|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | 基于可见光图像和卷积神经网络的冬小麦苗期长势参数估算显示文摘针对目前基于计算机视觉估算冬小麦苗期长势参数存在易受噪声干扰且对人工特征依赖性较强的问题,该文综合运用图像处理和深度学习技术,提出一种基于卷积神经网络(convolutional neural network, CNN)的冬小麦苗期长势参数估算方法。以冬小麦苗期冠层可见光图像作为输入,构建了适用于冬小麦苗期长势参数估算卷积神经网络模型,通过学习的方式建立冬小麦冠层可见光图像与长势参数的关系,实现了农田尺度冬小麦苗期冠层叶面积指数(leaf area index,LAI)和地上生物量(above ground biomass, AGB)的准确估算。为验证方法的有效性,该研究采用以冠层覆盖率(canopy cover, CC)作为自变量的线性回归模型和以图像特征为输入的随机森林(random forest, RF)、支持向量机回归(support vectormachinesregression,SVM)进行对比分析,采用决定系数(coefficientofdetermination,R2)和归一化均方根误差(normalized root mean square error, NRMSE)定量评价估算方法的准确率。结果表明:该方法估算准确率均优于对比方法,其中AGB估算结果的R2为0.7917,NRMSE为24.37%,LAI估算结果的R2为0.8256,NRMSE为23.33%。研究可为冬小麦苗期长势监测与田间精细管理提供参考。 | 马浚诚 刘红杰 郑飞翔 杜克明 张领先 胡新 孙忠富 | 2019 | 农业工程学报2019，35，5： | 20 |
| 2 | 基于RGB图像与深度学习的冬小麦田间长势参数估算系统显示文摘为准确、快速获取冬小麦田间长势信息,该研究设计并实现了一种基于深度学习的冬小麦田间长势参数估算系统。该系统主要包含长势参数估算模块和麦穗计数模块。长势参数估算模块基于残差网络ResNet18构建长势参数估算模型,实现了冬小麦苗期叶面积指数(Leaf Area Index,LAI)和地上生物量(Above Ground Biomass,AGB)的估算,并基于迁移学习进行泛化能力测试;麦穗计数模块基于Faster R-CNN并结合非极大值抑制(Non Maximum Suppression,NMS)构建麦穗计数模型,实现了开花期麦穗准确计数。结果表明,针对2017—2018和2018—2019两个生长季数据,基于ResNet18的长势参数估算模型对LAI估算的决定系数分别为0.83和0.80,对AGB估算的决定系数均为0.84,优于基于传统卷积神经网络(Convolutional Neural Networks,CNN)、VGG16和GoogLeNet构建的估算模型,并且泛化能力测试表明该模型对数据的季节性差异具有鲁棒性。基于Faster R-CNN的麦穗计数模型,在利用NMS优化后决定系数从0.66增至0.83,提升了25.8%,NRMSE从0.19降至0.05,下降了73.7%。相较于基于CNN构建的分类计数模型,基于Faster R-CNN+NMS的麦穗计数模型表现更优,决定系数为0.83,提升了33.9%,单个麦穗识别时间为1.009 s,效率提升了20.7%。综上所述,该系统能够满足冬小麦田间长势参数估算需求,可为冬小麦田间精细化管理提供支撑。 | 李云霞 马浚诚 刘红杰 张领先 | 2021 | 农业工程学报2021，37，24： | 8 |
| 3 | 数字图像估测棉花光合有效辐射吸收比例显示文摘研究利用数字图像技术估测棉花光合有效辐射吸收比例的方法,以期为棉花生长状况的动态监测提供依据。2013-2014年设置不同株行距配置试验,在棉花关键生育时期通过数码相机、线性光量子传感器分别测定棉花覆盖度和光合有效辐射吸收比例。结果表明,不同配置方式下,fCover和fAPAR的季节变化规律基本一致,生育后期由于非绿色器官的增多致使低估fCover;fCover与fIPAR和fAPAR呈线性的极显著正相关,与LAI和干物质呈指数的极显著正相关;综合分析2a数据,建立图像覆盖度估测fAPAR的模型(R2=0.895,SE=0.076);根据独立试验数据对估测模型进行检验的结果显示,模型的决定系数(R2=0.964)较高且预测误差(RMSE=0.058)较小。因此,图像覆盖度是一种简便、快捷、有效地估测棉花光合有效辐射吸收比例的方法。 | 王方永 韩焕勇 陈兵 孔宪辉 林海 余渝 宁新柱 王琼 | 2015 | 西北农业学报2015，24，10： | 5 |
| 4 | Growth monitoring of greenhouse lettuce based on a convolutional neural network显示文摘Growth-related traits,such as aboveground biomass and leaf area,are critical indicators to characterize the growth of greenhouse lettuce.Currently,nondestructive methods for estimating growth-related traits are subject to limitations in that the methods are susceptible to noise and heavily rely on manually designed features.In this study,a method for monitoring the growth of greenhouse lettuce was proposed by using digital images and a convolutional neural network(CNN).Taking lettuce images as the input,a CNN model was trained to learn the relationship between images and the corresponding growth-related traits,i.e.,leaf fresh weight(LFW),leaf dry weight(LDW),and leaf area(LA).To compare the results of the CNN model,widely adopted methods were also used.The results showed that the values estimated by CNN had good agreement with the actual measurements,with R^(2) values of 0.8938,0.8910,and 0.9156 and normalized root mean square error(NRMSE)values of 26.00,22.07,and 19.94%,outperforming the compared methods for all three growth-related traits.The obtained results showed that the CNN demonstrated superior estimation performance for the flat-type cultivars of Flandria and Tiberius compared with the curled-type cultivar of Locarno.Generalization tests were conducted by using images of Tiberius from another growing season.The results showed that the CNN was still capable of achieving accurate estimation of the growth-related traits,with R2 values of 0.9277,0.9126,and 0.9251 and NRMSE values of 22.96,37.29,and 27.60%.The results indicated that a CNN with digital images is a robust tool for the monitoring of the growth of greenhouse lettuce. | Lingxian Zhang Zanyu Xu Dan Xu Juncheng Ma Yingyi Chen Zetian Fu | 2020 | Horticulture Research2020，7，1： | 2 |
| 5 | 基于无人机多源遥感的玉米LAI垂直分布估算显示文摘为探究无人机多源遥感影像估算玉米叶面积指数(Leaf area index,LAI)垂直分布,在田间设置了密度和播期试验,在7个生育时期利用无人机采集了可见光、多光谱和热红外影像并同步获取玉米LAI垂直分布数据。同时,为合理制定无人机飞行任务,分析了不同飞行高度和不同太阳高度角下获取的无人机影像对估算玉米LAI的影响。基于无人机影像提取的与玉米LAI相关性较高的植被指数、纹理信息和冠层温度等特征,利用7种机器学习方法分别构建了玉米冠层不同高度LAI估算模型,从中选取鲁棒性强的2个模型用于分析在不同飞行高度和不同太阳高度角下估算LAI的差异。研究结果表明,MLPR和RFR模型对玉米LAI估算鲁棒性最强,全生育期下模型rRMSE为11.31%(MLPR)和11.42%(RFR)。玉米冠层LAI垂直分布估算误差,所有模型的平均rRMSE分别为9.1%(LAI-1)、14.19%(LAI-2)、18.62%(LAI-3)、23.29%(LAI-4)和26.7%(LAI-5)。对于玉米穗位叶及以下部位的LAI估算误差均在20%以下,得到了较好精度。同时,在不同飞行高度和太阳高度角试验中可以得出,当飞行高度为30 m时LAI估算精度最高,R^(2)为0.73,rRMSE为10.97%,在09:00—10:00观测的玉米LAI估算精度最高。无人机多源遥感影像数据可以准确估算玉米冠层LAI垂直分布,及时掌握玉米功能叶片LAI长势差异,可为玉米品种筛选提供辅助。 | 刘帅兵 金秀良 冯海宽 聂臣巍 白怡 余汛 | 2023 | 农业机械学报2023，54，5： | 2 |
| 6 | Impact of Varying Light and Dew on Ground Cover Estimates from Active NDVI,RGB,and LiDAR显示文摘Canopy ground cover(GC)is an important agronomic measure for evaluating crop establishment and early growth.This study evaluates the reliability of GC estimates,in the presence of varying light and dew on leaves,from three different ground-based sensors:(1)normalized difference vegetation index(NDVI)from the commercially available GreenSeeker®;(2)RGB images from a digital camera,where GC was determined as the portion of pixels from each image meeting a greenness criterion(i.e.,ðGreen−RedÞ/ðGreen+RedÞ>0);and(3)LiDAR using two separate approaches:(a)GC from LiDAR red reflectance(whereby red reflectance less than five was classified as vegetation)and(b)GC from LiDAR height(whereby height greater than 10 cm was classified as vegetation).Hourly measurements were made early in the season at two different growth stages(tillering and stem elongation),among wheat genotypes highly diverse for canopy characteristics.The active NDVI showed the least variation through time and was particularly stable,regardless of the available light or the presence of dew.In addition,between-sample-time Pearson correlations for NDVI were consistently high and significant(P<0:0001),ranging from 0.89 to 0.98.In comparison,GC from LiDAR and RGB showed greater variation across sampling times,and LiDAR red reflectance was strongly influenced by the presence of dew.Excluding times when the light was exceedingly low,correlations between GC from RGB and NDVI were consistently high(ranging from 0.79 to 0.92).The high reliability of the active NDVI sensor potentially affords a high degree of flexibility for users by enabling sampling across a broad range of acceptable light conditions. | David M.Deery David J.Smith Robert Davy Jose A.Jimenez-Berni Greg J.Rebetzke Richard A.James | 2021 | Plant Phenomics2021，3，1： | 0 |
| 7 | 基于卷积神经网络特征提取的莴苣生长无损监测显示文摘基于计算机视觉的莴苣生长无损监测对莴苣的种植管理有重要的意义。彩色图像包含的纹理、色泽等信息与莴苣生长参数密切相关。以往的研究包括基于人为设计的特征结合机器学习算法估计生长参数,以及通过卷积网络估计生长参数。该文设计了一种结合卷积神经网络和机器学习模型的二阶段算法,用于莴苣的生长参数无损估计。生长参数包括叶片鲜重(LFW)、叶片干重(LDW)、植株高度(H)、植株直径(D)和叶面积(LA)。算法的第一阶段训练卷积网络自动从图像中提取特征,第二阶段基于卷积网络提取的特征,利用集成机器学习算法Stacking(随机森林,深度森林)估计生长参数。实验结果表明,相比直接使用卷积网络估计,设计的二阶段算法能显著降低误差,在五个生长参数上的归一化均方误差(NMSE)分别为2.25%,2.61%,1.63%,0.84%,3.18%,估计值与真实值的决定系数(R 2)为0.9552,0.9578,0.8921,0.8844,0.9362。通过引入深度图,使用3D卷积网络从彩色图和深度图的组合中提取特征,高度(H)的估计准确度能进一步提高(NMSE:1.27%,R ^(2):0.9161)。表明通过卷积神经网络自动从图片中提取特征并结合集成机器学习算法用于莴苣的生长参数估计是可行的。 | 阳昊 黄超 刘欣然 王中举 王龙 | 2023 | 计算机技术与发展2023，33，8： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员