基于定向摄像头的大拱棚运输车视觉导航研究
|
摘要
针对大拱棚中运输车导航问题,提出了一种适用性更高的导航方法。为了规避叶间空隙对Hough直线变换精度造成的影响,使用道路尽头横向中心点作为导航信息标定点,搭建摄像头云台使得摄像头视轴始终与道路平行。使用色度法对作物与道路进行分割处理,通过面积筛选所得的轮廓点集,能够准确计算出道路尽头的横向中心点像素坐标,从而得到运输车的位姿信息。通过运动学建模对运输车进行了轨迹仿真,得到了运输车不同速度下对识别误差的动态响应。基于Raspberry Pi平台搭建了导航信息提取装置,在不同道路长度的拱棚中对比了本文方法与Hough变换法的识别精度,并使用不同类型摄像头进行了静态导航信息提取实验,同时在不同速度进行了运输车的直线行驶实验。静态实验表明,相比于传统Hough变换,该导航方法能够显著提高识别精度,使用长焦摄像头比普通摄像头识别精度平均提高了25. 7%,导航线平均识别偏差为2. 4 cm,检测速率为240 ms/f,具有较高的精度和实时性。行驶实验表明,该导航方法在不同速度下均能保证较小的稳态误差,能够满足生产要求。
To solve the key prerequisite of greenhouse carrier vehicle navigation,a new navigation method was proposed based on fixed direction camera. A pan-tilt camera was constructed to collimate the vision line to corridor's center line with geomagnetic sensor and digital servo. The angle error was detected by geomagnetic sensor and the error was compensated by servo. The drawback of Hough transform was avoided by using new method of picture processing. The vision system ran in Raspberry Pi based on OpenCV in Linux. It distinguished corridor and crop by value of hue instead of Excess—Green method and the end point of corridor was got by area of screening. By using the Ackerman principle,the vehicle's position and attitude angle can be received. The dynamic response was got by modeling the equation of vehicle and simulating the movement of vehicle at different vehicle speeds. The experiment was done in real greenhouse which was divided into two parts,including the static experiment and dynamic experiment. The error of navigation information was obtained by processing the picture in fixed platform and a control experiment with Hough transform. The vehicle can drive automatically at different speeds in greenhouse. The results showed that the average time cost of this method was less than240 ms/f,the average detection error of the navigation line was 2. 4 cm,and the long-focus camera can reduce the error by 25. 7%,which indicated that the method was available to get navigation line with appropriate accuracy and instantaneity.
To solve the key prerequisite of greenhouse carrier vehicle navigation,a new navigation method was proposed based on fixed direction camera. A pan-tilt camera was constructed to collimate the vision line to corridor's center line with geomagnetic sensor and digital servo. The angle error was detected by geomagnetic sensor and the error was compensated by servo. The drawback of Hough transform was avoided by using new method of picture processing. The vision system ran in Raspberry Pi based on OpenCV in Linux. It distinguished corridor and crop by value of hue instead of Excess—Green method and the end point of corridor was got by area of screening. By using the Ackerman principle,the vehicle's position and attitude angle can be received. The dynamic response was got by modeling the equation of vehicle and simulating the movement of vehicle at different vehicle speeds. The experiment was done in real greenhouse which was divided into two parts,including the static experiment and dynamic experiment. The error of navigation information was obtained by processing the picture in fixed platform and a control experiment with Hough transform. The vehicle can drive automatically at different speeds in greenhouse. The results showed that the average time cost of this method was less than240 ms/f,the average detection error of the navigation line was 2. 4 cm,and the long-focus camera can reduce the error by 25. 7%,which indicated that the method was available to get navigation line with appropriate accuracy and instantaneity.
引文
1魏爽,季宇寒,曹如月,等.农机自动导航控制决策方法与软件系统[J/OL].农业机械学报,2017,48(增刊):30-34,171.http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? file_no=2017s005&flag=1. DOI:10. 6041/j. issn. 1000-1298.2017. S0. 005.WEI Shuang,JI Yuhan,CAO Ruyue,et al. Decision control method and software of automatic navigation system for agricultural machinery[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):30-34,171.(in Chinese)
2 BENSON E R,REID J F,ZHANG Q. Machine vision-based guidance system for agricultural grain harvesters using cut-edge detection[J]. Biosystems Engineering,2003,86(4):389-398.
3 PAWIN T,TOFAEL A,TOMOHIRO T. Navigation of autonomous tractor for orchards and plantations using a laser range finder:automatic control of trailer position with tractor[J]. Biosystems Engineering,2016,147:90-103.
4 宋宇,刘永博,刘路,等.基于机器视觉的玉米根茎导航基准线提取方法[J/OL].农业机械学报,2017,48(2):38-44. http:∥www. jcsam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20170205&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2017. 02. 005.SONG Yu,LIU Yongbo,LIU Lu,et al. Extraction method of navigation baseline of corn roots based on machine vision[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(2):38-44.(in Chinese)
5 张甜.高茬水田耕整路径机器视觉识别方法研究[D].武汉:华中农业大学,2014.ZHANG Tian. Study on the method of machine vision recognition of high stubble paddyfield-tillage's path[D]. Wuhan:Huazhong Agricultural University,2014.(in Chinese)
6 高国琴,李明.基于K-means算法的温室移动机器人导航路径识别[J].农业工程学报,2014,30(7):25-33.GAO Guoqin,LI Ming. Navigating path recognition for greenhouse mobile robot based on K-means algorithm[J]. Transactions of the CSAE,2014,30(7):25-33.(in Chinese)
7 JUNG K,LEE I,SONG H,et al. Vision guidance system for AGV using ANFIS[C]∥Intelligent Robotics and Applications.Springer Berlin Heidelberg,2012:377-385.
8 BUTDEE S,SUEBSOMRAN A. Automatic guided vehicle control by vision system[C]∥Industrial Engineering and Engineering Management,2009. IEEE International Conference on IEEE,2009:694-697.
9 居锦,刘继展,李男,等.基于侧向光电圆弧阵列的温室路沿检测与导航方法[J].农业工程学报,2017,33(18):180-187.JU Jin,LIU Jizhan,LI Nan,et al. Curb-following detection and navigation of greenhouse vehicle based on arc array of photoelectric switches[J]. Transactions of the CSAE,2017,33(18):180-187.(in Chinese)
10 OHMORJ H. Utilization of the electric vehicle in greenhouse horticulture[J]. Journal of the Japanese Society of Agricultural Machinery,2010,72:527-530.
11 YAMASHITA J,SATOU K,HIKITA M,et al. Development of an automatic transport vehicle for use in greenhouses[J].Journal of the Japanese Society of Agricultural Machinery,2010,53:75-84.
12 王志文,郭戈.移动机器人导航技术现状与展望[J].机器人,2003,25(5):470-474.WANG Zhiwen,GUO Ge. Present situation and future development of mobile robot navigation technology[J]. Robot,2003,25 (5):470-474.(in Chinese)
13 王新忠,韩旭,毛罕平,等.基于最小二乘法的温室番茄垄间视觉导航路径检测[J/OL].农业机械学报,2012,43(6):161-166 . http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20120629&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2012. 06. 029.WANG Xinzhong,HAN Xu,MAO Hanping,et al. Navigation line detection of tomato ridges in greenhouse based on least square method[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2012,43(6):161-166.(in Chinese)
14 任永新,谭豫之,杨会华,等.基于模糊控制的黄瓜采摘机器人视觉导航[J].江苏大学学报(自然科学版),2009,30(4):343-346.REN Yongxin,TAN Yuzhi,YANG Huihua,et al. Visual navigation of cucumber picking robot based on fuzzy control[J]. Journal of Jiangsu University(Natural Science Edition),2009,30(4):343-346.(in Chinese)
15 贾士伟,李军民,邱权,等.基于激光测距仪的温室机器人道路边缘检测与路径导航[J].农业工程学报,2015,31(13):39-45.JIA Shiwei,LI Junmin,QIU Quan,et al. New corridor edge detection and navigation for greenhouse mobile robots based on laser scanner[J]. Transactions of the CSAE,2015,31(13):39-45.(in Chinese)
16 孙元义,张少磊,李伟.棉田喷药农业机器人的导航路径识别[J].清华大学学报(自然科学版),2007,47(2):206-209.SUN Yuanyi,ZHANG Shaolei,LI Wei. Guidance lane detection for pesticides praying robot in cotton fields[J]. Journal of Tsinghua University(Science and Technology),2007,47(2):206-209.(in Chinese)
17 相阿荣,王一鸣.利用色度法识别杂草和土壤背景物[J].中国农业大学学报,2000,5(4):98-100.XIANG Arong,WANG Yiming. The research on hue to identify weed and backgrounds[J]. Journal of China Agricultural University,2000,5(4):98-100.(in Chinese)
18 陈树人,沈宝国,毛罕平,等.基于颜色特征的棉田中铁苋菜识别技术[J].农业机械学报,2009,40(5):149-152.CHEN Shuren,SHEN Baoguo,MAO Hanping,et al. Copperleaf herb detection from cotton field based on color feature[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(5):149-152.(in Chinese)
19 ANDREASEN C,RUDEMO M,SEVESTRE S. Assessment of weed density at an early stage by use of image processing[J].Weed Research,1997,37(1):5-18.
20 WEI Guo,UDAY K R,NINOMIYA S. Illumination invariant segmentation of vegetation for time series wheat images based on decision tree model[J]. Computers and Electronics in Agriculture,2013,96(8):58-66.
21 陈戌冬,田跃,李杰,等.基于磁角度传感器云台控制系统的设计与研制[J].传感器与微系统,2007(11):72-74.CHEN Xudong,TIAN Yue,LI Jie,et al. Design and development of pan-silt control system based on magnetic sensor[J].Transducer and Microsystem Technologies,2007(11):72-74.(in Chinese)
22 纪钢,司洞洞,吴萍萍.基于反馈式可定位云台控制系统设计与实现[J].计算机测量与控制,2015,23(5):1582-1585.JI Gang,SI Dongdong,WU Pingping. Addressed PTZ control system design and implementation based on feedback[J]. Computer Measurement&Control,2015,23(5):1582-1585.(in Chinese)
23 王日俊,白越,续志军,等.基于扰动观测器的机载云台扰动复合补偿方法[J].光电子·激光,2015,26(1):108-115.WANG Rijun,BAI Yue,XU Zhijun,et al. A composite disturbance compensation method for airborne platform based on improved disturbance observer[J]. Journal of Optoelectronics·laser,2015,26(1):108-115.(in Chinese)
24 任孝平,蔡自兴.基于阿克曼原理的车式移动机器人运动学建模[J].智能系统学报,2009,4(6):534-537.REN Xiaoping,CAI Zixing. Using the Ackerman principle for kinematic modeling of wheeled mobile robots[J]. Transactions on Intelligent Systems,2009,4(6):534-537.(in Chinese)
25 史晨红,左敦稳,张国家.基于轨迹控制的AGV运动控制器设计研究[J].机械设计与制造工程,2014,43(2):7-12.SHI Chenhong,ZUO Dunwen,ZHANG Guojia. Design of AGV-based trajectory navigation motion controller[J]. Machine Design and Manufacturing Engineering,2014,43(2):7-12.(in Chinese)
26 周云山,王荣本,王志中,等.自动引导车辆系统的研究(四)——自动引导车辆(AGV)的建模仿真[J].农业工程学报,1994,10(4):62-67.ZHOU Yunshan,WANG Rongben,WANG Zhizhong,et al. Modeling and simulation of automated guided vehicle[J].Transactions of the CSAE,1994,10(4):62-67.(in Chinese)
2 BENSON E R,REID J F,ZHANG Q. Machine vision-based guidance system for agricultural grain harvesters using cut-edge detection[J]. Biosystems Engineering,2003,86(4):389-398.
3 PAWIN T,TOFAEL A,TOMOHIRO T. Navigation of autonomous tractor for orchards and plantations using a laser range finder:automatic control of trailer position with tractor[J]. Biosystems Engineering,2016,147:90-103.
4 宋宇,刘永博,刘路,等.基于机器视觉的玉米根茎导航基准线提取方法[J/OL].农业机械学报,2017,48(2):38-44. http:∥www. jcsam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20170205&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2017. 02. 005.SONG Yu,LIU Yongbo,LIU Lu,et al. Extraction method of navigation baseline of corn roots based on machine vision[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(2):38-44.(in Chinese)
5 张甜.高茬水田耕整路径机器视觉识别方法研究[D].武汉:华中农业大学,2014.ZHANG Tian. Study on the method of machine vision recognition of high stubble paddyfield-tillage's path[D]. Wuhan:Huazhong Agricultural University,2014.(in Chinese)
6 高国琴,李明.基于K-means算法的温室移动机器人导航路径识别[J].农业工程学报,2014,30(7):25-33.GAO Guoqin,LI Ming. Navigating path recognition for greenhouse mobile robot based on K-means algorithm[J]. Transactions of the CSAE,2014,30(7):25-33.(in Chinese)
7 JUNG K,LEE I,SONG H,et al. Vision guidance system for AGV using ANFIS[C]∥Intelligent Robotics and Applications.Springer Berlin Heidelberg,2012:377-385.
8 BUTDEE S,SUEBSOMRAN A. Automatic guided vehicle control by vision system[C]∥Industrial Engineering and Engineering Management,2009. IEEE International Conference on IEEE,2009:694-697.
9 居锦,刘继展,李男,等.基于侧向光电圆弧阵列的温室路沿检测与导航方法[J].农业工程学报,2017,33(18):180-187.JU Jin,LIU Jizhan,LI Nan,et al. Curb-following detection and navigation of greenhouse vehicle based on arc array of photoelectric switches[J]. Transactions of the CSAE,2017,33(18):180-187.(in Chinese)
10 OHMORJ H. Utilization of the electric vehicle in greenhouse horticulture[J]. Journal of the Japanese Society of Agricultural Machinery,2010,72:527-530.
11 YAMASHITA J,SATOU K,HIKITA M,et al. Development of an automatic transport vehicle for use in greenhouses[J].Journal of the Japanese Society of Agricultural Machinery,2010,53:75-84.
12 王志文,郭戈.移动机器人导航技术现状与展望[J].机器人,2003,25(5):470-474.WANG Zhiwen,GUO Ge. Present situation and future development of mobile robot navigation technology[J]. Robot,2003,25 (5):470-474.(in Chinese)
13 王新忠,韩旭,毛罕平,等.基于最小二乘法的温室番茄垄间视觉导航路径检测[J/OL].农业机械学报,2012,43(6):161-166 . http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20120629&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2012. 06. 029.WANG Xinzhong,HAN Xu,MAO Hanping,et al. Navigation line detection of tomato ridges in greenhouse based on least square method[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2012,43(6):161-166.(in Chinese)
14 任永新,谭豫之,杨会华,等.基于模糊控制的黄瓜采摘机器人视觉导航[J].江苏大学学报(自然科学版),2009,30(4):343-346.REN Yongxin,TAN Yuzhi,YANG Huihua,et al. Visual navigation of cucumber picking robot based on fuzzy control[J]. Journal of Jiangsu University(Natural Science Edition),2009,30(4):343-346.(in Chinese)
15 贾士伟,李军民,邱权,等.基于激光测距仪的温室机器人道路边缘检测与路径导航[J].农业工程学报,2015,31(13):39-45.JIA Shiwei,LI Junmin,QIU Quan,et al. New corridor edge detection and navigation for greenhouse mobile robots based on laser scanner[J]. Transactions of the CSAE,2015,31(13):39-45.(in Chinese)
16 孙元义,张少磊,李伟.棉田喷药农业机器人的导航路径识别[J].清华大学学报(自然科学版),2007,47(2):206-209.SUN Yuanyi,ZHANG Shaolei,LI Wei. Guidance lane detection for pesticides praying robot in cotton fields[J]. Journal of Tsinghua University(Science and Technology),2007,47(2):206-209.(in Chinese)
17 相阿荣,王一鸣.利用色度法识别杂草和土壤背景物[J].中国农业大学学报,2000,5(4):98-100.XIANG Arong,WANG Yiming. The research on hue to identify weed and backgrounds[J]. Journal of China Agricultural University,2000,5(4):98-100.(in Chinese)
18 陈树人,沈宝国,毛罕平,等.基于颜色特征的棉田中铁苋菜识别技术[J].农业机械学报,2009,40(5):149-152.CHEN Shuren,SHEN Baoguo,MAO Hanping,et al. Copperleaf herb detection from cotton field based on color feature[J].Transactions of the Chinese Society for Agricultural Machinery,2009,40(5):149-152.(in Chinese)
19 ANDREASEN C,RUDEMO M,SEVESTRE S. Assessment of weed density at an early stage by use of image processing[J].Weed Research,1997,37(1):5-18.
20 WEI Guo,UDAY K R,NINOMIYA S. Illumination invariant segmentation of vegetation for time series wheat images based on decision tree model[J]. Computers and Electronics in Agriculture,2013,96(8):58-66.
21 陈戌冬,田跃,李杰,等.基于磁角度传感器云台控制系统的设计与研制[J].传感器与微系统,2007(11):72-74.CHEN Xudong,TIAN Yue,LI Jie,et al. Design and development of pan-silt control system based on magnetic sensor[J].Transducer and Microsystem Technologies,2007(11):72-74.(in Chinese)
22 纪钢,司洞洞,吴萍萍.基于反馈式可定位云台控制系统设计与实现[J].计算机测量与控制,2015,23(5):1582-1585.JI Gang,SI Dongdong,WU Pingping. Addressed PTZ control system design and implementation based on feedback[J]. Computer Measurement&Control,2015,23(5):1582-1585.(in Chinese)
23 王日俊,白越,续志军,等.基于扰动观测器的机载云台扰动复合补偿方法[J].光电子·激光,2015,26(1):108-115.WANG Rijun,BAI Yue,XU Zhijun,et al. A composite disturbance compensation method for airborne platform based on improved disturbance observer[J]. Journal of Optoelectronics·laser,2015,26(1):108-115.(in Chinese)
24 任孝平,蔡自兴.基于阿克曼原理的车式移动机器人运动学建模[J].智能系统学报,2009,4(6):534-537.REN Xiaoping,CAI Zixing. Using the Ackerman principle for kinematic modeling of wheeled mobile robots[J]. Transactions on Intelligent Systems,2009,4(6):534-537.(in Chinese)
25 史晨红,左敦稳,张国家.基于轨迹控制的AGV运动控制器设计研究[J].机械设计与制造工程,2014,43(2):7-12.SHI Chenhong,ZUO Dunwen,ZHANG Guojia. Design of AGV-based trajectory navigation motion controller[J]. Machine Design and Manufacturing Engineering,2014,43(2):7-12.(in Chinese)
26 周云山,王荣本,王志中,等.自动引导车辆系统的研究(四)——自动引导车辆(AGV)的建模仿真[J].农业工程学报,1994,10(4):62-67.ZHOU Yunshan,WANG Rongben,WANG Zhizhong,et al. Modeling and simulation of automated guided vehicle[J].Transactions of the CSAE,1994,10(4):62-67.(in Chinese)