The Intergration of KCF-based Object Tracking and Gesture Recognition for Computer-assisted Surgery System
文献类型：会议论文
| 作者 | Yang, Zhi1; Zhao, Shuying1; Hua CS(华春生)2,3 |
| 出版日期 | 2019 |
| 会议日期 | September 28-30, 2019 |
| 会议地点 | Dalian, China |
| 关键词 | CAS optical surgical navigation KCF touchless hand input |
| 页码 | 113-116 |
| 英文摘要 | In recent years, Computer-assisted Surgery (CAS) has allowed a significant increase in accuracy improvement and minimally invasive surgery in a large number of high risk surgical procedures. Nevertheless, to our knowledge, the existing CAS system still has many shortcomings in navigation system and diagnosis system. Video-optical based navigation system becomes popular because it provides a higher precision and a larger working space but weak to interference such as occlusion and reflection; in quite a few cases, doctors often choose intraoperative diagnosis, how to shorten the precious time spent in the diagnosis of surgery is an important direction. In this paper, a novel optical CAS system is proposed, which consists of two parts, one is scalpel navigation based on Kernelized Correlation Filters (KCF) multi-target tracking algorithm, and the other is a touchless hand gesture input based method to help intraoperative diagnosis. Scalpel navigation uses the fm810 camera to determine the three-dimensional position of the scalpel and display it through a computer graphics method. Unlike traditional ultrasound-based systems, our systems use optical navigation for higher accuracy and greater operating range, using KCF target tracking algorithms to overcome occlusion and other effects. By applying the KCF tracker to the RGB image to obtain the pixel coordinates, and then using the aligned depth map to calculate the 3-dimensional coordinates, the system can realize the positioning of the scalpel and display the 3d model using the OpenGL and OpenMesh libraries. Afterward, an interactive method based on contactless gesture input is proposed for intraoperative diagnosis. Unlike most systems that attach importance to gesture recognition today, we start with surgical tasks and focus on the positioning accuracy of gestures on the screen. The experimental results demonstrate our computer-assisted surgery system can meet the accurate, stable and real-time requirements of scalpel tracking and gesture input. It is hoped that this paper will inspire more research on CAS tasks. |
| 源文献作者 | Institute of Electrical and Electronics Engineers Inc. |
| 产权排序 | 2 |
| 会议录 | 2019 2nd International Conference on Information Systems and Computer Aided Education, ICISCAE 2019
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISBN号 | 978-1-7281-3066-8 |
| 源URL | [http://ir.sia.cn/handle/173321/26867]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Yang, Zhi |
| 作者单位 | 1.College of Information Science and Engineering, Shenyang, Northeastern University, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China |
| 推荐引用方式 GB/T 7714 | Yang, Zhi,Zhao, Shuying,Hua CS. The Intergration of KCF-based Object Tracking and Gesture Recognition for Computer-assisted Surgery System[C]. 见:. Dalian, China. September 28-30, 2019. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。