基于无人机图像颜色与纹理特征的小麦不同生育时期生物量估算

doi:10.12133/j.smartag.SA202202004

摘要/Abstract

摘要：

为实现小麦生物量田间快速无损监测，开展基于不同密度、氮肥和品种处理的田间试验，应用无人机获取小麦越冬前期、拔节期、孕穗期和开花期4个时期的RGB图像，通过影像处理获取小麦颜色指数和纹理特征参数，并同时期通过田间取样获取小麦生物量；分析不同颜色指数和纹理特征参数与小麦生物量的关系，筛选出适合小麦生物量估算的颜色和纹理特征指数。结果表明，不同时期图像颜色指数和小麦生物量均有较高的相关性，且大部分达到极显著相关水平；图像纹理特征指数与小麦生物量的相关性较差，只有少数指标达到显著或极显著相关水平。基于上述结果，研究利用相关性最高的颜色指数或颜色指数与纹理特征指数结合构建小麦不同生育时期的生物量估算模型，并通过独立的实测生物量数据对模型进行了验证，模型模拟值与实测值之间的相关性均达到了极显著水平（P<0.01），RMSE均较小。其中，颜色指数模型在4个时期的R²分别为0.538、0.631、0.708和0.464，RMSE分别为27.88、516.99、868.26和1539.81 kg/ha。而颜色和纹理指数结合的模型在4个时期的R²分别为0.571、0.658、0.753和0.515，RMSE分别为25.49、443.20、816.25和1396.97 kg/ha，说明模型估算的结果是可靠的，且精度较高。同时结合无人机图像颜色和纹理特征指数的小麦生物量估测模型的效果要优于单一颜色指数模型。研究可为小麦田间长势实时监测与生物量估算提供新的手段。

关键词: 小麦, 无人机图像, 颜色指数, 纹理特征指数, 生物量, 纹理指数

Abstract:

In order to realize the rapid and non-destructive monitoring of wheat biomass, field wheat trials were conducted based on different densities, nitrogen fertilizers and varieties, and unmanned aerial vehicle (UAV) was used to obtain RGB images in the pre-wintering stage, jointing stage, booting stage and flowering stage of wheat. The color and texture feature indices of wheat were obtained using image processing, and wheat biomass was obtained by manual field sampling in the same period. Then the relationship between different color and texture feature indices and wheat biomass was analyzed to select the suitable feature index for wheat biomass estimation. The results showed that there was a high correlation between image color index and wheat biomass in different stages, the values of r were between 0.463 and 0.911 (P<0.05). However, the correlation between image texture feature index and wheat biomass was poor, only 5 index values reached significant or extremely significant correlation level. Based on the above results, the color indices with the highest correlation to wheat biomass or the combining indices of color and texture features in different growth stages were used to construct estimation model of wheat biomass. The models were validated using independently measured biomass data, and the correlation between simulated and measured values reached the extremely significant level (P<0.01), and root mean square error (RMSE) was smaller. The R² of color index model in the four stages were 0.538, 0.631, 0.708 and 0.464, and RMSE were 27.88, 516.99, 868.26 and 1539.81 kg/ha, respectively. The R² of the model combined with color and texture index were 0.571, 0.658, 0.753 and 0.515, and RMSE were 25.49, 443.20, 816.25 and 1396.97 kg/ha, respectively. This indicated that the estimated results using the models were reliable and accurate. It also showed that the estimation models of wheat biomass combined with color and texture feature indices of UAV images were better than the single color index models.

Key words: wheat, UAV?image, color?index, texture?feature?index, biomass, texture index

中图分类号:

S512

戴冕, 杨天乐, 姚照胜, 刘涛, 孙成明. 基于无人机图像颜色与纹理特征的小麦不同生育时期生物量估算[J]. 智慧农业(中英文), 2022, 4(1): 71-83.

DAI Mian, YANG Tianle, YAO Zhaosheng, LIU Tao, SUN Chengming. Wheat Biomass Estimation in Different Growth Stages Based on Color and Texture Features of UAV Images[J]. Smart Agriculture, 2022, 4(1): 71-83.

参考文献

1	WANG E. Study on remote sensing monitoring of maize growth and biomass[D]. Hefei: Anhui Agricultural University, 2018.
2	FAN Y, GONG Z, ZHAO W, et al. Study on vegetation biomass inversion method based on hyperspectral remote sensing[J]. Journal of Hebei Normal University(Natural Science Edition), 2016, 3: 267-271.
3	JIMENEZ-SIERRA D, CORREA E, BENíTEZ-RESTREPO H, et al. Novel feature-extraction methods for the estimation of above-ground biomass in rice crops[J]. Sensors, 2021, 21(13): 1-14.
4	HOU X, NIU Z, HUANG N, et al. The hyperspectral remote sensing estimation models of total biomass and true LAI of wheat[J]. Remote Sensing for Land & Resources, 2012, 24(4): 30-35.
5	LIU Q, PENG D, TU Y, et al. Estimating forest biomass by partial least squares regression[J]. Journal of Northeast Forestry University, 2014, 7: 44-47.
6	YUE J, ZHOU C, GUO W, et al. Estimation of winter-wheat above-ground biomass using the wavelet analysis of unmanned aerial vehicle-based digital images and hyperspectral crop canopy images[J]. International Journal of Remote Sensing, 2021, 42(5): 1602-1622.
7	LI J, SHI Y, VEERANAMPALAYAM-SIVAKUMAR A N, et al. Elucidating sorghum biomass, nitrogen and chlorophyll contents with spectral and morphological traits derived from unmanned aircraft system[J]. Frontiers in Plant Science, 2018, 9: 1-12.
8	GU Z, JU W, LI L, et al. Using vegetation indices and texture measures to estimate vegetation fractional coverage (VFC) of planted and natural forests in Nanjing city, China[J]. Advances in Space Research, 2013, 51(7): 1186-1194.
9	SARKER L R, NICHOL J E. Improved forest biomass estimates using ALOS AVNIR-2 texture indices[J]. Remote Sensing of Environment, 2011, 115(4): 968-977.
10	CAO Q, XU D, JU H. The biomass estimation of mangrove community based on the textural features and spectral information of TM images[J]. Forest Resources Management, 2010, 6: 102-108.
11	MU Q, GAO Z, BAO Y, et al. Estimation of sparse vegetation biomass based on grey-level co-occurrence matrix of vegetation indices[J]. Remote Sensing Information, 2016, 1: 58-63.
12	LIU C, YANG G, LI Z, et al. Biomass estimation in winter wheat by UAV spectral information and texture information fusion[J]. Scientia Agricultura Sinica, 2018, 51(16): 3060-3073.
13	LEE K J, LEE B W. Estimation of rice growth and nitrogen nutrition status using color digital camera image analysis[J]. European Journal of Agronomy, 2013, 48(3), 57-65.
14	WANG Y, WANG D, ZHANG G, et al. Estimating nitrogen status of rice using the image segmentation of G-R thresholding method[J]. Field Crops Research, 2013, 149(149): 33-39.
15	WANG J, ZHOU Q, SHANG J, et al. UAV- and machine learning-based retrieval of wheat SPAD values at the overwintering stage for variety screening[J]. Remote sensing, 2021, 13: 1-19.
16	YUE J, FENG H, LI Z, et al. Mapping winter-wheat biomass and grain yield based on a crop model and UAV remote sensing[J]. International Journal of Remote Sensing, 2021, 42(5): 1577-1601.
17	SHAN C, LIAO S, GONG Y, et al. Application of digital image processing for determination of vertical distribution of biomass in the canopy of winter wheat[J]. Acta Agronomica Sinica, 2007, 33(3): 419-424.
18	CHEN W. Evsluation of seed emergence unifermity of wheat based on UAV image[D]. Yangzhou: Yangzhou Univefrsity, 2018.
19	GITELSON A A, STARK R, GRITS U, et al. Vegetation and soil lines in visible spectral space: A concept and technique for remote estimation of vegetation fraction[J]. International Journal of Remote Sensing, 2002, 23(13): 2537-2562.
20	MAO D, WU X, DEPPONG C, et al. Negligible role of antibodies and C5 in pregnancy loss associated exclusively with C3-dependent mechanisms through complement alternative pathway[J]. Immunity, 2003, 19(6): 813-822.
21	WOEBBECKE D M, MEYER G E, BARGEN K VON, et al. Plant species identification, size, and enumeration using machine vision techniques on near-binary images[J]. Proceedings of SPIE-The International Society for Optical Engineering, 1993, 1836: 1-12.
22	HUNT JR E R, DAUGHTRY C S T, EITEL J U H, et al. Remote sensing leaf chlorophyll content using a visible band index[J]. Agronomy Journal, 2011, 103(4): 1090-1099.
23	TUCKER P W, HAZEN E E, COTTON F A. Staphylococcal nuclease reviewed: A prototypic study in contemporary enzymology[J]. Molecular & Cellular Biochemistry, 1979, 23(2): 67-86.
24	BENDIG J, YU K, AASEN H, et al. Combining UAV-based plant height from crop surface models, visible, and near infrared vegetation indices for biomass monitoring in barley[J]. International Journal of Applied Earth Observation & Geoinformation, 2015, 39: 79-87.
25	HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification[J]. IEEE Transactions on Systems Man & Cybernetics, 1973, 3(6): 610-621.
26	HUNT JR E R, HIVELY W D, FUJIKAWA S, et al. Acquisition of NIR-Green-Blue digital photographs from unmanned aircraft for crop monitoring[J]. Remote Sensing, 2010, 2(1): 290-305.
27	LU N, ZHOU J, HAN Z, et al. Improved estimation ofaboveground biomass in wheat from RGB imagery and point cloud data acquired withalow?cost unmanned aerial vehicle system[J]. Plant Methods, 2019, 15: 1-16.
28	DUAN B, FANG S, ZHU R, et al. Remote estimation of rice yield with unmanned aerial vehicle (UAV) data and spectral mixture analysis[J]. Frontiers in Plant Science, 2019,10: 1-14.
29	ZHOU Y, WANG D, CHEN C, et al. Prediction of wheat yield based on color index and texture feature index of UAV RGB image[J]. Journal of Yangzhou University (Agricultural and Life Science Edition), 2021, 42(3): 110-116.

[1]	龙佳宁, 张昭, 刘晓航, 李云霞, 芮照钰, 余江帆, 张漫, FLORES Paulo, 韩哲雄, 胡灿, 王旭峰. 利用改进EfficientNetV2和无人机图像检测小麦倒伏类型[J]. 智慧农业(中英文), 2023, 5(3): 62-74.
[2]	泮玮婷, 孙梦丽, 员琰, 刘平. 基于深度学习ImCascade R-CNN的小麦籽粒表形鉴定方法[J]. 智慧农业(中英文), 2023, 5(3): 110-120.
[3]	魏永康, 杨天聪, 丁信尧, 高越之, 袁鑫茹, 贺利, 王永华, 段剑钊, 冯伟. 基于不同空间分辨率无人机多光谱遥感影像的小麦倒伏区域识别方法[J]. 智慧农业(中英文), 2023, 5(2): 56-67.
[4]	卓越, 丁峰, 严海军, 徐婧. 无人机遥感在饲草作物生长监测中的应用研究进展[J]. 智慧农业(中英文), 2022, 4(4): 35-48.
[5]	郑晨曦, 温维亮, 卢宪菊, 郭新宇, 赵春江. 基于三维数字化的小麦植株表型参数提取方法[J]. 智慧农业(中英文), 2022, 4(2): 150-162.
[6]	赵晋陵, 杜世州, 黄林生. 联合多源多时相卫星影像和支持向量机的小麦白粉病监测方法[J]. 智慧农业(中英文), 2022, 4(1): 17-28.
[7]	王国宾, 韩鑫, 宋灿灿, 伊丽丽, 鲁文霞, 兰玉彬. 冬小麦田植保无人飞机喷施除草剂雾滴粒径及沉积飘移分布特性评估[J]. 智慧农业(中英文), 2021, 3(3): 38-51.
[8]	胡亚南, 梁驹, 梁社芳, 李世娟, 诸叶平, 鄂越. 基于DSSAT CERES-Wheat 模型的未来40年冬小麦最适播期分析[J]. 智慧农业（中英文）, 2021, 3(2): 68-76.
[9]	. 基于无人机图像以及不同机器学习和深度学习模型的小麦倒伏率检测[J]. 智慧农业（中英文）, 2021, 3(2): 23-34.
[10]	杨菲菲, 刘升平, 诸叶平, 李世娟. 基于高光谱遥感的冬小麦涝渍胁迫识别及程度判别分析[J]. 智慧农业（中英文）, 2021, 3(2): 35-44.
[11]	王琳, 梁健, 孟范玉, 孟炀, 张永涛, 李振海. 基于遥感与气象数据的冬小麦主产区籽粒蛋白质含量预报[J]. 智慧农业（中英文）, 2021, 3(2): 15-22.
[12]	束美艳, 陈向阳, 王喜庆, 马韫韬. 基于高光谱数据的玉米叶面积指数和生物量评估[J]. 智慧农业(中英文), 2021, 3(1): 29-39.
[13]	刘守阳, 金时超, 郭庆华, 朱艳, Baret Fred. 基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发[J]. 智慧农业（中英文）, 2020, 2(1): 87-98.
[14]	马新明, 马兆务, 许鑫, 席磊, 熊淑萍, 李海洋. 信息农机农艺技术融合的小麦智慧生产模式研究[J]. 智慧农业, 2019, 1(4): 62-71.
[15]	季云洲, 都盛佳, 纪同奎, 宋怀波. 基于嵌入式系统的小麦条锈病远程监测平台设计与试验[J]. 智慧农业, 2019, 1(3): 100-112.