摘要
针对金属冶炼排渣机械手对炉渣位置定位的问题,本文提出了一种基于近红外视觉的高温目标定位方法。使用红外阵列传感器和CMOS摄像头结构光三维重建视野标定后搭建出一套近红外视觉系统。用蜡烛光模拟高温炉渣,将红外阵列传感器采集的温度点阵数据绘制出伪彩色温度分布图,利用仿射不变性原理将其与彩色图像配准融合,生成高温炉渣及其周围环境的红外-可见光融合图像。最后,利用红外阵列传感器横、纵视野角分量投影的方法得到高温炉渣的三维坐标。实验结果表明,红外阵列传感器定位高温炉渣的方法是可行的。定位得到高温炉渣的三维坐标为机械手提供目标期望给定,机械手可进一步完成排渣任务。
A high-temperature target positioning method based on a near-infrared vision system is proposed for the slag positioning for the manipulator in metal smelting and slagging. A near-infrared vision system is built by infrared array sensors and a complementary metal–oxide–semiconductor(CMOS) camera after performing directional calibration of structured light three-dimensional reconstruction. Candle light is used to simulate the high-temperature slag, and the temperature lattice data collected by the infrared array sensor are plotted as a pseudocolor temperature distribution map. The affine invariance principle is used to align the pseudocolor temperature distribution map with the color image to generate an infrared–visible fusion image of the high-temperature slag and its surrounding environment. Finally, the three-dimensional coordinates of the high-temperature slag are obtained by the infrared array sensors' transverse and longitudinal viewing angle proportion projection. The experimental results show that the method of positioning high-temperature slag by an infrared array sensor is viable. The three-dimensional coordinates of the high-temperature slag gained by positioning could provide an objective expectation for the manipulator, helping the manipulator to complete slagging.
引文
[1]张栩.基于全景近红外视觉的室外移动机器人定位系统[J].微型电脑应用,2011,27(1):28-30.ZHANG XU.Outdoor mobile robot positioning system based on panoramic near infrared vision[J].Microcomputer Applications,2011,27(1):28-30.
[2]谢伊霖.关于变电运行工作中红外成像检测技术的应用探讨[J].低碳世界,2016,33:44-45.XIE Yilin.Discussion on the application of infrared imaging detection technology in substation operation[J].Low Carbon World,2016,33:44-45.
[3]庄严,王伟,王坷.移动机器人基于激光测距和单目视觉的室内同时定位和地图构建[J].自动化学报,2005,31(6):113-121.ZHANG Yan,WANG Wei,WANG Ke.Mobile robot indoor simultaneous localization and mapping using laser range finder and monocular vision[J].Acta Automatica Sinica,2005,31(6):113-121.
[4]崔素梅,赵美蓉,宋乐,等.基于模糊神经网络的红外图像边缘提取算法[J].激光与红外,2012,42(9):1063-1067.CUI Sumei,ZHAO Meirong,SONG Le,et al.Infrared image edge extraction based on fuzzy neural network[J].Laser and Infrared,2012,42(9):1063-1067.
[5]刘前进,杨卫,刘云武.基于热释电红外传感器的多节点定位系统研究与设计[J].计算机测量与控制,2014,22(9):2947-2948.LIU Qiang,YANG Wei,LIU Yunwu.Research and design of multi-node positioning system based on pyroelectric infrared sensor[J].Computer Measurement and Control,2014,22(9):2947-2948.
[6]潘敏,孟非,包涵,等.一种新型红外立体视觉定位系统研究[J].单片机与嵌入式系统应用,2013,13(3):7-10.PAN Min,MENG Fei,BAO Han,et al.Research on infrared stereo vision positioning system[J].Microcontollers and Embedded Systems,2013,13(3):7-10.
[7]王念欧.基于人流分布感知的智能空调控制系统设计[D].杭州:浙江大学,2015.WANG Nianou.Design of Intelligent Air Conditioning Control System based on Human Flow Distribution Perception[D].Hangzhou:Zhejiang University,2015.
[8]Ishiguro H.Development of Low-Cost Compact Omnidirectional Vision Sensors and their applications[M]//Panoramic vision.Springer-Verlag New York,Inc.1998.
[9]杨任兵,程文播,钱庆,等.红外图像中基于多特征提取的跌倒检测算法研究[J].红外技术,2017,39(12):1131-1138.YANG Renbing,CENG Wenbo,QIAN Qing,et al.Fall detection algorithm based on multi feature extraction in infrared image[J].Infrared Technology,2017,39(12):1131-1138.
[10]Shakunaga T.An object pose estimation system using a single camera[C]//IEEE Int.Conf.on Intelligent Robots and System’s,1992:1053-1060.
[11]江士雄,曹丹华,吴裕斌.面向机器人抓取的双目视觉系统标定与目标位姿估计算法[J].仪表技术与传感器,2016(11):110-113.JIANG Shixiong,CAO Danhua,WU Yubin.Binocular vision system calibration and object pose estimation method for robert fetching[J].Instrument Technique and Sensor,2016(11):110-113.
[12]冯春成,刘满禄,张华,等.工业机器人机械臂加工目标定位控制研究[J].计算机仿真,2017,34(6):319-324.FENG Chuncheng,LIU Manlu,ZHANG Hua,et al.Research on machining target positioning control of industrial robot manipulator[J].Computer Simulation,2017,34(6):319-324.
[13]YANG X,LING Y,LI S,et al.Graying for images with color-discrete characteristic[J].Optik-International Journal for Light and Electron Optics,2011,122(18):1633-1637.
[14]刘博,仲思东.一种基于自适应阈值的SUSAN角点提取方法[J].红外技术,2006,28(6):331-333.LIU Bo,ZHONG Sidong.A SUSAN corner detector based on adaptive threshold[J].Infrared Technology,2006,28(6):331-333.
[15]Perez M M,Dennis T J.An adaptive implementation of the Susan method for image edge and feature detection[C]//International Conference on Image Processing of IEEE,1997:10.1109/ICIP.1997.638789.
[16]Liao B,Xu J,Sun H,et al.Robust corner detection based on bilateral filter in direct curvature scale space[C]//International Conference in Swarm Intelligence,Springe:2015.
[17]Phillips J B,Eliasson H.Camera Image Quality Benchmarking[M]//Wiley:2017.
[18]Rassokhin D N,Lobanov V S,Agrafiotis D K.Nonlinear mapping of massive data sets by fuzzy clustering and neural networks[J].Journal of Computational Chemistry,2015,22(4):373-386.
[19]贾林,顾爽,陈启军.基于图像视觉伺服的移动机器人自主导航实现[J].华中科技大学学报:自然科学版,2011(S2):220-222.JIA Lin,GU Shuang,CHEN Qijun.An autonomous navigation procedure for mobile robot on image-based visual servoing[J].Journal of Huazhong University of Science and Technology:Nature Science Edition,2011(S2):220-222.
[20]Thoo H W,Ratnam M M.An improved method of projected area determination in nanoindentation using image processing with sub-pixel edge location[J].Experimental Techniques,2016,40(2):803-818.