiency, and has potential clinical application value.

将手术空间映射到图像空间的手术配准在手术导航中起着重要作用。准确的手术配准可以帮助外科医生有效地定位手术器械。复杂的基于标记的手术配准方法准确度很高，但很耗时。因此，提出了一种无需人工干预、高精度、高效率的无标记手术配准方法。首先，使用专门设计的校准板对基于多视觉系统的手术导航系统进行校准。在提取结构光视觉系统获取的腹部点云时，利用计算机断层扫描（CT）图像构造约束，过滤掉不相关区域的点，提高计算效率。将基于高斯混合模型（GMM）的相干点漂移（CPD）算法应用于缺乏表面特征的腹部点云配准。为提高CPD算法的效率，首先将系统标定结果用于点云的粗配准，然后通过实验研究合适的点云预处理方法及其参数。最后，利用腹部体模进行穿刺模拟实验。实验结果表明，所提出的手术配准方法具有较高的准确率和效率，具有潜在的临床应用价值。将系统标定结果用于点云的粗配准，然后通过实验研究合适的点云预处理方法及其参数。最后，利用腹部体模进行穿刺模拟实验。实验结果表明，所提出的手术配准方法具有较高的准确性和效率，具有潜在的临床应用价值。将系统标定结果用于点云的粗配准，然后通过实验研究合适的点云预处理方法及其参数。最后，利用腹部体模进行穿刺模拟实验。实验结果表明，所提出的手术配准方法具有较高的准确性和效率，具有潜在的临床应用价值。