Design and test of row-follow control system based on visual perception of lateral-offset of weeding component in paddy field
-
摘要:目的
为使水稻机械除草部件作业时能避开秧苗、降低伤苗率,设计了一种基于机器视觉与比例积分微分(Proportion integration differentiation,PID)控制的避苗控制系统。
方法利用改进超绿算法对秧苗进行灰度化,运用图像投影法对感兴趣区域(Region of interest,ROI)内的秧苗进行特征提取及图像坐标定位,采用稳健回归算法拟合秧苗,得到苗带中心线,通过小孔成像模型转换,获得秧苗的地面坐标位置及除草部件中心与苗带中心线的距离。基于PID控制算法对液压纠偏系统进行控制,并应用Matlab/Simulink对系统进行仿真研究。
结果系统可实现避苗作业,模型的稳态响应时间为0.34 s。系统性能对比试验的结果表明:避苗控制系统明显减少了除草部件的伤苗情况,平均伤苗率为3.75%;而没有避苗控制系统的情况下,平均伤苗率为24.88%。
结论本文设计的对行控制系统满足除草部件作业路径实时校正要求,可有效降低稻田机械除草的伤苗率。研究结果为水稻及其他作物的机械除草对行控制提供参考。
Abstract:ObjectiveIn order to avoid seedling and reduce seedling damage rate during the operation of mechanical weeding, a control system of avoiding seedling based on machine vision and proportion integration differentiation (PID) control technology was designed.
MethodThe improved extra-green algorithm was used to gray rice seedlings. The image projection method was used to extract the characteristics of rice seedlings within the region of interest (ROI) to obtain the corresponding image coordinates. The robust regression algorithm was used to fit rice seedlings to obtain the center line of seedling belt. The ground coordinate position of seedling, and the distance between the center of weeding unit and the center line of seedling belt were obtained by transforming the model of aperture imaging. The hydraulic rectifying system was controlled based on PID control algorithm, and the Simulink in Matlab software was used for the simulation analysis of the system.
ResultThe seedling avoidance was realized, and the steady-state response time of the system model was 0.34 s. The performance comparison tests of the control system with and without the control system of avoiding seedlings showed that the control system of avoiding seedlings could obviously reduce the seedling damage of weeding components, with the average seedling injury rate of 3.75%, and the rate without the control system of avoiding seedlings was 24.88%.
ConclusionThe row-follow control system for mechanical weeding designed in this study can correct the working path of the weeding components in real time, which effectively reduces the seedling injury rate of mechanical weeding. The results of this study can provide some reference for mechanical weeding row-follow control of rice and other crops.
-
Keywords:
- Rice /
- Mechanical weeding /
- Machine vision /
- Avoiding seedling control /
- PID control
-
图 3 图像的投影
图中红色虚线代表ROI区域的阈值$T{_S}_{n}$和TC;绿色虚线表示$ {M}_{1} $、$ {M}_{2} $、$ {m}_{1} $的值,即ROI区域的横、纵坐标中点的位置;蓝色实线表示稻株图像的投影。在垂直投影中,$ {D}_{1} $、$ {D}_{2} $和$ {U}_{1} $、$ {U}_{2} $分别表示ROI内每穴稻株图像的起点边界和终点边界;在水平投影中,$ {u}_{1} $、${d}_{1}$分别表示ROI内稻株图像的起点边界和终点边界
Figure 3. Projection of the image
The red dotted line represents the threshold $T{_S}_{n}$ and TC of the ROI, and the green dotted line represents; $ {M}_{1} $, $ {M}_{2} $ and $ {m}_{1} $, the position of the midpoint of the horizontal and vertical coordinates of the ROI; The solid blue line represents the projection of the seedling image. In vertical projection, $ {D}_{1} $, $ {D}_{2} $ and $ {U}_{1} $, $ {U}_{2} $ represent the start and end boundaries of each seedling image in the ROI, respectively; In the horizontal projection, $ {u}_{1} $ and $ {d}_{1} $ represent the start and end boundaries of the seedling image in the ROI, respectively
图 7 基于Amesim的液压系统仿真模型
1:给定信号;2:减法器;3:比例放大器;4:比例换向阀;5:溢流阀;6:油压源;7:油箱;8:液压缸;9:对行执行机构;10:直线位移传感器;11:油源
Figure 7. Hydraulic system simulation model based on Amesim
1: Given signal; 2: Subtractor; 3: Proportional amplifier; 4: Proportional reversing valve; 5: Relief valve; 6: Oil pressure source; 7: Oil tank; 8: Hydraulic cylinder; 9: Row-follow actuator; 10: Linear displacement sensor; 11: Oil source
图 9 基于PID的液压系统仿真模型
1:给定信号;2:减法器;3:比例系数;4:积分系数;5:微分系数;6:积分器;7:微分器;8:比例换向阀传递函数;9:阀控缸传递函数;10:直线位移传感器反馈系数
Figure 9. PID-based hydraulic system simulation model
1: Given signal; 2: Subtractor; 3: Proportional coefficient; 4: Integral coefficient; 5: Differential coefficient; 6: Integrator; 7: Differentiator; 8:Transfer function of proportional directional valve; 9: Valve controlled cylinder transfer function; 10: Feedback coefficient of linear displacement sensor
表 1 直线拟合方法分析
Table 1 Analysis of straight line fitting method
拟合方法
Fitting method标准差
Standard deviation平均拟合时间/s
Average fitting time最小二乘法
Least squares4.230 6 0.12 Hough变换
Hough transform3.100 7 0.41 稳健回归
Robust regression2.842 2 0.17 表 2 有无避苗系统的伤苗率对比
Table 2 Comparison of seedling injury rate with or without seedling avoidance system
试验序号
No. of test伤苗率/% Injury rate of seedling 无 Without 有 With 1 22.50 2.65 2 23.10 3.83 3 26.20 5.33 4 37.90 3.44 5 14.70 3.51 平均值 Average 24.88 3.75 -
[1] 伍同, 曾山, 赵润茂, 等. 智能化作物株间机械除草技术分析与研究[J]. 农机化研究, 2019, 41(6): 1-6. doi: 10.3969/j.issn.1003-188X.2019.06.001 [2] 罗锡文, 廖娟, 胡炼, 等. 我国智能农机的研究进展与无人农场的实践[J]. 华南农业大学学报, 2021, 42(6): 8-17. doi: 10.7671/j.issn.1001-411X.202108040 [3] 夏新, 张广才, 鲍康阜, 等. 水直播稻田化学除草试验[J]. 现代农业科技, 2021(12): 118-121. doi: 10.3969/j.issn.1007-5739.2021.12.047 [4] 李春胜, 谭宏杰, 李娜, 等. 水稻田间除草现状分析及未来发展趋势的思考[J]. 农业与技术, 2021, 41(24): 10-12. [5] 齐龙, 赵柳霖, 马旭, 等. 3GY-1920型宽幅水田中耕除草机的设计与试验[J]. 农业工程学报, 2017, 33(8): 47-55. [6] 邓小静. 农用无人机植保的应用及发展[J]. 南方农机, 2021, 52(2): 61-62. doi: 10.3969/j.issn.1672-3872.2021.02.031 [7] 蒋郁, 齐龙, 龚浩, 等. 气动式水稻株间机械除草装置研制[J]. 华南农业大学学报, 2020, 41(6): 37-49. doi: 10.7671/j.issn.1001-411X.202006015 [8] 张俊雄, 王凯, 张良, 等. 横移对行控制系统设计与试验分析[J]. 江苏大学学报(自然科学版), 2017, 38(4): 423-427. [9] ÅSTRAND B, BAERVELDT A J. An agricultural mobile robot with vision-based perception for mechanical weed control[J]. Autonomous Robots, 2002, 13(1): 21-35. doi: 10.1023/A:1015674004201
[10] ÅSTRAND B, BAERVELDT A J. A vision based row-following system for agricultural field machinery[J]. Mechatronics, 2005, 15(2): 251-269. doi: 10.1016/j.mechatronics.2004.05.005
[11] 陈娇, 姜国权, 杜尚丰, 等. 基于垄线平行特征的视觉导航多垄线识别[J]. 农业工程学报, 2009, 25(12): 107-113. doi: 10.3969/j.issn.1002-6819.2009.12.019 [12] 孟庆宽, 何洁, 仇瑞承, 等. 基于机器视觉的自然环境下作物行识别与导航线提取[J]. 光学学报, 2014, 34(7): 180-186. [13] 孟庆宽. 基于机器视觉的农业车辆—农具组合导航系统路径识别及控制方法研究[D]. 北京: 中国农业大学, 2014. [14] 李军锋, 李逃昌, 彭继慎. 农业机器人视觉导航路径识别方法研究[J]. 计算机工程, 2018, 44(9): 38-44. [15] 司永胜, 姜国权, 刘刚, 等. 基于最小二乘法的早期作物行中心线检测方法[J]. 农业机械学报, 2010, 41(7): 163-167. doi: 10.3969/j.issn.1000-1298.2010.07.034 [16] 郭祥雨, 薛新宇. 基于机器视觉的水稻制种田导航线提取方法[J]. 中国农机化学报, 2021, 42(5): 197-201. [17] 贾洪雷, 李森森, 王刚, 等. 中耕期玉米田间避苗除草装置设计与试验[J]. 农业工程学报, 2018, 34(7): 15-22. doi: 10.11975/j.issn.1002-6819.2018.07.002 [18] 齐龙, 刘闯, 蒋郁. 水稻机械除草技术装备研究现状及智能化发展趋势[J]. 华南农业大学学报, 2020, 41(6): 29-36. doi: 10.7671/j.issn.1001-411X.202008043 [19] 韩豹, 杨亚楠, 王宏伟, 等. 苗间除草部件入土深度PID自动控制系统设计与台架试验[J]. 农业工程学报, 2018, 34(11): 68-77. doi: 10.11975/j.issn.1002-6819.2018.11.009 [20] 陈勇, 田磊, 郑加强. 基于直接施药方法的除草机器人[J]. 农业机械学报, 2005, 36(10): 91-93. [21] 郭伟斌, 陈勇, 侯学贵, 等. 除草机器人机械臂的逆向求解与控制[J]. 农业工程学报, 2009, 25(4): 108-112. [22] 胡炼, 罗锡文, 严乙桉, 等. 基于爪齿余摆运动的株间机械除草装置研制与试验[J]. 农业工程学报, 2012, 28(14): 10-16. doi: 10.3969/j.issn.1002-6819.2012.14.002 [23] 胡炼, 罗锡文, 曾山, 等. 基于机器视觉的株间机械除草装置的作物识别与定位方法[J]. 农业工程学报, 2013, 29(10): 12-18. [24] 杨洋, 张博立, 查家翼, 等. 玉米行间导航线实时提取[J]. 农业工程学报, 2020, 36(12): 162-171. doi: 10.11975/j.issn.1002-6819.2020.12.020 [25] HAGUE T, TILLETT N D. A bandpass filter-based approach to crop row location and tracking[J]. Mechatronics, 2001, 11(1): 1-12. doi: 10.1016/S0957-4158(00)00003-9
[26] 蒋郁, 崔宏伟, 区颖刚, 等. 基于茎基部分区边缘拟合的稻株定位方法[J]. 农业机械学报, 2017, 48(6): 23-31. -
期刊类型引用(4)
1. 张馨悦,王超,王庆杰,康可新,李贵蓉,刘立晶. 玉米苗期行间除草二级对行装置设计与试验. 农业机械学报. 2025(04): 42-51+60 . 百度学术
2. 何创新,巩蕾,苗中华,韩科立,郝付平,韩增德. 基于平行轨迹导航的采棉机自动对行控制方法. 农业机械学报. 2024(06): 34-41 . 百度学术
3. 苏鹏鉴,马海琴,叶俊明. 基于无人系统的智能视觉控制算法研究. 电子测量技术. 2024(09): 93-97 . 百度学术
4. 张晓龙,易克传,姜春霞,凃何平,郭子明. 基于四连杆机构自动对行装置的设计与仿真. 东莞理工学院学报. 2024(05): 110-116 . 百度学术
其他类型引用(0)