Please wait a minute...
img

Wechat

Remote Sensing Technology and Application  2022, Vol. 37 Issue (3): 599-607    DOI: 10.11873/j.issn.1004-0323.2022.3.0599
    
Object-oriented Extraction of Maize Fallen Area based on Multi-source Satellite Remote Sensing Images
Houwen Zhu1(),Chong Luo2,Haixiang Guan1,Xinle Zhang1(),Jiaxin Yang1,Mengning Song1,Huanjun Liu1,2
1.College of Public Administration and law,Northeast Agricultural University,Harbin 150030,China
2.Northeast Institute of Geography and Agricultural Ecology,Chinese Academy of Sciences,Changchun 130012,China
Download:  HTML  PDF (1872KB) 
Export:  BibTeX | EndNote (RIS)      
Abstract  

Maize lodging caused by wind disaster may lead to a large reduction in maize production. Using remote sensing technology to accurately monitor maize lodging area and spatial distribution information is very important for disaster assessment.In this paper, Planet and Sentinel-2 images are combined with object-oriented and pixel-based methods to extract maize lodging in the study area, and different image features (spectral features, vegetation index and texture features) and different classification methods (support vector machine SVM, Random forest method RF and maximum likelihood method MLC) influence on the extraction accuracy of corn lodging.The results show that: ① The accuracy of corn lodging extraction using Planet images with high spatial resolution is generally higher than that of Sentinel-2 images;② From the perspective of classification accuracy and area accuracy, the spectral features, vegetation index, and mean feature of Planet image combined with object-oriented RF classification, the overall accuracy and Kappa coefficient are 93.77% and 0.87, respectively, and the average area error is the lowest 4.76%;③The accuracy of extracting maize lodging using Planet and Sentinel-2 images combined with object-oriented classification is higher than that of pixel-based classification. This research not only analyzes the advantages of object-oriented methods, but also evaluates the applicability of using different image data combined with object-oriented methods, which can provide a certain reference for remote sensing to extract crop lodging related research.

Key words:  Remote sensing monitoring      Maize lodging      Feature combination      Pixel      Oriented object     
Received:  30 October 2021      Published:  25 August 2022
ZTFLH:  S127  
Corresponding Authors:  Xinle Zhang     E-mail:  zhuhouwen0816@yeah.net;zhangxinle@gmail.com
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Houwen Zhu
Chong Luo
Haixiang Guan
Xinle Zhang
Jiaxin Yang
Mengning Song
Huanjun Liu

Cite this article: 

Houwen Zhu,Chong Luo,Haixiang Guan,Xinle Zhang,Jiaxin Yang,Mengning Song,Huanjun Liu. Object-oriented Extraction of Maize Fallen Area based on Multi-source Satellite Remote Sensing Images. Remote Sensing Technology and Application, 2022, 37(3): 599-607.

URL: 

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2022.3.0599     OR     http://www.rsta.ac.cn/EN/Y2022/V37/I3/599

Fig.1  Location and verification point distribution of research area
Fig.2  Field survey photos of maize lodging
波段名称中心波长/μm空间分辨率/m
波段10.455~0.5153
波段20.500~0.5903
波段30.590~0.6703
波段40.780~0.8603
Table 1  Parameters of Planet satellite remote sensing data
植被指数简写计算公式
归一化植被指数NDVINDVI=NIR-REDNIR+RED

过量绿指数

ExG

r=R(R+B+G)

b=B(R+B+G)

g=G(R+B+G)

ExG=2×g-r-b

绿色归一化植被指数GNDVIGNDVI=???NIR-GREENNIR+GREEN
土壤调节植被指数SAVISAVI=(NIR-REDNIR+RED+L)(1+L)
Table 2  Calculation formula of four vegetation indices used in this study
Fig.3  Spectral reflectance curves
面向对象分类基于像元分类
特征支持向量机随机森林最大似然法支持向量机随机森林最大似然法
总体分类精度Kappa系数总体分类精度Kappa系数总体分类精度Kappa系数总体分类精度Kappa系数总体分类精度Kappa系数总体分类精度Kappa系数
光谱特征87.55%0.7492.66%0.8585.77%0.7176.44%0.4792%0.8389.33%0.78
光谱+均值特征93.77%0.8793.33%0.8691.11%0.8193.33%0.8691.11%0.8288.44%0.76
光谱+植被指数特征80.44%0.5992.44%0.8489.77%0.7966.22%0.3188.81%0.7589.33%0.78
光谱+植被指数+均值特征94.66%0.8893.77%0.8790.22%0.8093.77%0.8790.66%0.8190.22%0.80
Table 3  Accuracy evaluation of lodging identification results from Planet images
面向对象分类基于像元分类
特征随机森林随机森林
总体分类精度Kappa系数总体分类精度Kappa系数
光谱特征87.50%0.7382.06%0.62
光谱+均值特征88.58%0.7687.50%0.73
光谱+植被指数特征84.78%0.6979.89%0.60
光谱+植被指数+均值特征85.32%0.7280.43%0.61
Table 4  Accuracy evaluation of lodging identification results from Sentinel-2 images
特征地块实测面积 /m2面向对象分类基于像元分类

支持向量机

面积/m2

随机森林

面积/m2

最大似然法

面积/m2

支持向量机

面积/m2

随机森林

面积/m2

最大似然法

面积/m2

光谱特征地块1779 704966 114838 923849 033384 489845 604845 487
地块2860 377906 452923 272928 782905 049919 422932 265
光谱+均值特征地块1779 704816 985809 769844 776832 095846 585849 519
地块2860 377923 019906 671925 020919 431918 009937 926
光谱+植被指数特征地块1779 704788 111838 834843 615901 629843 921843 327
地块2860 377926 365908 932919 989393 012916 569937 944
光谱+植被指数+均值特征地块1779 704818 594814 121839 898833 301845 694833 301
地块2860 377910 947904 639919 656919 143919 386935 991
Table 5  Results of maize lodging area in the test area from Planet images
特征地块面向对象分类基于像元分类

支持向量机

误差/%

随机森林

误差/%

最大似然法

误差/%

支持向量机

误差/%

随机森林

误差/%

最大似然法

误差/%

光谱特征地块119.297.598.8950.688.458.43
地块25.087.317.955.196.868.35
光谱+均值特征地块14.783.858.346.718.578.95
地块27.285.387.516.866.699.01
光谱+植被指数特征地块11.077.588.1915.638.238.15
地块27.665.646.9254.326.539.01
光谱+植被指数+均值特征地块14.984.417.726.878.466.87
地块25.875.146.886.836.858.78
Table 6  Error in the results of maize lodging area in the test area from Planet images
特征地块实测面积/m2面向对象分类基于像元分类
随机森林随机森林
面积/m2误差/%面积/m2误差/%
光谱特征地块1779 704849 0068.88852 9449.39
地块2860 377899 7304.57898 1584.39
光谱+均值特征地块1779 704845 1238.39847 2118.65
地块2860 377885 6722.93891 1363.57
光谱+植被指数特征地块1779 704829 4476.37840 1667.75
地块2860 377887 4143.14893 2693.82
光谱+植被指数+均值特征地块1779 704833 6276.91835 9187.20
地块2860 377893 4763.84891 7383.64
Table 7  Results and errors of maize lodging area in the test area from Sentinel-2 images
Fig.4  Results of area extraction of lodging maize with different images and methods
1 Ma Jiliang, Kong Weisheng, Zhu Tiehui. Characteristics,impacts of agricultural disaster,and mechanism of disaster prevention,mitigation and response: From the perspective of literature review[J]. Journal of China Agricultural University (Social Sciences Edition),2020,37(5):122-129
1 麻吉亮,孔维升,朱铁辉.农业灾害的特征、影响以及防灾减灾抗灾机制——基于文献综述视角[J].中国农业大学学报(社会科学版),2020,37(5):122-129.
2 Wang Lizhi, Gu Xiaohe, Hu Shengwu, et al. Remote sensing monitoring of maize lodging disaster with multi-temporal HJ-1B CCD image[J].Scientia Agricultura Sinica,2016,49(21):4120-4129.
2 王立志,顾晓鹤,胡圣武,等.基于多时相HJ-1B CCD影像的玉米倒伏灾情遥感监测[J].中国农业科学,2016,49(21):4120-4129.
3 Zhang Z, Flores P, Igathinathane C, et al. Wheat lodging detection from UAS imagery using machine learning algorithms[J].Remote Sensing, 2020,12(11):1838. DOI: .
doi: 10.3390/rs12111838
4 Li G, Han W, Huang S, et al. Extraction of sunflower lodging information based on UAV multi-spectral remote sensing and deep learning[J].Remote Sensing, 2021,13(14):2721. DOI: .
doi: 10.3390/rs13142721
5 Sun Q, Sun L, Shu M, et al. Monitoring maize lodging grades via unmanned aerial vehicle multispectral image[J]. Plant Phenomics,2019(2):1-16. DOI: .
doi: 10.34133/2019/5704154
6 Li Guang, Zhang Liyuan, Song Zhaoyang, et al. Extraction method of wheat lodging information based on multi-temporal UAV remote sensing data[J]. Transactions of the Chinese Society for Agricultural Machinery,2019,50(4):211-20.
6 李广,张立元,宋朝阳,等.小麦倒伏信息无人机多时相遥感提取方法[J].农业机械学报,2019,50(4):211-220.
7 Zheng E, Tian Y, Xu Z, et al. The extraction of maize lodgingregionsin UAV imagesusingdeepfully convolutional neural network[C]∥ IOP Conference Series:Earth and Environmental Science,2020,474(3):032004. DOI: .
doi: 10.1088/1755-1315/474/3/032004
8 Wang J, Li K, Shao Y, et al. Monitoring of rice lodging using Sentinel-1 data[J].Journal of Physics Conference Series,2020,1651:012080. DOI: .
doi: 10.1088/1742-6596/1651/1/012080
9 Chauhan S, Darvishzadeh R, Boschetti M, et al. Discriminant analysis for lodging severity classification in wheat using Radarsat-2 and Sentinel-1 data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 164:138-151. DOI: .
doi: 10.1016/j.isprsjprs.2020.04.012
10 Zhao L, Yang J, Li P, et al. Characterizing lodging damage in wheat and canola using Radarsat-2 Polarimetric SAR data[J]. Remote Sensing Letters, 2017,8(7-9):667675. DOI: .
doi: 10.1080/2150704x.2017.1312028
11 Wang Lei, Yang Wunian, Ren Jintong, et al. Object-oriented extraction method of typical urban features based on GF-2 images[J]. Bulletin of Surveying and Mapping, 2018(1):138-142.
11 王蕾,杨武年,任金铜,等.GF-2影像面向对象典型城区地物提取方法[J].测绘通报,2018(1):138-142.
12 Zhang Changsai, Yang Shuwen, Liu Zhengjun, et al. Image information extraction based on multi-level segmentation in extremely high altitude area[J]. Science of Surveying and Mapping, 2018,43(10):144-149,162.
12 张昌赛,杨树文,刘正军,等.多层次分割的极高海拔区影像信息提取[J].测绘科学,2018,43(10):144-149,162.
13 Zhang Chunhua, Li Xiunan, Wu Mengquan, et al. Object-oriented classification of land cover based on Landsat-8 OLI image data in the Kunyu Mountain[J]. Scientia Geographica Sinica, 2018,38(11):1904-1913.
13 张春华,李修楠,吴孟泉,等.基于Landsat-8 OLI数据与面向对象分类的昆仑山地区土地覆盖信息提取[J].地理科学,2018,38(11):1904-1913.
14 Yin Yanmin, Jia Li. Sentinel-2 study on crop mapping of Shandian River Basin based on images[J] Remote Sensing Technology and Application, 2021,36(2):400-410
14 尹燕旻,贾立.基于Sentinel-2的闪电河流域农作物分类研究[J].遥感技术与应用,2021,36(2):400-410.
15 Yuan Hua, Zhang Wanqiu, Guo HongJiang. Classification of QuickBird image based on object-oriented technology[C]∥ 2010 International Conference on Remote Sensing(ICRS),2010:473-475.
16 Pei Huan, Sun Tianjiao, Wang Xiaoyan. Object-oriented land use/cover classification based on texture features of Landsat-8 OLI image[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 248-255.
16 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.
17 Jia Wei, Gao Xiaohong, Yang Lingyu, et al. Land cover information extraction for complicated terrain region via an object-oriented classification method[J]. Journal of Lanzhou University(Natural Science Edition), 2018,54(4):486-493.
17 贾伟,高小红,杨灵玉,等.面向对象方法的复杂地形区地表覆盖信息提取[J].兰州大学学报(自然科学版),2018,54(4):486-493.
18 Guan H X, Liu H J, Meng X T, et al. A quantitative monitoring method for determining maize lodging in different growth stages[J]. Remote Sensing, 2020,12(19). DOI: .
doi: 10.3390/rs12193149
19 Oommen T, Misra D, Twarakavi N, et al. An objective analysis of support vector machine based classification for remote sensing[J]. Mathematical Geosciences, 2008, 40(4):409-424. DOI: .
doi: 10.1007/s11004-008-9156-6
20 Belgiu M, Drăguţ Lucian. Random forest in remote sensing: A review of a Plications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016,114:24. DOI: .
doi: 10.1016/j.isprsjprs.2016.01.011
21 Breiman L. Random forests, machine learning 45[J]. Journal of Clinical Microbiology, 2001, 2:199-228.
22 Yuan L, Chen X, Wang X, et al. Spatial associations between NDVI and environmental factors in the Heihe River Basin[J]. Journal of Geographical Sciences, 2019,29(9):1548-1564.
23 Jia L, Buerkert A, Chen X, et al. Low-altitude aerial photography for optimum fertilization of winter wheat on the North China Plain[J]. Field Crops Research, 2004, 89(2-3):389-395. DOI: .
doi: 10.1016/j.fcr.2004.02.014
24 Huete A R. A Soil-Adjusted Vegetation Index(SAVI)[J]. Remote Sensing of Environment, 1988,25(3):295-309. DOI: .
doi: 10.1016/0034-4257(88)90106-x
25 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. DOI: .
doi: 10.1016/s0034-4257(96)00072-7
26 Giannakos A, Feidas H. Classification of convective and stratiform rain based on the spectral and textural features of Meteosat Second Generation infrared data[J]. Theoretical & APlied Climatology, 2013, 113(3-4):495-510.
27 Li Zongnan, Chen Zhongxin, Ren Guoye,et al.Estimation of mai-ze lodging area based on Worldview-2 image[J].Transactions of the Chinese Society of Agricultural Engineering,2016,32(2):1-5
27 李宗南,陈仲新,任国业,等.基于Worldview-2影像的玉米倒伏面积估算[J].农业工程学报,2016,32(2):1-5.
28 Zhang Xinle, Guan Haixiang, Liu Huanjun, et al. Extraction of maize lodging area in mature period based on UAV multispectral image[J]Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(19): 98-106.
28 张新乐,官海翔,刘焕军,等.基于无人机多光谱影像的完熟期玉米倒伏面积提取[J].农业工程学报,2019,35(19):98-106.
29 Tian Tian, Fan Wenyi, Lu Wei,et al. An object-based information extraction technology for dominant tree species group types[J]. Chinese Journal of Aplied Ecology,2015,26(6):1665-1672.
29 田甜,范文义,卢伟,等.面向对象的优势树种类型信息提取技术[J].应用生态学报,2015,26(6):1665-1672.
30 Shu Meiyan, Gu Xiaohe, Sun Lin, et al. Structural characteristics change and spectral response analysis of maize canopy under lodging stress[J]. Spectroscopy and Spectral Analysis, 2019, 39(11):3553-3559.
30 束美艳,顾晓鹤,孙林,等.倒伏胁迫下的玉米冠层结构特征变化与光谱响应解析[J].光谱学与光谱分析,2019,39(11):3553-3559.
No Suggested Reading articles found!