Medical robotics and computer-assisted surgery are hotspots in the field of robotics and medicine, changing the essence of traditional surgery using a combination of robotic, image processing, and computer technologies. The present paper aimed to study the auxiliary puncture procedure using a robot based on binocular vision optical positioning technology that can be used in minimally invasive surgery for coordinate precision of skin markers. ZED binocular cameras were selected for image acquisition and a model was established based on Zhang's calibration. Moreover, a Hough circle detection algorithm was proposed for binocular stereo image feature extraction to obtain the marker points in three-dimensional space coordinates. Accurate marker coordinate information for a human 3D bone model was obtained, laying the foundation for further research regarding robot-assisted precise positioning technology for use in puncture surgery.