|本期目录/Table of Contents|

[1]刘 晶,钟力强,董 娜.变电站巡检机器人视觉精确定位算法研究[J].工业仪表与自动化装置,2019,(06):8-13.[doi:1000-0682(2019)06-0000-00]
　LIU Jing,ZHONG Liqiang,DONG Na.Algorithm research of visual accurate alignment for substation?inspection robot[J].Industrial Instrumentation & Automation,2019,(06):8-13.[doi:1000-0682(2019)06-0000-00]
点击复制

变电站巡检机器人视觉精确定位算法研究

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2019年06期
页码:
8-13
栏目:
出版日期:
2019-12-15

文章信息/Info

Title:
Algorithm research of visual accurate alignment for substation?inspection robot
作者:
刘 晶1; 钟力强1; 董 娜2
1. 广东电网有限责任公司电力科学研究院，广州 510080；
2. 天津大学 电气自动化与信息工程学院，天津 300072
Author(s):
LIU Jing1;  ZHONG Liqiang1;  DONG Na2
1. Electric Power Research Institute of Guangdong Power Grid Co., Ltd.,Guangzhou 510080,China;
2. School of Electrical and Information Engineering, Tianjin University, Tianjin 300072,China
关键词:
变电站巡检机器人; 精确二次对准; 视觉伺服控制; SIFT算法
Keywords:
substation inspection robot;  accurate alignment;  visual servoing;  scale invariant feature transform(SIFT) algorithm
分类号:
TM63;TP249
DOI:
1000-0682(2019)06-0000-00
文献标志码:
A
摘要:
该文研究了变电站环境下基于可见光单目视觉的变电站智能巡检机器人云台二次对准问题。该方法采用一幅预先采集的参考图像定义机器人的期望位置和摄像机云台期望方向，利用尺度不变特征变换(SIFT)特征匹配算法实现当前图像与参考图像之间的匹配以获取视觉反馈信息，采用RANSAC算法求解当前图像与参考图像间的仿射变换。并通过创建云台控制信号和图像特征空间之间的雅克比矩阵映射关系，结合图像多尺度变换实现云台精确二次对准。在变电站户外环境下的实验结果证实了该方法的有效性。
Abstract:
A method of PTZ accurate alignment for substation inspection robot is based on monocular vision camera is proposed. The desired position of robot and orientation of PTZ(Pan Tilt Zoom) camera are defined by the pre-captured reference image . The scale invariant feature transform (SIFT) algorithm is applied to extract the visual feedback information by matching the current view and the reference image. A random sample consensus(RANSAC) algorithm is used to solve the affine transform between the current and reference image. The Jacobian matrix, representing the mapping relationship, is created by processing control signal of the PTZ control platform and feature space for the image. Besides this, PTZ accurate alignment is realized combined with the image multi-scale transformation. The experiment results of a realistic outdoor substation environment demonstrate the effectiveness of the processed method.

参考文献/References:

[1] Luo RC, Liao CT, Su KL, Lin KC Automatic docking and recharging system for autonomous security robot[J]. Intelligent Robots and Systems, 2005 IEEE/RSJ International Conference, 2005:2953-2958.

[2] Jin-Xia Yu,Zi-Xing Cai,Zhuo-Hua Duan.Dead reckoning of mobile robot in complex terrain based on propri-oceptive sensors[C].International Conference on Machine Learning and Cybernetics, 2008, 4:1930-1935.
[3] Malis E,Vargas M.Deeper understanding of the homogra- phy decomposition for vision-based control[C]. PhD thesis, INRIA, 2007.
[4] Rublee E, Rabaud V, Konolige K, and Bradski G. Orb: an efficient alternative to sift or surf. IEEE International Con-ference on Computer Vision, 2011: 2564-2571
[5] Hashimoto M, Kawashima H, Nakagami T, Oba F. Sensor fault detection and identification in dead-reckoning system of mobile robot: interacting multiple model approach[C]. IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001, 3:1321-1326.
[6] Blanc G, Mezouar Y, Martinet P. Indoor navigation of a wheeled mobile robot along visual routes[C]. In Proceed-ings of the IEEE International Conference on Robotics and Automation, 2005: 3365-3370.
[7] Sagüés C, Guerrero JJ. Visual correction for mobile robot homing[J].Robotics and Autonomous Sys-tems,2005: 50(1): 41-49.
[8] Comport A, Pressigout M, Marchand E, et al. A visual servoing control law that is robust to image outliers[C].in IEEE/RSJInternational Conference on Intelligent Robots and Systems, Las Vegas, Nevada, 2003:492-497.
[9] Chen S Y. Kalman filter for robot vision:A survey[J]. IEEE Transactions on Industrial Electronics,2012,59(11): 4409-4420.
[10] Bay H, Tuytelaars T, Van Gool L.Surf:Speeded up robust features[C].Computer Vision-ECCV 2006,2006:404-417.
[11] López-Nicolás G,Sagüés C,Guerrero JJ,et al. Nonholono- mic Epipolar Visual Servoing[C]. IEEE Int. Conference on Robotics and Automation, 2006: 2378-2384.
[12] Kummerle R, Grusettu, et. G2o: a general framework for graph optimization[J]. IEEE International Conference on Robotics and Automation, 2011: 3607-3613.
[13] Weike K, Azad P, Dillmann R. Fast and robust feature- based recognition of multiple objects[C]. Humanoid Ro-bots,2006 6th IEEE-RAS International C,onference, 2006: 264-269.
[14] Binhai W, li L, et al. The application of Image Based Visual Servo Control System for Smart Guard[C].10th IEEE International Conference on Control & Automation, 2013: 2331-2336.
[15] Yuqiu S, Wei S. Research on CMAC study control strategy for robotic visual servo system[J]. Computer Engineering and Applications, 2010,46(26): 238-240.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：2019-03-20
基金项目：中国南方电网有限责任公司科技项目“线路行走式机器人小型化、轻型化及实用化技术及其在电网维护中的应用研究”(GDKJXM20173031)
作者简介：刘晶(1987)，女，工程师，博士，从事机器人控制及模式识别工作。
更新日期/Last Update: 1900-01-01