[1]承达瑜,武择鹏,付春晓,等.融合无人机多源遥感数据的冬小麦株高估测[J].江苏农业学报,2025,(11):2209-2221.[doi:doi:10.3969/j.issn.1000-4440.2025.11.014]
　CHENG Dayu,WU Zepeng,FU Chunxiao,et al.Estimation of winter wheat plant height based on multi-source remote sensing data from an unmanned aerial vehicle[J].,2025,(11):2209-2221.[doi:doi:10.3969/j.issn.1000-4440.2025.11.014]
点击复制

融合无人机多源遥感数据的冬小麦株高估测()

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年11期
页码:
2209-2221
栏目:
农业信息工程
出版日期:
2025-11-30

文章信息/Info

Title:
Estimation of winter wheat plant height based on multi-source remote sensing data from an unmanned aerial vehicle
作者:
承达瑜1; 2; 武择鹏1; 付春晓3; 赵安周1; 王建东4; 何伟德1
(1.河北工程大学矿业与测绘工程学院,河北邯郸056038；2.河北省水生态文明及社会治理研究中心,河北邯郸056038；3.河北工程大学水利水电学院,河北邯郸056038；4.中国农业科学院农业环境与可持续发展研究所,北京100081)
Author(s):
CHENG Dayu1; 2; WU Zepeng1; FU Chunxiao3; ZHAO Anzhou1; WANG Jiandong4; HE Weide1
(1.School of Mining and Geomatics, Hebei University of Engineering, Handan 056038, China;2.Research Center of Water Ecological Civilization and Social Governance of Hebei Provincial, Handan 056038, China;3.School of Water Conservancy and Hydroelectric Power, Hebei University of Engineering, Handan 056038, China;4.Institute of Environment and Sustainable Development in Agriculture, Chinese Academy of Agricultural Sciences, Beijing 100081, China)
关键词:
冬小麦; 株高估测; 多源遥感数据
Keywords:
winter wheat; estimation of plant height; multi-source remote sensing data
分类号:
S512+1;TP79
DOI:
doi:10.3969/j.issn.1000-4440.2025.11.014
文献标志码:
A
摘要:
及时、高效地获取冬小麦株高信息对优化其生产管理方案具有重要参考作用。为提高小麦株高反演效果,本研究利用多光谱影像数据提取的植被指数、纹理特征参数及正射影像提取的冬小麦株高数据,结合随机森林(Random forest,RF)、支持向量机(Support vector regression,SVR)和偏最小二乘回归(Partial least squares regre-ssion,PLSR)等算法,提出一种融合无人机多源遥感数据的冬小麦株高估测方法。首先利用正射影像数据提取数字表面模型(DSM),计算不同生长期的冬小麦株高(Winter wheat plant height,WWPH)数据；再基于多光谱影像数据和地面实测株高数据,经过相关性分析,筛选出适用于建立估测模型的植被指数和纹理特征参数；然后,基于植被指数+纹理特征+WWPH数据和植被指数+WWPH数据等不同输入数据组合,利用RF算法、SVR算法和PLSR算法构建小麦株高估测模型,根据模型性能的比较,筛选出小麦株高估测适宜的特征数据输入组合和算法,最后根据适宜的特征数据组合和算法进行试验区域小麦株高的估测。结果表明:基于植被指数+WWPH数据+纹理特征组合,利用RF算法构建的小麦株高估算模型对拔节期和抽穗期小麦株高的估测精度均最高,测试集的决定系数（R2)分别为0872和0887,均方根差(RMSE)分别为1731 cm和1335 cm。利用适宜的特征数据组合和算法估测得到研究区域拔节期冬小麦株高为40.46～5261 cm,试验区域内小麦株高差异较大,而抽穗期小麦株高为60.32～7194 cm,试验区域内小麦株高总体较均匀,估测结果与田间实测结果基本一致。
Abstract:
The timely and efficient acquisition of winter wheat plant height information plays a crucial role as a reference for optimizing its production management strategies. To improve the inversion accuracy of wheat plant height, this study proposed a method based on unmanned aerial vehicle (UAV) multi-source remote sensing data. It utilized the vegetation indices and texture feature parameters extracted from multispectral imagery, combined with the plant height data derived from the orthophoto, and integrated random forest (RF), support vector regression (SVR), and partial least squares regression (PLSR) algorithms. First, a digital surface model (DSM) was extracted from the orthophoto data and utilized to calculate the winter wheat plant height (WWPH) at different growth stages. Based on multispectral imagery and ground-measured plant height data, vegetation indices and textural feature parameters suitable for constructing the estimation model were selected through correlation analysis. Then, based on different input combinations such as vegetation indices + texture features + WWPH data and vegetation indices + WWPH data, winter wheat plant height estimation models were constructed using the RF, SVR, and PLSR algorithms. Based on the comparison of model performance, the optimal combination of input features and the most suitable algorithm for wheat plant height estimation were selected. Finally, the estimation of wheat plant height in the experimental area was conducted using the optimal feature combination and algorithm. The results indicated that the wheat plant height estimation model, which was developed using the combination of vegetation indices, WWPH data and texture features based on the RF algorithm, achieved the highest accuracy for both the jointing and heading stages. For the testing set, the coefficients of determination (R2) were 0.872 and 0.887, and the root mean square errors (RMSE) were 1.731 cm and 1.335 cm, respectively. Using the optimal feature combination and algorithm, the estimated plant height in the study area ranged from 40.46 cm to 52.61 cm at the jointing stage, exhibiting significant spatial variability. In contrast, the estimated height at the heading stage ranged from 60.32 cm to 71.94 cm, showing a more uniform spatial distribution. These estimation results were in close agreement with the field-measured data.

参考文献/References:

[1]郭涛,颜安,耿洪伟. 基于无人机影像的小麦株高与LAI预测研究[J]. 麦类作物学报,2020,40(9):1129-1140.
[2]申华磊,苏歆琪,赵巧丽,等. 基于深度学习的无人机遥感小麦倒伏面积提取方法[J]. 农业机械学报,2022,53(9):252-260,341.
[3]LU N, ZHOU J, HAN Z X, et al. Improved estimation of aboveground biomass in wheat from RGB imagery and point cloud data acquired with a low-cost unmanned aerial vehicle system[J]. Plant Methods,2019,15:17.
[4]TAO H L, FENG H K, XU L J, et al. Estimation of the yield and plant height of winter wheat using UAV-based hyperspectral images[J]. Sensors,2020,20(4):1231.
[5]GOMEZ-GARCIA D, RODRIGUEZ-MORALES F, WELCH S, et al. High-throughput phenotyping of wheat canopy height using ultrawideband radar:first results[J]. IEEE Geoscience and Remote Sensing Letters,2020,19:3500105.
[6]MALAMBO L, POPESCU S C, MURRAY S C, et al. Multitemporal field-based plant height estimation using 3D point clouds gene-rated from small unmanned aerial systems high-resolution imagery[J]. International Journal of Applied Earth Observation and Geoinformation,2018,64:31-42.
[7]周梦维,柳钦火,刘强,等. 基于机载小光斑全波形LIDAR的作物高度反演[J]. 农业工程学报,2010,26(8):183-188.
[8]刘治开,牛亚晓,王毅,等. 基于无人机可见光遥感的冬小麦株高估算[J]. 麦类作物学报,2019,39(7):859-866.
[9]梁永检,吴文志,施泽升,等. 基于无人机RGB遥感的甘蔗株高估测[J]. 作物杂志,2023(1):226-232.
[10]张建,谢田晋,杨万能,等. 近地遥感技术在大田作物株高测量中的研究现状与展望[J]. 智慧农业（中英文）,2021,3(1):1-15.
[11]刘建春,陈思,文波龙,等. 基于无人机多光谱遥感的水稻株高估测方法[J]. 遥感信息,2023,38(3):61-68.
[12]李燕强,张娟娟,熊淑萍,等. 不同冬小麦品种株高的高光谱估算模型[J]. 麦类作物学报,2012,32(3):523-529.
[13]谢田晋. 基于无人机遥感的作物高度获取方法评估[D]. 武汉:华中农业大学,2021.
[14]吴婷婷,刘昕哲,聂睿琪,等. 基于细粒度校正的育种小区小麦株高无人机测量方法[J]. 农业机械学报,2023,54(6):158-167.
[15]郭燕,贺佳,曾凯,等. 基于无人机数字表面模型的冬小麦生物量估算模型构建及迁移能力分析[J]. 干旱区资源与环境,2024,38(9):97-105.
[16]承达瑜,何伟德,付春晓,等. 融合无人机光谱信息与纹理特征的冬小麦综合长势监测[J]. 农业机械学报,2024,55(9):249-261.
[17]杨静,张亚杰,陈金威,等. 基于MODIS数据的三种植被指数在海南岛植被监测中的适用性研究[J]. 干旱气象,2024,42(2):274-282.
[18]刘洋,李强子,杜鑫,等. 不同样本集划分策略对农作物遥感分类精度的影响[J]. 河南农业科学,2024,53(6):144-153.
[19]CARLSON T N, RIPLEY D A. On the relation between NDVI,fractional vegetation cover,and leaf area index[J]. Remote Sensing of Environment,1997,62(3):241-252.
[20]YANG C H, EVERITT J H, BRADFORD J M, et al. Airborne hyperspectral imagery and yield monitor data for mapping cotton yield variability[J]. Precision Agriculture,2004,5(5):445-461.
[21]GITELSON A A, KAUFMAN Y J, MERZLYAK M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sensing of Environment,1996,58(3):289-298.
[22]SELVARAJ M G, VALDERRAMA M, GUZMAN D, et al. Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)[J]. Plant Methods,2020,16:87.
[23]ZHANG J Y, QIU X L, WU Y T, et al. Combining texture,color,and vegetation indices from fixed-wing UAS imagery to estimate wheat growth parameters using multivariate regression methods[J]. Computers and Electronics in Agriculture,2021,185:106138.
[24]解毅,王佳楠,刘钰. 基于Sentinel-1/2数据特征优选的冬小麦种植区识别方法研究[J]. 农业机械学报,2024,55(2):231-241.
[25]MONTANARO G, PETROZZA A, RUSTIONI L, et al. Phenotyping key fruit quality traits in olive using RGB images and back propagation neural networks[J]. Plant Phenomics,2023,5:61.
[26]LAMM R D, SLAUGHTER D C, GILES D K. Precision weed control system for cotton[J]. Transactions of the ASAE,2002,45(1):231-238.
[27]VARELA S, PEDERSON T, BERNACCHI C J, et al. Understanding growth dynamics and yield prediction of Sorghum using high temporal resolution UAV imagery time series and machine learning[J]. Remote Sensing,2021,13(9):1763.
[28]ZHOU Y C, LAO C C, YANG Y L, et al. Diagnosis of winter-wheat water stress based on UAV-borne multispectral imaget exture and vegetation indices[J]. Agricultural Water Management,2021,256:107076.
[29]郭燕,王来刚,贺佳,等. 基于多层级特征筛选和无人机影像的冬小麦植株氮含量预测[J]. 农业工程学报,2024,40(12):174-182.
[30]BANNARI A, MORIN D, BONN F, et al. A review of vegetation indices[J]. Remote Sensing Reviews,1995,13(1/2):95-120.
[31]于明,郭志永,王岩. 基于计算机视觉的植物病害识别方法综述[J]. 科学技术与工程,2024,24(12):4811-4823.
[32]裴欢,孙天娇,王晓妍. 基于Landsat 8 OLI影像纹理特征的面向对象土地利用/覆盖分类[J]. 农业工程学报,2018,34(2):248-255.
[33]范军亮,王涵,廖振棋,等. 基于纹理-颜色特征与植被指数融合的冬小麦LAI估测[J]. 农业机械学报,2023,54(7):347-359.
[34]徐凡,李茂松,王春艳,等. 充分与非充分灌溉条件下冬小麦光合速率与产量的关系[J]. 中国农业气象,2009,30(增刊1):60-63，67.
[35]刘畅,杨贵军,李振海,等. 融合无人机光谱信息与纹理信息的冬小麦生物量估测[J]. 中国农业科学,2018,51(16):3060-3073.
[36]王强,许有鹏,杨龙,等. 太湖平原地区洪水特征变化及驱动机理[J]. 地理学报,2023,78(5):1088-1103.
[37]高越,布仁仓,熊在平,等. 基于气候时滞效应和空间异质性对中国植被总初级生产力的模拟[J]. 生态学报,2024,44(17):7615-7630.

相似文献/References:

[1]葛道阔,曹宏鑫,马晓群,等.基于作物生长模型的小麦旱涝敏感性分析与损失评估[J].江苏农业学报,2016,(06):1302.[doi:doi:10.3969/j.issn.1000-4440.2016.06.017]
　GE Dao-kuo,CAO Hong-xin,MA Xiao-qun,et al.Sensitivity analysis and damage assessment for wheat drought and waterlogged based on crop growth model[J].,2016,(11):1302.[doi:doi:10.3969/j.issn.1000-4440.2016.06.017]
[2]金正婷,李卫国,景元书.基于影像融合的冬小麦种植面积提取适宜尺度研究[J].江苏农业学报,2015,(06):1312.[doi:doi:10.3969/j.issn.1000-4440.2015.06.018]
　JIN Zheng-ting,LI Wei-guo,JING Yuan-shu.Appropriate extraction scale of winter wheat planting area based on image fusion[J].,2015,(11):1312.[doi:doi:10.3969/j.issn.1000-4440.2015.06.018]
[3]肇思迪,娄运生,庞渤,等.UV-B辐射增强下施硅对冬小麦光合特性和产量的影响[J].江苏农业学报,2017,(05):1036.[doi:doi:10.3969/j.issn.1000-4440.2017.05.012]
　ZHAO Si-di,LOU Yun-sheng,PANG Bo,et al.Effects of silicate application on photosynthesis and yield in winter wheat under elevated UV-B radiation[J].,2017,(11):1036.[doi:doi:10.3969/j.issn.1000-4440.2017.05.012]
[4]葛道阔,曹宏鑫,杨余旺,等.基于WCSODS的小麦旱涝灾损区域化监测与精细化评估[J].江苏农业学报,2017,(05):1062.[doi:doi:10.3969/j.issn.1000-4440.2017.05.016]
　GE Dao-kuo,CAO Hong-xin,YANG Yu-wang,et al.Regional monitoring and refined assessment for damage from wheat drought and waterlogging based on WCSODS[J].,2017,(11):1062.[doi:doi:10.3969/j.issn.1000-4440.2017.05.016]
[5]巫明焱,董光,税丽,等.基于Landsat 8影像的济宁市春季主要作物种植面积变化监测[J].江苏农业学报,2018,(03):559.[doi:doi:10.3969/j.issn.1000-4440.2018.03.012]
　WU Ming-yan,DONG Guang,SHUI Li,et al.Change detection of main spring crops area in Jining based on Landsat 8 images[J].,2018,(11):559.[doi:doi:10.3969/j.issn.1000-4440.2018.03.012]
[6]李卫国,顾晓鹤,葛广秀,等.县域冬小麦病害遥感监测信息系统研制[J].江苏农业学报,2019,(02):302.[doi:doi:10.3969/j.issn.1000-4440.2019.02.009]
　LI Wei-guo,GU Xiao-he,GE Guang-xiu,et al.Development of remote sensing monitoring information system for county scale winter wheat diseases[J].,2019,(11):302.[doi:doi:10.3969/j.issn.1000-4440.2019.02.009]
[7]单捷,孙玲,王志明,等.GF-1影像遥感监测指标与冬小麦长势参数的关系[J].江苏农业学报,2019,(06):1323.[doi:doi:10.3969/j.issn.1000-4440.2019.06.008]
　SHAN Jie,SUN Ling,WANG Zhi-ming,et al.Relationship between remote sensing monitoring indices and growth parameters in winter wheat based on GF-1 images[J].,2019,(11):1323.[doi:doi:10.3969/j.issn.1000-4440.2019.06.008]
[8]陶惠林,冯海宽,徐良骥,等.基于无人机高光谱遥感数据的冬小麦生物量估算[J].江苏农业学报,2020,(05):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
　TAO Hui-lin,FENG Hai-kuan,XU Liang-ji,et al.Winter wheat biomass estimation based on hyperspectral remote sensing data of unmanned aerial vehicle(UAV)[J].,2020,(11):1154.[doi:doi:10.3969/j.issn.1000-4440.2020.05.012]
[9]马美娟,陈小新,张云霞,等.分期播种冬小麦农田小气候特征及其生育状况分析[J].江苏农业学报,2021,(03):613.[doi:doi:10.3969/j.issn.1000-4440.2021.03.009]
　MA Mei-juan,CHEN Xiao-xin,ZHANG Yun-xia,et al.Analysis on field microclimate characteristics and growth of winter wheat under different sowing dates[J].,2021,(11):613.[doi:doi:10.3969/j.issn.1000-4440.2021.03.009]
[10]吴金芝,黄明,王志敏,等.干旱对冬小麦旗叶光合参数、产量和水分利用效率的影响[J].江苏农业学报,2021,(05):1108.[doi:doi:10.3969/j.issn.1000-4440.2021.05.003]
　WU Jin-zhi,HUANG Ming,WANG Zhi-min,et al.Effects of drought on flag leaf photosynthetic parameters, grain yield and water use efficiency in winter wheat[J].,2021,(11):1108.[doi:doi:10.3969/j.issn.1000-4440.2021.05.003]

备注/Memo

备注/Memo:
收稿日期：2024-12-12基金项目：河北省重大科技成果转化专项(22287401Z)；国家自然科学基金项目(42171212)作者简介：承达瑜(1980-),男,江苏常州人,博士,副教授,研究方向为地理大数据挖掘、作物长势遥感监测及计算机视觉。(E-mail)yuyumails@126.com通讯作者：付春晓,(E-mail)chunxiao999999@163.com
更新日期/Last Update: 2025-12-18