一种视觉导引AGV叉车倾斜畸变自标定方法
|
摘要
为了提高单目视觉自动导引叉车视觉导引精度,以及叉车对接托盘过程中实时测距,提出了一种可根据导引色带进行动态倾斜标定的方法,该方法对采集图像滤波处理后,采用增大纵向模板权值的Sobel算子提取边界,改进霍夫变换查找边线方程,通过边线方程计算地面坐标系下的透视点,进行倾斜畸变校正。实验结果表明,该方法测量精度高,可精确感知车体托盘距离,鲁棒性、实时性较好。
In order to improve the guidance accuracy of the monocular vision automatic guidance forklift and measure the engaging of the forklift and the pallet in real time, this paper presents a method which can carry out dynamic tilt calibration using guiding ribbon.According to this method, the Hough transform is modified to find the boundary equation after the filtering process on the collected image,then the boundary is isolated using the Sobel operator with enhanced vertical template weight. At the end, the boundary equation is used to calculate the perspective point in the ground coordinate system and correct the tilt distortion. The result of a test demonstrates the accuracy,robustness and real-time performance of the method.
In order to improve the guidance accuracy of the monocular vision automatic guidance forklift and measure the engaging of the forklift and the pallet in real time, this paper presents a method which can carry out dynamic tilt calibration using guiding ribbon.According to this method, the Hough transform is modified to find the boundary equation after the filtering process on the collected image,then the boundary is isolated using the Sobel operator with enhanced vertical template weight. At the end, the boundary equation is used to calculate the perspective point in the ground coordinate system and correct the tilt distortion. The result of a test demonstrates the accuracy,robustness and real-time performance of the method.
引文
[1]Michael Seelinger,John-David Yoder.Automatic visual guidance of a forklift engaging a pallet[J].Robotics and Autonomous Systems,2005,54(12).
[2]张建鹏,楼佩煌,钱晓明,武星.多窗口实时测距的视觉导引AGV精确定位技术研究[J].仪器仪表学报,2016,37(6):1 356-1 363.
[3]Shourui Yang,Miao Liu,Shibin Yin,Yin Guo,Yongjie Ren,Jigui Zhu.An improved method for location of concentric circles in vision measurement[J].Measurement,2017,100(3):243-251.
[4]Richard N McNeely,Eric Pazo,Andrew Spence,Olivier Richoz,M Andrew Nesbit,Tara C B Moore,Jonathan E Moore.Comparison of the visual performance and quality of vision with combined symmetrical inferonasal near addition versus inferonasal and superotemporal placement of rotationally asymmetric refractive multifocal intraocular lenses[J].Journal of Cataract&Refractive Surgery,2016,42(12).
[5]郑太雄,黄帅,李永福,等.基于视觉的三维重建关键技术研究综述[EB/OL].https://doi.org/10.16383/j.aas.2017c170502.2018-10-15.
[6]Gang Chen,Rui Peng,Zhicheng Wang,Weidong Zhao.Recognition and locating of pallet based on image processing for vision guided forklift[A].Proceedings of 2011 World Congress on Engineering and Technology(CET 2011)VOL07[C].2011.
[7]Jittima Varagul,Toshio Ito.Simulation of Detecting Function object for AGV Using Computer Vision with Neural Network[J].Procedia Computer Science,2016,96.
[8]David Culler,James Long.A Prototype Smart Materials Warehouse Application Implemented Using Custom Mobile Robots and Open Source Vision Technology Developed Using EmguCV[J].Procedia Manufacturing,2016,(5).
[9]Falko Sojka,Matthias Meissner,Christian Zwick,Roman Forker,Michael Vyshnepolsky,Claudius Klein,Michael Horn-von Hoegen,Torsten Fritz.To tilt or not to tilt:Correction of the distortion caused by inclined sample surfaces in low-energy electron diffraction[J].Ultramicroscopy,2013,133.
[10]汪贵平,王会峰,刘盼芝,巨永锋.特征平行直线的成像畸变现场校正[J].光子学报,2014,43(1):93-97.
[11]杨麒,李天伟,黄谦,李伟.基于直线投影特征的镜头畸变校正方法[J].计算机测量与控制,2018,26(9):264-268.
[12]喻俊,楼佩煌,武星,王龙军.基于静止和运动两种状态的自动导引车视觉标定[J].中国机械工程,2012,23(6):703-707.
[13]何春华,张雪飞,胡迎春.基于改进Sobel算子的边缘检测算法的研究[J].光学技术,2012,38(3):323-327.
[14]沈德海,鄂旭,侯建.一种改进的Sobel算子边缘检测及细化算法[J].渤海大学学报(自然科学版),2014,35(3):256-260.
[2]张建鹏,楼佩煌,钱晓明,武星.多窗口实时测距的视觉导引AGV精确定位技术研究[J].仪器仪表学报,2016,37(6):1 356-1 363.
[3]Shourui Yang,Miao Liu,Shibin Yin,Yin Guo,Yongjie Ren,Jigui Zhu.An improved method for location of concentric circles in vision measurement[J].Measurement,2017,100(3):243-251.
[4]Richard N McNeely,Eric Pazo,Andrew Spence,Olivier Richoz,M Andrew Nesbit,Tara C B Moore,Jonathan E Moore.Comparison of the visual performance and quality of vision with combined symmetrical inferonasal near addition versus inferonasal and superotemporal placement of rotationally asymmetric refractive multifocal intraocular lenses[J].Journal of Cataract&Refractive Surgery,2016,42(12).
[5]郑太雄,黄帅,李永福,等.基于视觉的三维重建关键技术研究综述[EB/OL].https://doi.org/10.16383/j.aas.2017c170502.2018-10-15.
[6]Gang Chen,Rui Peng,Zhicheng Wang,Weidong Zhao.Recognition and locating of pallet based on image processing for vision guided forklift[A].Proceedings of 2011 World Congress on Engineering and Technology(CET 2011)VOL07[C].2011.
[7]Jittima Varagul,Toshio Ito.Simulation of Detecting Function object for AGV Using Computer Vision with Neural Network[J].Procedia Computer Science,2016,96.
[8]David Culler,James Long.A Prototype Smart Materials Warehouse Application Implemented Using Custom Mobile Robots and Open Source Vision Technology Developed Using EmguCV[J].Procedia Manufacturing,2016,(5).
[9]Falko Sojka,Matthias Meissner,Christian Zwick,Roman Forker,Michael Vyshnepolsky,Claudius Klein,Michael Horn-von Hoegen,Torsten Fritz.To tilt or not to tilt:Correction of the distortion caused by inclined sample surfaces in low-energy electron diffraction[J].Ultramicroscopy,2013,133.
[10]汪贵平,王会峰,刘盼芝,巨永锋.特征平行直线的成像畸变现场校正[J].光子学报,2014,43(1):93-97.
[11]杨麒,李天伟,黄谦,李伟.基于直线投影特征的镜头畸变校正方法[J].计算机测量与控制,2018,26(9):264-268.
[12]喻俊,楼佩煌,武星,王龙军.基于静止和运动两种状态的自动导引车视觉标定[J].中国机械工程,2012,23(6):703-707.
[13]何春华,张雪飞,胡迎春.基于改进Sobel算子的边缘检测算法的研究[J].光学技术,2012,38(3):323-327.
[14]沈德海,鄂旭,侯建.一种改进的Sobel算子边缘检测及细化算法[J].渤海大学学报(自然科学版),2014,35(3):256-260.