融合无人机多源传感器的马铃薯叶绿素含量估算

边明博; 马彦鹏; 樊意广; 陈志超; 杨贵军; 冯海宽

融合无人机多源传感器的马铃薯叶绿素含量估算

边明博^1,2,
马彦鹏^1,2,
樊意广^1,2,
陈志超³,
杨贵军^1,2,
冯海宽^1,4,

1. 北京市农林科学院信息技术研究中心;
2. 农业农村部农业遥感机理与定量遥感重点实验室;
3. 河南理工大学测绘与国土信息工程学院;
4. 南京农业大学国家信息农业工程技术中心

基金项目:

黑龙江省揭榜挂帅科技攻关项目(2021ZXJ05A05)

国家自然科学基金项目(41601346)

详细信息

作者简介:
边明博(1996—),男,实习研究员,主要从事农业定量遥感研究,E-mail:bianmingbo0515@163.com

通讯作者:
冯海宽(1982—),男,高级工程师,主要从事农业定量遥感研究,E-mail:fenghaikuan123@163.com

中图分类号: S532;S127
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 1
出版历程
- 收稿日期: 2023-04-05
- 刊出日期: 2023-08-24

Estimation of Potato Chlorophyll Content Based on UAV Multi-source Sensor

1. Information Technology Research Center, Beijing Academy of Agriculture and Forestry Sciences;
2. Key Laboratory of Quantitative Remote Sensing in Agriculture, Ministry of Agriculture and Rural Affairs;
3. School of Geomatics and Land Information Engineering, Henan Polytechnic University;
4. National Engineering and Technology Center for Information Agriculture, Nanjing Agricultural University

摘要

摘要: 叶绿素是衡量作物光合作用的重要指标，监测马铃薯关键生育期叶片叶绿素含量（Leaf chlorophyll content, LCC）至关重要。获取马铃薯块茎形成期、块茎增长期和淀粉积累期的无人机RGB和多光谱影像，提取无人机多光谱影像的光谱反射率构建植被指数（Vegetation index, VIs）,利用Gabor滤波器提取RGB影像的纹理信息（Texture information, TIs）。然后利用机器学习SVR-REF方法进行数据降维获取植被指数和纹理特征重要性排序，并采用迭代的方法在植被指数最佳模型中加入纹理信息，观察每次加入的纹理信息对模型的动态影响。最后使用支持向量机（Support vector machine, SVR）和K-最近邻算法（K-nearest neighbor, KNN）2种机器学习方法进行建模。结果表明，马铃薯3个关键生育期，加入纹理特征后的2种模型精度和稳定性均有提高，且SVR模型精度优于KNN。块茎形成期，SVR模型建模R²由0.61提升至0.71,RMSE由0.20 mg/g降为0.17 mg/g,精度提升14.2%,验证R²由0.58提升至0.66,RMSE由0.19 mg/g降至0.17 mg/g,精度提升10.5%。块茎增长期，SVR建模R²由0.59提升至0.67,RMSE由0.16 mg/g降至0.14 mg/g,验证R²由0.71提升至0.79,RMSE由0.15 mg/g降至0.13 mg/g,精度提升13.3%。淀粉积累期，SVR建模R²由0.62提升为0.69,RMSE由0.17 mg/g降至0.14 mg/g,精度提升17.6%,验证R²由0.47提升至0.63,RMSE由0.17 mg/g降至0.14 mg/g,精度提升17.6%。另外，3个时期参与SVR建模的植被指数数量分别为19、16、3,纹理数量分别为4、2、9,在植被指数不能充分响应叶绿素含量时，会有更多纹理信息参与建模，并且模型精度提升更高，进一步论证了纹理特征在马铃薯叶绿素含量反演中的重要性。
- 马铃薯 /
- 叶绿素含量 /
- 图谱融合 /
- Gabor纹理 /
- 机器学习
Abstract: Chlorophyll is an important indicator for measuring crop photosynthesis, and monitoring leaf chlorophyll content（LCC） of potatoes during critical growth stages. UAV RGB and multispectral images were obtained during the potato tuber formation, tuber growth, and starch accumulation periods. Vegetation indices（VIs） were extracted from UAV multispectral images, and texture information（TIs） was extracted from RGB images by using Gabor filters. Then, the SVR-REF method was used for data dimensionality reduction to obtain the importance ranking of vegetation indices and texture features, and an iterative approach was used to add texture information to the best vegetation index model and observe the dynamic effect of each added texture information on the model. Finally, support vector machine（SVR） and K-nearest neighbor（KNN） algorithms were used for modeling. The results showed that the accuracy and stability of the two models were improved after adding texture features during the critical growth stages of potatoes, and the SVR model performed better than the KNN model. During the tuber formation period, the SVR modeling R~2 was increased from 0.61 to 0.71, and RMSE was decreased from 0.20 mg/g to 0.17 mg/g, with an accuracy improvement of 14.2%. The validation R~2 was increased from 0.58 to 0.66, and RMSE was decreased from 0.19 mg/g to 0.17 mg/g, with an accuracy improvement of 10.5%. During the tuber growth period, the SVR modeling R~2 was increased from 0.59 to 0.67, and RMSE was decreased from 0.16 mg/g to 0.14 mg/g, with an accuracy improvement of 13.3%. The validation R~2 was increased from 0.71 to 0.79, and RMSE was decreased from 0.15 mg/g to 0.13 mg/g, with an accuracy improvement of 13.3%. During the starch accumulation period, the SVR modeling R~2 was increased from 0.62 to 0.69, and RMSE was decreased from 0.17 mg/g to 0.14 mg/g, with an accuracy improvement of 17.6%. The validation R~2 was increased from 0.47 to 0.63, and RMSE was decreased from 0.17 mg/g to 0.14 mg/g, with an accuracy improvement of 17.6%. In addition, the number of vegetation indices involved in SVR modeling during the three periods were 19, 16, and 3, respectively, and the number of texture features were 4, 2, and 9, respectively. When vegetation indices were unable to respond adequately to chlorophyll content, more texture information was involved in modeling, and the model accuracy was improved significantly, further demonstrating the importance of texture features in chlorophyll content inversion in potatoes.
- potato /
- chlorophyll content /
- atlas fusion /
- Gabor textures /
- machine learning

HTML全文

参考文献(22)

[1]	ZHANG H,XU F,WU Y,et al.Progress of potato staple food research and industry development in China[J].Journal of Integrative Agriculture,2017,16(12):2924-2932.
[2]	JIA J,YANG D,LI J,et al.Research and comparative analysis about potato production situation between China and continents in the world[J].Agric.Eng.,2011,1:84-86.
[3]	WIJESINGHA J,DAYANANDA S,WACHENDORF M,et al.Comparison of spaceborne and UAV-borne remote sensing spectral data for estimating monsoon crop vegetation parameters[J].Sensors,2021,21(8):2886.
[4]	BOHMAN B J,ROSEN C J,MULLA D J.Evaluation of variable rate nitrogen and reduced irrigation management for potato production[J].Agronomy Journal,2019,111(4):2005-2017.
[5]	LI X,LI L,LIU X.Collaborative inversion heavy metal stress in rice by using two-dimensional spectral feature space based on HJ-1 A HSI and radarsat-2 SAR remote sensing data[J].International Journal of Applied Earth Observation and Geoinformation,2019,78:39-52.
[6]	PUTRA B T W.New low-cost portable sensing system integrated with on-the-go fertilizer application system for plantation crops[J].Measurement,2020,155:107562.
[7]	YANG M D,HUANG K S,KUO Y H,et al.Spatial and spectral hybrid image classification for rice lodging assessment through UAV imagery[J].Remote Sensing,2017,9(6):583.
[8]	ZHUO W,WU N,SHI R,et al.UAV mapping of the chlorophyll content in a tidal flat wetland using a combination of spectral and frequency indices[J].Remote Sensing,2022,14(4):827.
[9]	刘杨,黄珏,孙乾,等.利用无人机数码影像估算马铃薯地上生物量[J].遥感学报,2021,25(9):2004-2014.LIU Yang,HUANG Jue,SUN Qian,et al.Estimation of potato aboveground biomass using UAV digital images[J].Journal of Remote Sensing,2021,25(9):2004-2014.(in Chinese)
[10]	陶惠林,徐良骥,冯海宽,等.基于无人机数码影像的冬小麦株高和生物量估算[J].农业工程学报,2019,35(19):107-116.TAO Huilin,XU Liangji,FENG Haikuan,et al.Plant height and biomass estimation of winter wheat based on UAV digital image[J].Transactions of the CSAE,2019,35(19):107-116.(in Chinese)
[11]	LANG Q,ZHIYONG Z,LONGSHENG C,et al.Detection of chlorophyll content in maize canopy from UAV imagery[J].IFAC-PapersOnLine,2019,52(30):330-335.
[12]	YUE J,YANG G,TIAN Q,et al.Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground-resolution image textures and vegetation indices[J].ISPRS Journal of Photogrammetry and Remote Sensing,2019,150:226-244.
[13]	陈鹏,冯海宽,李长春,等.无人机影像光谱和纹理融合信息估算马铃薯叶片叶绿素含量[J].农业工程学报,2019,35(11):63-74.CHEN Peng,FENG Haikuan,LI Changchun,et al.UAV image spectral and texture fusion information to estimate the chlorophyll content of potato leaves[J].Transactions of the CSAE,2019,35(11):63-74.(in Chinese)
[14]	SUN X,YANG Z,SU P,et al.Non-destructive monitoring of maize LAI by fusing UAV spectral and textural features[J].Frontiers in Plant Science,2023,14:1158837.
[15]	樊意广,冯海宽,刘杨,等.利用无人机多源传感器估算马铃薯植株氮含量[J].光谱学与光谱分析,2022,42(10):3217-3225.FAN Yiguang,FENG Haikuan,LIU Yang,et al.Estimation of nitrogen content of potato plants using UAV multi-source sensors[J].Spectroscopy and Spectral Analysis,2022,42(10):3217-3225.(in Chinese)
[16]	FENG L,ZHANG Z,MA Y,et al.Alfalfa yield prediction using uav-based hyperspectral imagery and ensemble learning[J].Remote Sensing,2020,12(12):2080.
[17]	LICHTENTHALER H K.Chlorophylls and carotenoids:pigments of photosynthetic biomembranes[M]//Methods in Enzymology.Academic Press,1987:350-382.
[18]	QI H,WU Z,ZHANG L,et al.Monitoring of peanut leaves chlorophyll content based on drone-based multispectral image feature extraction[J].Computers and Electronics in Agriculture,2021,187:106292.
[19]	魏鹏飞,徐新刚,李中元,等.基于无人机多光谱影像的夏玉米叶片氮含量遥感估测[J].农业工程学报,2019,35(8):126-133,335.WEI Pengfei,XU Xingang,LI Zhongyuan,et al.Remote sensing estimation of leaf nitrogen content of summer maize based on UAV multispectral imagery[J].Transactions of the CSAE,2019,35(8):126-133,335.(in Chinese)
[20]	孙诗睿,赵艳玲,王亚娟,等.基于无人机多光谱遥感的冬小麦叶面积指数反演[J].中国农业大学学报,2019,24(11):51-58.SUN Shirui,ZHAO Yanling,WANG Yajuan,et al.Inversion of leaf area index of winter wheat based on UAV multispectral remote sensing[J].Journal of China Agricultural University,2019,24(11):51-58.(in Chinese)
[21]	SHEN L,GAO M,YAN J,et al.Winter wheat SPAD value inversion based on multiple pretreatment methods[J].Remote Sensing,2022,14(18):466.
[22]	ZHENG H,CHENG T,ZHOU M,et al.Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery[J].Precision Agriculture,2018,20(3):611-629.