Özgüner Orhan, Hao Ran, Jackson Russell C, Shkurti Tom, Newman Wyatt, Çavuşoğlu M Cenk
Department of Electrical Engineering and Computer Science, Case Western Reserve University, Cleveland, OH.
IEEE Int Conf Robot Autom. 2018 May;2018:6617-6624. doi: 10.1109/icra.2018.8460867. Epub 2018 Sep 13.
This paper presents algorithms for three-dimensional tracking of surgical needles using the stereo endoscopic camera images obtained from the da Vinci Surgical Robotic System. The proposed method employs Bayesian state estimation, computer vision techniques, and robot kinematics. A virtual needle rendering procedure is implemented to create simulated images of the surgical needle under the da Vinci robot endoscope, which makes it possible to measure the similarity between the rendered needle image and the real needle. A particle filter algorithm using the mentioned techniques is then used for tracking the surgical needle. The performance of the tracking is experimentally evaluated using an actual da Vinci surgical robotic system and quantitatively validated in a ROS/Gazebo simulation thereof.
本文提出了利用从达芬奇手术机器人系统获得的立体内窥镜相机图像对手术针进行三维跟踪的算法。所提出的方法采用了贝叶斯状态估计、计算机视觉技术和机器人运动学。实施了一个虚拟针渲染程序，以创建达芬奇机器人内窥镜下手术针的模拟图像，这使得测量渲染的针图像与真实针之间的相似度成为可能。然后使用一种采用上述技术的粒子滤波算法来跟踪手术针。使用实际的达芬奇手术机器人系统对跟踪性能进行了实验评估，并在其ROS/Gazebo模拟中进行了定量验证。
