<acronym id="2gwac"><center id="2gwac"></center></acronym>
<acronym id="2gwac"><center id="2gwac"></center></acronym>
華中科技大學學報(自然科學版) 2020, Vol. 48 Issue (10): 14-19 DOI10.13245/j.hust.201003

欄目:控制與信息工程
磁控雙半球膠囊機器人姿態的圖像檢測方法
張永順 , 王智博 , 劉 旭 , 楊慧遠
大連理工大學精密與特種加工教育部重點實驗室 大連 116024
摘要 提出一種雙半球膠囊機器人軸線方位的姿態檢測方法.以空間萬向旋轉磁矢量誤差模型所確定最小誤差方位為雙半球膠囊機器人的初始圖像標定位置,對初始位置膠囊自轉角信息進行校正.通過內嵌相機獲得膠囊初始位置與調姿后的胃腸內壁圖像,對這兩幅圖像進行特征點識別與匹配,并結合對極幾何約束,最終獲得胃腸道等寬裕環境內雙半球膠囊機器人軸線方位.設計了模擬實驗平臺,在體外豬大腸內進行試驗驗證了該方法的可行性,并且在雙半球膠囊實際工作狀態下進行試驗,確定了該方法在機器人姿態檢測上的實用性.
關鍵詞 雙半球膠囊機器人 ;姿態估計 ;空間萬向旋轉磁矢量 ;特征識別和匹配 ;對極幾何
Image detection method for posture of magnetically controlled dual hemisphere capsule robot
ZHANG Yongshun , WANG Zhibo , LIU Xu , YANG Huiyuan
Key Laboratory for Precision and Non-traditional Machining of Ministry of Education,Dalian University of Technology,Dalian 116024,Liaoning China
Abstract A posture detection method for the axis orientation of the dual hemisphere capsule robot (DHCR) was proposed.The minimum error orientation was as the initial image calibration position of the DHCR,which was determined by the spatial universal rotating magnetic vector error model,and the capsule rotation angle information of the initial position was corrected.The images of gastrointestinal inner wall of initial calibration and posture adjustment were obtained by the embedded camera,and feature points of these two images were identified and matched.The epipolar geometric constraints were combined, and finally the axis orientation of the DHCR in the gastrointestinal tract and other ample environment was obtained.A simulation experiment platform was designed and tested in the vitro pig large intestine to verify the feasibility of the method,and the experiment was carried out in the actual working state of the DHCR.The practicability of the method on the robot was determined.
Keywords dual hemispherical capsule robot ; posture estimation ; spatial universal rotating magnetic vector ; feature recognition and matching ; epipolar geometry
基金資助國家自然科學基金資助項目(61773084)

中圖分類號TP242.6
文獻標志碼A
文章編號1671-4512(2020)10-0014-06
參考文獻
[1] THAN T D,ALICI G,ZHOU H,et al.A review of localization systems for robotic endoscopic capsules[J].IEEE Transactions on Biomedical Engineering,2012,59(9):2387-2399.
[2] LIEN G S,LIU C W,JIANG J A,et al.Magnetic control system targeted for capsule endoscopic operations in the stomach—design,fabrication,and in vitro and ex vivo evaluations[J].IEEE Transactions on Biomedical Engin- eering,2012,59(7):2068-2079.
[3] 張永順,周華濤,張林霞,等.一種新型雙半球形膠囊機器人[J].機械工程學報.2017,53(15):110-118.
[4] 胡超,蔡振宇,尤曉赫,等.基于膠囊內窺鏡圖像的腸胃道三維重建技術[J].傳感技術學報,2017(5):708-714.
[5] NATALI D C,BECCANI M,VALDASTRI P.Real-time pose detection for magnetic medical devices[J].IEEE Transactions on Magnetics,2013,49(7):3524-3527.
[6] SONG S,QIU X,WANG J,et al.Real-time tracking and navigation for magnetically manipulated untethered robot [J].IEEE Access,2016,4:7104-7110.
[7] XU J.Research on sensors arrangement for capsule endoscope microrobot magnetic localization[C]// Proc of 2013 25th Chinese Control and Decision Conference.Guiyang:IEEE,2013:5208-5211.
[8] SPYROU E,IAKOVIDIS D K,NIAFAS S,et al.Comparative assessment of feature extraction methods for visual odometry in wireless capsule endoscopy[J].Computers in Biology & Medicine,2015,65:297-307.
[9] SPYROU E,IAKOVIDIS D K.Video-based measurements for wireless capsule endoscope tracking[J].Measurement Science and Technology,2014,25(1):15002.
[10] AGHANOURI M,GHAFFARI A,DADASHI N.Image-based localization of the active wireless capsule endoscope inside the stomach[C]// Proc of 2017 IEEE EMBS International Conference on Biomedical & Health Informatics.Orlando:IEEE,2017:13-16.
[11] 張永順,王楠,馬壯.腸道膠囊機器人的轉向隨動力學模型[J].機械工程學報.2012(1):84-90.
[12] 于子淳.基于獨立變量的空間萬向旋轉磁場正交變換操作原理[D].大連理工大學圖書館,2017.
[13] ZHANG Y,SU Z,CHI M,et al.Magnitude and orientation error correction of a superimposed spatial universal rotating magnetic vector[J].IEEE Transactions on Magnetics,2016,52(5):1-9.
[14] 徐德等.機器人視覺測量與控制[M].北京:國防工業出版社,2016.
[15] LOWE D G.Distinctive image features from scale invariant key points[J].International Journal of Computer Vision,2004,60(2):91-110.
[16] BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features[J].Computer Vision and Image Under- standing,2008,110(3):346-359.
[17] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]// Proc of 2011 International Conference on Computer Vision.Barcelona: IEEE,2011:2564-2571.
[18] IAKOVIDIS D K,DIMAS G,KARARGYRIS A,et al.Robotic validation of visual odometry for wireless capsule endoscopy[C]// Proc of 2016 IEEE International Conference on Imaging Systems and Techniques.Chania:IEEE,2016:83-87.
[19] ZHANG Z.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[20] RICHARD HARTLEY A.Multiple view geometry in computer vision[M].2nd Edition.Cambridge:Cambridge University Press,2004.
文獻來源
張永順, 王智博, 劉 旭, 楊慧遠. 磁控雙半球膠囊機器人姿態的圖像檢測方法[J]. 華中科技大學學報(自然科學版), 2020, 48(10): 14-19
DOI:10.13245/j.hust.201003
时时彩票