Please wait a minute...
img

官方微信

遥感技术与应用  2019, Vol. 34 Issue (5): 970-982    DOI: 10.11873/j.issn.1004-0323.2019.5.0970
林业遥感专栏     
基于高分二号遥感影像的树种分类方法
李哲,张沁雨,彭道黎()
北京林业大学大学林学院,北京 100083
Classification Method of Tree Species based on GF-2 Remote Sensing Images
Zhe Li,Qinyu Zhang,Daoli Peng()
College of Forestry, Beijing Forestry University, Beijing 100083, China
 全文: PDF(5608 KB)   HTML
摘要:

为推广国产高分数据在森林树种分类方面的应用,以北京市延庆区八达岭国家森林公园主要区域的6期高分二号影像为数据源,在分层分类的基础上,利用支持向量机递归特征消除、C5.0决策树、FSO 3种特征优选方法,从4种特征维度下实现面向对象的支持向量机和随机森林的森林树种分类,最终取得总体精度平均为83.65%,特定树种生产者精度介于93.75%(山杏)和38.10%(刺槐)之间,特定树种用户精度介于100%(华北落叶松)和44.74%(榆树)之间的良好结果。结果表明:C5.0决策树耗时最短(0.01 h)且其所选特征应用于分类总体精度最高(86.90%);在不同特征维度下支持向量机分类的总体精度比随机森林平均高出3.28%;支持向量机和随机森林均对特征维度不敏感,但良好的特征优选结果仍会对支持向量机的分类效率(最高提升86.98%)和随机森林的分类精度(最高提升9.22%)产生较大影响。

关键词: 高分二号树种分类特征优选支持向量机随机森林    
Abstract:

In order to promote the application of Chinese Gaofen data in the classification of forest tree species, The six GF-2 images of the main area of Badaling National Forest Park in Yanqing District, Beijing were used as the data source, we used support vector machine-recursive feature elimination, C5.0 decision tree and feature space optimization three feature optimization methods to accomplish the object-oriented Support Vector Machines (SVM) and Random Forest (RF) forest tree classification from four feature dimensions on the basis of the hierarchical classification. we can achieve good classification results that the average Overall Accuracy of the study was 83.65%, the Producer's Accuracy of specific tree species was between 93.75% (Apricot) and 38.10% (Locust), and the Use's Accuracy of specific tree species was between 100% (North China Larch) and 44.74% (Elm). The results showed the C5.0 feature selection took the shortest time(0.01 h) and features selected by it could be applied to the highest classification accuracy (86.90%). Under different feature dimensions, the Overall Accuracy of SVM classification was 3.28% higher than the RF.SVM and RF were both insensitive to feature dimensions, but good feature optimization results will still have a large impact on the classification efficiency of SVM(Highest improvement was 86.98%) and the classification accuracy of RF(Highest improvement was 9.22%).

Key words: GF-2    Tree species classification    Feature selection    Support vector machines    Random forest
收稿日期: 2018-10-13 出版日期: 2019-12-05
ZTFLH:  TP75  
基金资助: 国家林业局948项目(2015?4?32)
通讯作者: 彭道黎     E-mail: dlpeng@bjfu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李哲
张沁雨
彭道黎

引用本文:

李哲,张沁雨,彭道黎. 基于高分二号遥感影像的树种分类方法[J]. 遥感技术与应用, 2019, 34(5): 970-982.

Zhe Li,Qinyu Zhang,Daoli Peng. Classification Method of Tree Species based on GF-2 Remote Sensing Images. Remote Sensing Technology and Application, 2019, 34(5): 970-982.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2019.5.0970        http://www.rsta.ac.cn/CN/Y2019/V34/I5/970

图1  研究区域位置与外业调查点分布图(a) 研究区域位置 (b) 2018年4月25日获取的真彩色影像
序号采集时间产品号对应生长期
12014-10-171065695变色初期
22017-01-272149217停止生长期
32017-03-072223865发芽初期
42017-05-152359849生长旺盛期
52017-11-042742984落叶初期
62018-04-253144010展叶末期
表 1  影像信息统计
特征类别特征数量
光谱特征亮度(Brightness)1
均值(Mean)24
标准差(Standard deviation)24
比率(Ratio)24
最大差异度量(Max. diff.)1
植被指数差值植被指数(DVI)6
绿色归一化植被指数(GNDVI)6
归一化植被指数(NDVI)6
再归一化植被指数(RDVI)6
比值植被指数(RVI)6
土壤调节植被指数(SAVI)6
纹理特征GLCM角二阶矩(GLCM.Ang.2nd moment)25
GLCM反差(GLCM.Contrast )25
GLCM相关性(GLCM.Correlation)25
GLCM异质性(GLCM.Dissimilarity)25
GLCM熵(GLCM.Entropy)25
GLCM同质性(GLCM.Homogeneity)25
GLCM均值(GLCM.Mean)25
GLCM标准差(GLCM.StdDev.)25
GLDV角二阶矩(GLDV.Ang.2nd moment)25
GLDV反差(GLDV.Contrast)25
GLDV熵(GLDV.Entropy)25
GLDV均值(GLDV.Mean)25
表 2  特征统计
图2  尺度参数分析结果(150~350)
图3  尺度参数分析结果(80~150)
排名特征参数排名特征参数排名特征参数
1GLCM.Ang.2nd.moment.1_B2GNDVI.33Ratio.1_G
4Ratio.5_N5Ratio.1_R6RVI.1
7Mean.1_R8Mean.6_N9GLCM.Homogeneity.
10GLCM.Entropy.4_G11GNDVI.112GLCM.Entropy.3_R
13GLCM.Homogeneity.1_N14Standard.deviation.1_N15Standard.deviation.4_R
16Standard.deviation.1_G17GLCM.StdDev.2_G18GLCM.Homogeneity.3_R
19GLCM.Ang.2nd.moment.4_N20Ratio.4_N21GLDV.Contrast.5_G
22Standard.deviation.4_G23GLCM.Ang.2nd.moment.1_N24GLCM.Mean.1_N
表 3  第二层分类优选特征及重要性排名
排名特征参数排名特征参数排名特征参数
1Ratio.3_R2Ratio.5_B3Ratio.1_G
4Mean.1_G5SAVI.16Standard.deviation.1_B
7Ratio.2_B8Mean.6_R9Standard.deviation.1_R
10Ratio.4_G11Mean.6_B12Ratio.2_R
13GLCM.Correlation
表 4  优选特征及重要性排名(C5.0)
排名特征参数排名特征参数排名特征参数
1Ratio.1_R2Mean.4_R3SAVI.1
4RVI.15NDVI.16Mean.4_N
7GLDV.Ang.2nd.moment.6_G8Mean.4_G9DVI.4
10GLDV.Entropy.6_G11Ratio.3_R12GLCM.Dissimilarity.6_G
13GLDV.Mean.6_G14GLCM.Homogeneity.6_G15GLCM.Correlation.6_G
16GLDV.Contrast.6_G17GLCM.Contrast.6_G18RDVI.4
19GLDV.Ang.2nd.moment.6_B20Mean.4_B21Ratio.5_R
22GLDV.Ang.2nd.moment.6_R23SAVI.324RVI.3
25NDVI.326GLDV.Entropy.6_B27GLDV.Entropy.6_R
28GLCM.Dissimilarity.6_B29GLDV.Mean.6_B30GLCM.Homogeneity.6_N
31GLCM.Dissimilarity.6_R32GLDV.Mean.6_R33GLCM.Homogeneity.6_B
34GLCM.Correlation.6_B35Ratio.3_N36SAVI.5
37RVI.538NDVI.539GLCM.Homogeneity.6_R
40GLDV.Ang.2nd.moment.6_N41GLCM.Correlation.6_R42GLCM.Contrast.6_B
43GLDV.Contrast.6_B44GNDVI.345GLCM.Contrast.6_R
46GLDV.Contrast.6_R47RDVI.348Ratio.5_N
表 5  优选特征及重要性排名(SVM-RFE)
排名特征参数排名特征参数排名特征参数
1Mean.4_N2DVI.13SAVI.6
4GLDV.Entropy.6_G5GLCM.Correlation.1_B6GLCM.Correlation.4_R
7GLCM.Correlation.3_N8GLCM.Entropy.3_N9GLCM.Correlation.2_R
10RVI.111Mean.6_R12GLCM.Correlation.1_N
13GLCM.StdDev14GLDV.Entropy.6_N15Mean.1_R
16GLCM.Correlation.2_N17Mean.5_R18GLCM.Correlation.3_B
19GLCM.Correlation.4_B20GLCM.StdDev.6_G21Standard.deviation.4_N
22GLDV.Mean.6_N23Standard.deviation.6_N24GLCM.Entropy.4_B
25Standard.deviation.4_B26GLCM.Correlation.1_R27GLCM.Correlation.5_N
28Mean.1_N29Ratio.1_G30GLCM.Correlation.5_R
31GLCM.Correlation.3_R32Mean.5_G33GLCM.Correlation.2_G
34GLCM.Entropy.1_N35GLDV.Entropy.2_N36GLCM.Correlation
37GLCM.Correlation.4_G38Brightness39GLCM.Dissimilarity.6_B
40Mean.2_R41Standard.deviation.4_G42DVI.4
43GLCM.Dissimilarity.2_R44GLDV.Entropy.3_N45GLCM.Correlation.1_G
46GLCM.Correlation.4_N47GLCM.Dissimilarity.6_N48NDVI.6
49GLDV.Entropy.1_N50GLCM.Entropy.6_N
表 6  优选特征及重要性排名(FSO)
类别

灌木

林地

乔木

林地

非林地

用户精度

/%

总体精度:89.97%Kappa系数:0.82
灌木林地38346189.07
乔木林地27340192.39
非林地496683.54
生产者精度/%92.5186.0897.06
表 7  乔木林地与灌木林地混淆矩阵
C5.0SVM-RFEFSOALL
生产者精度/%用户精度/%生产者精度/%用户精度/%生产者精度/%用户精度/%生产者精度/%用户精度/%
灌木林地92.7990.3592.7990.3592.7990.3592.7990.35
非林地100.0091.04100.0091.04100.0091.04100.0091.04
山杏93.7581.0878.1365.7984.3872.9784.3881.82
侧柏86.7968.6681.1374.1492.4570.0092.4570.00
榆树76.6769.7063.3361.2973.3373.3373.3375.86
刺槐64.2979.4157.1466.6761.9081.2561.9076.47
油松85.3296.8885.3291.1887.1696.9484.4094.85
元宝枫85.4295.3570.8389.4777.0886.0585.4285.42
杨树81.0896.7767.5771.4381.0888.2478.3890.63
华北落叶松89.4785.0089.4773.9189.47100.0089.4794.44
总体精度/%86.9081.9286.1686.16
Kappa系数0.850.790.840.84
表8  不同特征维度下SVM的精度比较
图 4  Mtry对袋外误差的影响
C5.0SVM-RFEFSOALL
生产者精度/%用户精度/%生产者精度/%用户精度/%生产者精度/%用户精度/%生产者精度/%用户精度/%
灌木林地92.7990.3592.7990.3592.7990.3592.7990.35
非林地100.0091.04100.0091.04100.0091.04100.0091.04
山杏87.5087.5071.8856.1084.3884.3881.2583.87
侧柏83.0260.2769.8160.6683.0264.7179.2562.69
榆树63.3363.3356.6744.7466.6752.6366.6757.14
刺槐61.9078.7938.1051.6159.5278.1359.5273.53
油松80.7395.6581.6591.7580.7396.7080.7394.62
元宝枫89.5897.7354.1781.2585.4297.6285.4297.62
杨树83.7893.9456.7658.3381.0888.2478.3890.63
华北落叶松89.4770.8389.4768.0089.4770.8389.4762.96
总体精度/%84.8775.6584.1383.39
Kappa系数0.830.720.820.81
表 9  不同特征维度下RF的精度比较
图5  分类结果比较
图6  总体精度比较
图 7  特征重要性比较
1 Matsuki T, Yokoya N, Iwasaki A. Hyperspectral Tree Species Classification of Japanese Complex Mixed Forest with the Aid of Lidar Data[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2015,8(5):1-11.
2 Lei Guangbin, Li Ainong, Tan Jianbo, et al. Forest Types Mapping in Mountainous Area Using Multi-source and Multi-temporal Satellite Images and Decision Tree Models[J]. Remote Sensing Technology and Application,2016,31(1):31-41.雷光斌,李爱农,谭剑波,等. 基于多源多时相遥感影像的山地森林分类决策树模型研究[J]. 遥感技术与应用,2016,31(1):31-41.
3 Yan Wei, Zhou Wen, Yi Lilong, et al. Research Progress of Remote Sensing Classification and Change Monitoring of Forest Types[J]. Remote Sensing Technology and Application,2019,34(3):445-454.颜伟,周雯,易立龙,等. 森林类型遥感分类及变化监测研究进展[J]. 遥感技术与应用,2019,34(3):445-454.
4 Pasquarella V J, Holden C E, Woodcock C E. Improved Mapping of Forest Type Using Spectral-temporal Landsat Features[J]. Remote Sensing of Environment, 2018,210:193-207.
5 Li Weitao. Forest Vegetation Classification Using High Resolution Remote Sensing Image[D]. Beijing: Beijing Forestry University,2016.李伟涛. 高分辨率遥感森林植被分类提取研究[D]. 北京:北京林业大学,2016.
6 Immitzer M, Atzberger C, Koukal T. Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data[J]. Remote Sensing,2012,4(9):2661-2693.
7 Pu R, Landry S. A Comparative Analysis of High Spatial Resolution IKONOS and WorldView-2 Imagery for Mapping Urban Tree Species[J]. Remote Sensing of Environment,2012,124:516-533.
8 Liu Huaipeng, An Huijun, Wang Bing, et al. Tree Species Classification Using WorldView-2 Images based on Recursive Texture Feature Elimination[J]. Journal of Beijing Forestry University,2015,37(8):53-59.刘怀鹏,安慧君,王冰,等. 基于递归纹理特征消除的WorldView-2树种分类[J]. 北京林业大学学报,2015,37(8):53-59.
9 Li Dan, Ke Yinghai, Gong Huili, et al. Urban Tree Species Classification with Machine Learning Classifier Using WorldView-2 Imagery[J]. Geography and Geo-information Science,2016,31(2):84-89.李丹,柯樱海,宫辉力,等. 基于高分辨率遥感影像的城市典型乔木树种分类研究[J]. 地理与地理信息科学,2016,32(1):84-89.
10 Majid I A, Latif Z A, Adnan N A. Tree Species Classification Using Worldview-3 Data[C]∥Shah Alam: University Teknologi Malaysia,2016.
11 Song Minghui, Object-oriented Urban Land Classification with GF-2 Remote Sensing Image[J]. Remote Sensing Technology and Application,2019,34(3):547-553.[宋明辉. 基于高分二号数据的面向对象城市土地利用分类研究[J]. 遥感技术与应用,2019,34(3):547-553.]
12 Ma Xiuqiang, Peng Ling, Xu Suning, et al. Application of GF-2 Satellite Data to Mine Geological Environment Investigation in Daye,Hubei Province[J]. Remote Sensing for Land & Resources,2017,29(Sup.1):127-131.马秀强,彭令,徐素宁,等. 高分二号数据在湖北大冶矿山地质环境调查中的应用[J]. 国土资源遥感,2017,29(增刊1):127-131.
13 Wang Fang, Yang Wunian, Deng Xiaoyu, et al. Discussion on Urban Ecological Land Classification Method based on GF-2 Data[J]. Science of Surveying and Mapping,2018,43(3):71-76.王芳,杨武年,邓晓宇,等. 高分二号数据的城市生态用地分类方法探讨[J]. 测绘科学,2018,43(3):71-76.
14 Zhu X L, Liu D S. Accurate Mapping of Forest Types Using Dense Seasonal Landsat Time-series[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2014,96(11):1-11.
15 Howard D M, Wylie B K. Annual Crop Type Classification of the US Great Plains for 2000 to 2011[J]. Photogrammetry and Remote Sensing,2014,80(6):537-549.
16 Evans T L, Costa M, Tomas W M, et al. Large-scale Habitat Mapping of the Brazilian Pantanal Wetland: A Synthetic Aperture Radar Approach[J]. Remote Sensing of Environment,2014,155:89-108.
17 Mao Xuegang, Cheng Wenqu, Wei Jingyu, et al. Effect and Evaluation of Segmentation Scale on Object-based Forest Species Classification[J]. Scientia Silvae Sinicae,2017,53(12):73-83.毛学刚,陈文曲,魏晶昱,等. 分割尺度对面向对象树种分类的影响及评价[J]. 林业科学,2017,53(12):73-83.
18 Zhu Yongsen, Zeng Yongnian, Zhang Meng. Extract of Land Use/Cover Information based on HJ Satellites Data and Object-oriented Classification[J]. Transactions of the Chinese Society of Agricultural Engineering,2017,33(14):258-265.朱永森,曾永年,张猛. 基于HJ卫星数据与面向对象分类的土地利用/覆盖信息提取[J]. 农业工程学报,2017,33(14):258-265.
19 Hao Long, Chen Yongfu, Liu Hua, et al. Object-oriented Forest Classification of Linzhi County based on CART Decision Tree with Texture Information[J]. Remote Sensing Technology and Application,2017,32(2):386-394.郝泷,陈永福,刘华,等. 基于纹理信息CART决策树的林芝县森林植被面向对象分类[J]. 遥感技术与应用,2017,32(2):386-394.
20 Phiri D, Morgenroth J, Xu C, et al. Effects of Pre-processing Methods on Landsat OLI-8 Land Cover Classification Using OBIA and Random Forests Classifier[J]. International Journal of Applied Earth Observation and Geoinformation,2018,73:170-178.
21 Liu Yan. Study on Kernel Function of Support Vector Machine[D]. Xi'an: Xidian University,2012.刘琰. 支持向量机核函数的研究[D]. 西安:西安电子科技大学,2012.
22 Song Rongjie, Ning Jifeng, Chang Qingrui, et al. Kiwifruit Orchard Mapping based on Wavelet Textures and Random Forest[J]. Transactions of The Chinese Society of Agricultural Machinery, 2018,49(4):222-231.宋荣杰,宁纪锋,常庆瑞,等. 基于小波纹理和随机森林的猕猴桃果园遥感提取[J]. 农业机械学报,2018,49(4):222-231.
23 Ren Xinyu. Urban Forest Vegetation Classification in Consideration of Vegetation Phenology based on High Spatial Resolution Satellite Imagery[D]. Nanjing: Nanjing Forestry University,2016.任芯雨. 考虑植被季相节律的高分辨率遥感影像城市森林分类[D]. 南京:南京林业大学,2016.
24 Bai Jinting. The Forest Classification Combining Multidimensional Features based on High-resolution Remote Sensing Images[D]. Beijing: Beijing Forestry University,2016.白金婷. 结合高分辨率遥感影像多维特征的森林分类[D]. 北京:北京林业大学,2016.
25 Ma Haoran. Object-based Remote Sensing Image Classification of Forest based on Multi-level Segmentation[D]. Beijing: Beijing Forestry University,2014.马浩然. 基于多层次分割的遥感影像面向对象森林分类[D]. 北京:北京林业大学,2014.
26 Li Chungan. Object-oriented Classification of Forest Cover Using SPOT5 Imagery[D]. Beijing: Beijing Forestry University,2009.李春干. 面向对象的SPOT5图像森林分类研究[D]. 北京:北京林业大学,2009.
27 Hao Pengyu. Crop Classification Using Time Series Remote Sensing Data[D]. Beijing: Institute of Remote Sensing and Digital Earth,2017.郝鹏宇. 基于多时相遥感数据的农作物分类研究[D]. 北京:中国科学院遥感与数字地球研究所,2017.
28 Dalponte M, Orka H O, Gobakken T, et al. Tree Species Classification in Boreal Forests with Hyperspectral Data[J]. IEEE Transactions on Geoscience and Remote Sensing,2013,51(5):2632-2645.
29 Millard K, Richardson M. On the Importance of Training Data Sample Selection in Random Forest Image Classification: A Case Study in Peatland Ecosystem Mapping[J]. Remote Sensing,2015,7(7):8489-8515.
30 Congalton R G. A Review of Assessing the Accuracy of Classification of Remotely Sensed Data[J]. Remote Sensing of Environment,1991,37:35-46.
31 Belgiu M, Dragut L. Random Forest in Remote Sensing: A Review of Applications and Future Directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2016,114:24-31.
32 Ghosh A, Joshi P K. A Comparison of Selected Classification Algorithms for Mapping Bamboo Patches in Lower Gangetic Plains Using Very High Resolution WorldView 2 Imagery[J]. International Journal of Applied Earth Observation and Geoinformation,2014,26(1):298-311.
33 Rodriguez-Galiano V F, Chica-Olmo M, Abarca-Hemandez F, et al. Random Forest Classification of Mediterranean Land Cover Using Multi-seasonal Imagery and Multi-seasonal Texture[J]. Remote Sensing of Environment,2012,121:93-107.
34 Cheng Ximeng, Shen Zhanfeng, Xing Tingyan, et al. Efficiency and Accuracy Analysis of Multispectral Image Classification based on mRMR Feature Selection Method[J]. Journal of Geo-information Science,2016,18(6):815-823.程希萌,沈占锋,邢廷炎,等. 基于mRMR特征优选算法的多光谱遥感影像分类效率精度分析[J]. 地球信息科学, 2016,18(6):815-823.
35 Guan H Y, Li J T, Chapman M, et al. Integration of Orthoimagery and LiDAR Data for Object-based Urban Thematic Mapping Using Random Forests[J]. International Journal of Remote Sensing,2013,34(14):5166-5186.
36 Mishra N B, Crews K A. Mapping Vegetation Morphology Types in a Dry Savanna Ecosystem: Integrating Hierarchical Object-based Image Analysis with Random Forest[J]. International Journal of Remote Sensing,2014,35(3):1175-1198.
[1] 刘立, 刘勇. 基于优化分割分类层次体系的土地覆被分类制图方法探讨[J]. 遥感技术与应用, 2019, 34(1): 79-89.
[2] 谷晓天, 高小红, 马慧娟, 史飞飞, 刘雪梅, 曹晓敏. 复杂地形区土地利用/土地覆被分类机器学习方法比较研究[J]. 遥感技术与应用, 2019, 34(1): 57-67.
[3] 吴薇, 张源, 李强子, 黄慧萍. 基于迭代CART算法分层分类的土地覆盖遥感分类[J]. 遥感技术与应用, 2019, 34(1): 68-78.
[4] 牟多铎, 刘磊. ELM与SVM在高光谱遥感图像监督分类中的比较研究[J]. 遥感技术与应用, 2019, 34(1): 115-124.
[5] 皋厦, 申鑫, 代劲松, 曹林. 结合LiDAR单木分割和高光谱特征提取的城市森林树种分类[J]. 遥感技术与应用, 2018, 33(6): 1073-1083.
[6] 陈伟民,张凌,宋冬梅,王斌,丁亚雄,许明明,崔建勇. 基于AdaBoost改进随机森林的高光谱图像地物分类方法研究[J]. 遥感技术与应用, 2018, 33(4): 612-620.
[7] 梁继,褚楠,郑敦勇,彭焕华,张静. 面向道路边坡监测的高分二号应用研究[J]. 遥感技术与应用, 2018, 33(4): 638-645.
[8] 刘振波,邹娴,葛云健,陈健,曹雨濛. 基于高分一号WFV影像的随机森林算法反演水稻LAI[J]. 遥感技术与应用, 2018, 33(3): 458-464.
[9] 熊伟,徐永力,姚力波,崔亚奇. 基于SVM的高分辨率SAR图像舰船目标检测算法[J]. 遥感技术与应用, 2018, 33(1): 119-127.
[10] 田峰,陈冬花,黄新利,李虎,姚国慧. 基于形态学阴影指数的高分二号影像建筑物高度估计#br#[J]. 遥感技术与应用, 2017, 32(5): 844-850.
[11] 陈洋波,张涛,窦鹏,董礼明,陈华. 基于SVM的东莞市土地利用/覆被自动分类误差来源与后处理[J]. 遥感技术与应用, 2017, 32(5): 893-903.
[12] 史飞飞,高小红,杨灵玉,何林华,贾伟. 基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J]. 遥感技术与应用, 2017, 32(2): 206-217.
[13] 胡根生,吴问天,黄文江,梁栋,黄林生. 粒子群优化的最小二乘支持向量机在小麦白粉病监测中的应用[J]. 遥感技术与应用, 2017, 32(2): 299-304.
[14] 王艳楠,王健健,龚健新,袁帅,刘辉,罗文. 基于环境卫星数据的沿海滩涂地物类型分类的随机森林方法[J]. 遥感技术与应用, 2016, 31(6): 1107-1113.
[15] 鲍蕊,夏俊士,薛朝辉,杜培军,车美琴. 基于形态学属性剖面的高光谱影像集成分类[J]. 遥感技术与应用, 2016, 31(4): 731-738.