苗期玉米冠层识别与质心定位方法研究
|
摘要
为了快速定位玉米植株位置,以苗期4～6叶玉米为研究对象,提出了一种苗期玉米冠层识别与质心定位方法。首先,在大田环境下获取农田作物视频数据,基于Faster R-CNN对玉米冠层进行识别;其次,用差分内积线性特性改进质心检测算法,对玉米冠层和杂草进行分割,并对玉米冠层识别区域进行质心定位计算,得到玉米苗质心的像素坐标;最后,通过农田实验对本文冠层识别与质心定位方法进行验证。结果表明,苗期玉米冠层识别方法的平均识别率达92. 9%,检测一帧图像的平均时间为0. 17 s,玉米冠层质心定位误差不超过1像素。
Identification and location of maize canopy at seedling stage is an important basis for plant operation and fertilization. Aiming at the problem that fertilizer utilization rate is not high,strip and broadcast fertilizer are the main fertilization methods in China,a new method for identification and location of maize canopy in seedling stage was proposed,which could identify and locate the canopy centroid of maize in seedling stage under farmland environment. In order to locate the maize plant position quickly,the maize canopy was identified by the method of deep learning,and then the centroid location of the identified area was calculated. Firstly,Faster R-CNN was used to identify the seedling maize canopy in the field environment. Then the centroid detection algorithm based on the linear property of differential inner product improved the centroid location method of maize canopy. After the corn canopy and the weeds were segmented,the centroid of maize canopy was located and the pixel coordinates of maize seedling centroid were obtained. Through the verification in the actual farmland environment,the accuracy of identification and positioning of the canopy centroid reached 92. 9%. The average detection time of a frame image was 0. 17 s. The positioning error of the canopy centroid was less than 1 pixel.Through the analysis of the test results,the research results can provide information support for the positioning fertilization and research basis for the follow-up variable fertilization operations,so as to achieve the production goal of saving fertilizer and increasing efficiency.
Identification and location of maize canopy at seedling stage is an important basis for plant operation and fertilization. Aiming at the problem that fertilizer utilization rate is not high,strip and broadcast fertilizer are the main fertilization methods in China,a new method for identification and location of maize canopy in seedling stage was proposed,which could identify and locate the canopy centroid of maize in seedling stage under farmland environment. In order to locate the maize plant position quickly,the maize canopy was identified by the method of deep learning,and then the centroid location of the identified area was calculated. Firstly,Faster R-CNN was used to identify the seedling maize canopy in the field environment. Then the centroid detection algorithm based on the linear property of differential inner product improved the centroid location method of maize canopy. After the corn canopy and the weeds were segmented,the centroid of maize canopy was located and the pixel coordinates of maize seedling centroid were obtained. Through the verification in the actual farmland environment,the accuracy of identification and positioning of the canopy centroid reached 92. 9%. The average detection time of a frame image was 0. 17 s. The positioning error of the canopy centroid was less than 1 pixel.Through the analysis of the test results,the research results can provide information support for the positioning fertilization and research basis for the follow-up variable fertilization operations,so as to achieve the production goal of saving fertilizer and increasing efficiency.
引文
[1]赵春江,薛绪掌,王秀,等.精准农业技术体系的研究进展与展望[J].农业工程学报,2003,19(4):7-12.ZHAO Chunjiang,XUE Xuzhang,WANG Xiu,et al.Advance and prospects of precision agriculture technology system[J].Transactions of the CSAE,2003,19(4):7-12.(in Chinese)
[2]姜靖,刘永功.美国精准农业发展经验及对我国的启示[J].科学管理研究,2018,36(5):117-120.JIANG Jing,LIU Yonggong.Experience of precision agriculture development in US and inspiration to China[J].Scientific Management Research,2018,36(5):117-120.(in Chinese)
[3]李欣倪,张文爱,宋健,等.基于Android平台的变量施肥无线控制系统设计与试验[J].中国农机化学报,2019,40(3):165-172.LI Xinni,ZHANG Wen'ai,SONG Jian,et al.Design and experiment of variable rate fertilization wireless control system based on Android platform[J].Journal of Chinese Agricultural Mechanization,2019,40(3):165-172.(in Chinese)
[4]杨硕,王秀,翟长远,等.支持种肥监测的变量施肥系统设计与试验[J].农业机械学报,2018,49(10):145-153.YANG Shuo,WANG Xiu,ZHAI Changyuan,et al.Design and test on variable rate fertilization system supporting seeding and fertilizing monitoring[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):145-153.(in Chinese)
[5]齐兴源,周志艳,林蜀云,等.稻田气力式变量施肥机肥料喷撒器设计与试验[J].农业机械学报,2018,49(增刊):164-170.QI Xingyuan,ZHOU Zhiyan,LIN Shuyun,et al.Design of fertilizer spraying device of pneumatic variable-rate fertilizer applicator for rice production[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(Supp.):164-170.(in Chinese)
[6]安晓飞,王晓鸥,付卫强,等.四要素变量施肥机肥箱施肥量控制算法设计与试验[J].农业机械学报,2018,49(增刊):149-154.AN Xiaofei,WANG Xiaoou,FU Weiqiang,et al.Design and experiment of fertilizer amount control algorithm in four factors variable rate fertilization system[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(Supp.):149-154.(in Chinese)
[7]王相友,胡周勋,李学强,等.多回流式变量喷药控制系统设计与试验[J].农业机械学报,2019,50(2):123-131.WANG Xiangyou,HU Zhouxun,LI Xueqiang,et al.Design and experiment of multi-reflux variable spraying control system[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(2):123-131.(in Chinese)
[8]牛丛,徐丽明,马帅,等.变量喷药技术的应用现状与发展[J].农业装备与车辆工程,2018,56(12):1-4.NIU Cong,XU Liming,MA Shuai,et al.Application and development of variable spray technology[J].Agricultural Equipment&Vehicle Engineering,2018,56(12):1-4.(in Chinese)
[9]蔡吉晨.基于二维激光雷达的果树在线探测方法及对靶变量喷药技术研究[D].北京:中国农业大学,2018.CAI Jichen.Research on tree on-line detection method and targeted variable-rate spraying techniques based on laser-scanning sensor[D].Beijing:China Agricultural University,2018.(in Chinese)
[10]杨洋,张亚兰,苗伟,等.基于卷积神经网络的玉米根茎精确识别与定位研究[J].农业机械学报,2018,49(10):46-53.YANG Yang,ZHANG Yalan,MIAO Wei,et al.Accurate identification and location of corn rhizome based on Faster R-CNN[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):46-53.(in Chinese)
[11]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].农业机械学报,2017,48(2):38-44.SONG Yu,LIU Yongbo,LIU Lu,et al.Extraction method of navigation baseline of corn roots based on machine vision[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(2):38-44.(in Chinese)
[12]赵春江,杨信廷,李斌,等.中国农业信息技术发展回顾及展望[J].中国农业文摘-农业工程,2018,30(4):3-7.ZHAO Chunjiang,YANG Xinting,LI Bin,et al.The retrospect and prospect of agricultural information technology in China[J].Agricultural Science and Engineering in China,2018,30(4):3-7.(in Chinese)
[13]IMANOV E,ALZOUHBI A K.Machine learning comparative analysis for plant classification[M].CHAM:Springer International Publishing AG,2019:586-593,896.
[14]NAKARMI A D,TANG L.Automatic inter-plant spacing sensing at early growth stages using a 3D vision sensor[J].Computers&Electronics in Agriculture,2012,82(1):23-31.
[15]YANG Shanjie,MEI Shuli,ZHANG Yane.Detection of maize navigation centerline based on machine vision[J].IFAC-Papers On Line,2018,51(17):570-575.
[16]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.JIANG Yu,CUI Hongwei,QU Yinggang,et al.Positioning method of rice seedlings based on edge fitting in separated region of stem base[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(6):23-31.(in Chinese)
[17]李航.玉米苗基部图像定位方法设计[D].沈阳:沈阳农业大学,2017.LI Hang.Maize seedling base image positioning method design[D].Shenyang:Shenyang Agricultural University,2017.(in Chinese)
[18]郭孟杰.基于图像处理的番茄茎根部生长结构参数提取[D].沈阳:沈阳农业大学,2016.GUO Mengjie.Extraction of tomato stem root growth structure parameter based on digital image processing[D].Shenyang:Shenyang Agricultural University,2016.(in Chinese)
[19]刁智华,赵明珍,宋寅卯,等.基于机器视觉的玉米精准施药系统作物行识别算法及系统实现[J].农业工程学报,2015,31(7):47-52.DIAO Zhihua,ZHAO Mingzhen,SONG Yinmao,et al.Crop line recognition algorithm and realization in precision pesticide system based on machine vision[J].Transactions of the CSAE,2015,31(7):47-52.(in Chinese)
[20]魏帅均,张彦娥,梅树立.基于俯视图像的玉米株心快速识别方法研究[J].农业机械学报,2017,48(增刊):136-141.WEI Shuaijun,ZHANG Yan'e,MEI Shuli.Fast recognition method of maize core based on top view image[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):136-141.(in Chinese)
[21]JIAN Jin,TANG Lie.Corn plant sensing using real-time stereo vision[J].Journal of Field Robotics,2010,26(6-7):591-608.
[22]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.HU Lian,LUO Xiwen,ZENG Shan,et al.Plant recongnition and localization for intra-row mechanical weeding device based on machine vision[J].Transactions of the CSAE,2013,29(10):12-18.(in Chinese)
[23]雷蕾,李言俊,张科.图像目标质心快速搜索算法[J].红外技术,2007,29(9):548-551.LEI Lei,LI Yanjun,ZHANG Ke.A fast algorithm for searching object centriods in binary images[J].Infrared Technology,2007,29(9):548-551.(in Chinese)
[24]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Trans.Pattern Anal.Mach.Intell.,2017,39(6):1137-1149.
[25]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2014.
[26]GIRSHICK R.Fast R-CNN[C]∥IEEE International Conference on Computer Vision,2015.
[27]宋克欧,黄凤岗,兰晓亭.二值图像目标质心快速搜索跟踪算法[J].模式识别与人工智能,1998,11(2):161-168.SONG Keou,HUANG Fenggang,LAN Xiaoting.A fast algorithm for searching and tracking object centroids in binary images[J].Pattern Recognition and Artificial Intelligence,1998,11(2):161-168.(in Chinese)
[2]姜靖,刘永功.美国精准农业发展经验及对我国的启示[J].科学管理研究,2018,36(5):117-120.JIANG Jing,LIU Yonggong.Experience of precision agriculture development in US and inspiration to China[J].Scientific Management Research,2018,36(5):117-120.(in Chinese)
[3]李欣倪,张文爱,宋健,等.基于Android平台的变量施肥无线控制系统设计与试验[J].中国农机化学报,2019,40(3):165-172.LI Xinni,ZHANG Wen'ai,SONG Jian,et al.Design and experiment of variable rate fertilization wireless control system based on Android platform[J].Journal of Chinese Agricultural Mechanization,2019,40(3):165-172.(in Chinese)
[4]杨硕,王秀,翟长远,等.支持种肥监测的变量施肥系统设计与试验[J].农业机械学报,2018,49(10):145-153.YANG Shuo,WANG Xiu,ZHAI Changyuan,et al.Design and test on variable rate fertilization system supporting seeding and fertilizing monitoring[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):145-153.(in Chinese)
[5]齐兴源,周志艳,林蜀云,等.稻田气力式变量施肥机肥料喷撒器设计与试验[J].农业机械学报,2018,49(增刊):164-170.QI Xingyuan,ZHOU Zhiyan,LIN Shuyun,et al.Design of fertilizer spraying device of pneumatic variable-rate fertilizer applicator for rice production[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(Supp.):164-170.(in Chinese)
[6]安晓飞,王晓鸥,付卫强,等.四要素变量施肥机肥箱施肥量控制算法设计与试验[J].农业机械学报,2018,49(增刊):149-154.AN Xiaofei,WANG Xiaoou,FU Weiqiang,et al.Design and experiment of fertilizer amount control algorithm in four factors variable rate fertilization system[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(Supp.):149-154.(in Chinese)
[7]王相友,胡周勋,李学强,等.多回流式变量喷药控制系统设计与试验[J].农业机械学报,2019,50(2):123-131.WANG Xiangyou,HU Zhouxun,LI Xueqiang,et al.Design and experiment of multi-reflux variable spraying control system[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(2):123-131.(in Chinese)
[8]牛丛,徐丽明,马帅,等.变量喷药技术的应用现状与发展[J].农业装备与车辆工程,2018,56(12):1-4.NIU Cong,XU Liming,MA Shuai,et al.Application and development of variable spray technology[J].Agricultural Equipment&Vehicle Engineering,2018,56(12):1-4.(in Chinese)
[9]蔡吉晨.基于二维激光雷达的果树在线探测方法及对靶变量喷药技术研究[D].北京:中国农业大学,2018.CAI Jichen.Research on tree on-line detection method and targeted variable-rate spraying techniques based on laser-scanning sensor[D].Beijing:China Agricultural University,2018.(in Chinese)
[10]杨洋,张亚兰,苗伟,等.基于卷积神经网络的玉米根茎精确识别与定位研究[J].农业机械学报,2018,49(10):46-53.YANG Yang,ZHANG Yalan,MIAO Wei,et al.Accurate identification and location of corn rhizome based on Faster R-CNN[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(10):46-53.(in Chinese)
[11]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].农业机械学报,2017,48(2):38-44.SONG Yu,LIU Yongbo,LIU Lu,et al.Extraction method of navigation baseline of corn roots based on machine vision[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(2):38-44.(in Chinese)
[12]赵春江,杨信廷,李斌,等.中国农业信息技术发展回顾及展望[J].中国农业文摘-农业工程,2018,30(4):3-7.ZHAO Chunjiang,YANG Xinting,LI Bin,et al.The retrospect and prospect of agricultural information technology in China[J].Agricultural Science and Engineering in China,2018,30(4):3-7.(in Chinese)
[13]IMANOV E,ALZOUHBI A K.Machine learning comparative analysis for plant classification[M].CHAM:Springer International Publishing AG,2019:586-593,896.
[14]NAKARMI A D,TANG L.Automatic inter-plant spacing sensing at early growth stages using a 3D vision sensor[J].Computers&Electronics in Agriculture,2012,82(1):23-31.
[15]YANG Shanjie,MEI Shuli,ZHANG Yane.Detection of maize navigation centerline based on machine vision[J].IFAC-Papers On Line,2018,51(17):570-575.
[16]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.JIANG Yu,CUI Hongwei,QU Yinggang,et al.Positioning method of rice seedlings based on edge fitting in separated region of stem base[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(6):23-31.(in Chinese)
[17]李航.玉米苗基部图像定位方法设计[D].沈阳:沈阳农业大学,2017.LI Hang.Maize seedling base image positioning method design[D].Shenyang:Shenyang Agricultural University,2017.(in Chinese)
[18]郭孟杰.基于图像处理的番茄茎根部生长结构参数提取[D].沈阳:沈阳农业大学,2016.GUO Mengjie.Extraction of tomato stem root growth structure parameter based on digital image processing[D].Shenyang:Shenyang Agricultural University,2016.(in Chinese)
[19]刁智华,赵明珍,宋寅卯,等.基于机器视觉的玉米精准施药系统作物行识别算法及系统实现[J].农业工程学报,2015,31(7):47-52.DIAO Zhihua,ZHAO Mingzhen,SONG Yinmao,et al.Crop line recognition algorithm and realization in precision pesticide system based on machine vision[J].Transactions of the CSAE,2015,31(7):47-52.(in Chinese)
[20]魏帅均,张彦娥,梅树立.基于俯视图像的玉米株心快速识别方法研究[J].农业机械学报,2017,48(增刊):136-141.WEI Shuaijun,ZHANG Yan'e,MEI Shuli.Fast recognition method of maize core based on top view image[J].Transactions of the Chinese Society for Agricultural Machinery,2017,48(Supp.):136-141.(in Chinese)
[21]JIAN Jin,TANG Lie.Corn plant sensing using real-time stereo vision[J].Journal of Field Robotics,2010,26(6-7):591-608.
[22]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.HU Lian,LUO Xiwen,ZENG Shan,et al.Plant recongnition and localization for intra-row mechanical weeding device based on machine vision[J].Transactions of the CSAE,2013,29(10):12-18.(in Chinese)
[23]雷蕾,李言俊,张科.图像目标质心快速搜索算法[J].红外技术,2007,29(9):548-551.LEI Lei,LI Yanjun,ZHANG Ke.A fast algorithm for searching object centriods in binary images[J].Infrared Technology,2007,29(9):548-551.(in Chinese)
[24]REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Trans.Pattern Anal.Mach.Intell.,2017,39(6):1137-1149.
[25]GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2014.
[26]GIRSHICK R.Fast R-CNN[C]∥IEEE International Conference on Computer Vision,2015.
[27]宋克欧,黄凤岗,兰晓亭.二值图像目标质心快速搜索跟踪算法[J].模式识别与人工智能,1998,11(2):161-168.SONG Keou,HUANG Fenggang,LAN Xiaoting.A fast algorithm for searching and tracking object centroids in binary images[J].Pattern Recognition and Artificial Intelligence,1998,11(2):161-168.(in Chinese)