联合GF-5与GF-6卫星数据的多分类器组合亚热带树种识别

doi:10.11707/j.1001-7488.20201010

Abstract

Abstract:

Objective: In view of the problems that the recognition accuracy of remote sensing tree species under the complex stratospheric structure and high forest density of subtropical forest is not high, and that the performances of different classification algorithms to the recognition of different tree species are various, the method of multi-classor combined tree species recognition of high spectral resolution combined with high spatial resolution data was investigated to promote the in-depth application of multi-source data in the field of forest resource survey and monitoring. Method: Taken Huangfu Mountain National Forest Park as research area, and assisted with data of GF-6 PMS and GF-5 AHSI, digital elevation model(DEM) and forest resource survey data, the effective tree species recognition algorithm of multi-classor adaptive for object multi-source data, which is under the conditions of subtropical natural secondary forests, complex coronary structures and high forest density, was built in this study. First of all, the GF-6 PMS data was divided according to object-oriented multi-scale and combined with the field survey data by using the graph cutting algorithm(GC) to select the sample. Then, it was carried out to use GF-5 AHSI data to extract 26 vegetation index features(VIF), to use GF-6 PMS data to extract 128 parties of each band texture features(TEF), and combined with 304 bands of GF-5 AHSI with removal of bad band as spectral features(SF) and 3 DEM-built terrain factors as terrain features(TRF, factor features according to various inter-class separability were selected and 10 recognition schemes based on characteristic selection results were built. Finally, the weight adaptive voting combination classifier(WACC) using near-category(KNN), support vector machine(SVM), Bayesian classification(Bayesian), classification regression tree(CART), and random forest(RF) was constructed to recognize tree species based on 10 classification schemes and to verify the accuracy of tree species identification. Result: Under the linear discriminant analysis model, the discriminant accuracy was identified to tend to be stable when the factor of spectral characteristics, texture features and vegetation index characteristic were increased to 28, 12 and 10, respectively. The spectral characteristic factors with better recognition ability for the tree species were mainly concentrated in the red light and near-infrared bands, the texture feature factors mainly concentrated on mean, entropy and angular second-order moment, while the vegetation index features were mainly concentrated on the index of characterization greenness, carbon attenuation, and coronary aquifer aquifers. The overall accuracy of tree species recognition in the weight adaptive classifier combination algorithm was 87.51%, and the Kappa coefficient of 0.854 was better than that of the single classifier algorithm. The overall accuracy obtained by different characteristic factor schemes under each classification algorithm was as follows: SF+TEF+VIF > SF+TEF+VIF+TRF > SF+TEF+TRF > SF+VIF > SF+VIF+TRF > SF+TEF > SF > SF+TRF > VIF > TEF. Conclusion: he weight adaptive classifier combination algorithm under the combination of SF-TEF-VIF features could effectively identify tree species in subtropical natural secondary forests, and enjoy good recognition accuracy and credibility, and the data of GF-5 AHIS and GF-6 PMS would present a good application potential and prospect in the fields of forest resource survey and monitoring.

Key words: combinatorial classifier, GF-5, GF-6, tree species identification, object oriented, feature selection

CLC Number:

S757

Xusheng Li,Hu Li,Donghua Chen,Yufeng Liu,Saisai Liu,Congfang Liu,Guoqing Hu. Multiple Classifiers Combination Method for Tree Species Identification Based on GF-5 and GF-6[J]. Scientia Silvae Sinicae, 2020, 56(10): 93-104.

Figures/Tables 12

Table 1

Fig.1

Table 2

Fig.2

Table 3

Fig.3

Fig.4

Table 4

Table 5

Fig.5

Fig.6

Table 6

References 0

	陈尔学, 李增元, 谭炳香, 等. 高光谱数据森林类型统计模式识别方法比较评价. 林业科学, 2007. 43 (1): 84- 89.
	Chen E X , Li Z Y , Tan B X , et al. Validation of statistic based forest types classification methods using hyperspectral data. Scientia Silvae Sinicae, 2007. 43 (1): 84- 89.
	陈向宇, 云挺, 薛联凤, 等. 基于激光雷达点云数据的树种分类. 激光与光电子学进展, 2019. 56 (12): 122801.
	Chen X Y , Yun T , Xue L F , et al. Classification of tree species based on LiDAR point cloud data. Laser & Optoelectronics Progress, 2019. 56 (12): 122801.
	冯海林, 胡明越, 杨垠晖, 等. 基于树木整体图像和集成迁移学习的树种识别. 农业机械学报, 2019. 50 (8): 235- 242.
	Feng H L , Hu M Y , Yang Y H , et al. Tree species recognition based on overall tree image and ensemble of transfer learning. Transactions of the Chinese Society for Agricultural Machinery, 2019. 50 (8): 235- 242.
	傅锋, 王新杰, 汪锦, 等. 高分二号影像树种识别及龄组划分. 国土资源遥感, 2019. 31 (2): 118- 124.
	Fu F , Wang X J , Wang J , et al. Tree species and age groups classification based on GF-2 image. Remote Sensing for Land and Resources, 2019. 31 (2): 118- 124.
	李想, 刘凯, 朱远辉, 等. 基于资源三号影像的红树林物种分类研究. 遥感技术与应用, 2018. 33 (2): 360- 369.
	Li X , Liu K , Zhu Y H , et al. Study on mangrove species classification based on ZY-3 image. Remote Sensing Technology and Application, 2018. 33 (2): 360- 369.
	刘帆, 王传宽, 王兴昌. 近地遥感在森林冠层物候动态监测中的应用. 应用生态学报, 2018. 29 (6): 1768- 1778.
	Liu F , Wang C K , Wang X C . Application of near-surface remote sensing in monitoring the dynamics of forest canopy phenology. Chinese Journal of Applied Ecology, 2018. 29 (6): 1768- 1778.
	刘丽娟, 庞勇, 范文义, 等. 机载LiDAR和高光谱融合实现温带天然林树种识别. 遥感学报, 2013. 17 (3): 679- 695.
	Liu L J , Pang Y , Fan W Y , et al. Fused airborne LiDAR and hyperspectral data for tree species identification in a natural temperate forest. Jourmal of Remote Sensing, 2013. 17 (3): 679- 695.
	刘怡君, 庞勇, 廖声熙, 等. 机载LiDAR和高光谱融合实现普洱山区树种分类. 林业科学研究, 2016. 29 (3): 407- 412.
	Liu Y J , Pang Y , Liao S X , et al. Merged airborne LiDAR and hyperspectral data for tree species classification in Puer's mountainous area. Forest Research, 2016. 29 (3): 407- 412.
	刘银年. "高分五号"卫星可见短波红外高光谱相机的研制. 航天返回与遥感, 2018. 39 (3): 25- 28.
	Liu Y N . Visible-shortwave infrared hyperspectral imager of GF-5 satellite. Spacecraft Recovery & Remote Sensing, 2018. 39 (3): 25- 28.
	任冲, 鞠洪波, 张怀清, 等. 多源数据林地类型的精细分类方法. 林业科学, 2016. 52 (6): 54- 65.
	Ren C , Ju H B , Zhang H Q , et al. Multi-source data for forest land type precise classification. Scientia Silvae Sinicae, 2016. 52 (6): 54- 65.
	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. 应用生态学报, 2015. 26 (6): 1665- 1672.
	Tian T , Fan W Y , Lu W , et al. An object-based information extraction technology for dominant tree species group types. Chinese Journal of Applied Ecology, 2015. 26 (6): 1665- 1672.
	滕文秀, 温小荣, 王妮, 等. 基于深度迁移学习的无人机高分影像树种分类与制图. 激光与光电子学进展, 2019. 56 (7): 277- 286.
	Teng W X , Wen X R , Wang N , et al. Tree species classification and mapping based on deep transfer learning with unmanned aerial vehicle high resolution images. Laser & Optoelectronics Progress, 2019. 56 (7): 277- 286.
	王怀警, 谭炳香, 王晓慧, 等. 多分类器组合森林类型精细分类. 遥感信息, 2019. 34 (2): 107- 115.
	Wang H J , Tan B X , Wang X H , et al. Multiple classifiers combination method for precise classification of forest type. Remote Sensing Information, 2019. 34 (2): 107- 115.
	王怀警, 谭炳香, 房秀凤, 等. C5. 0决策树Hyperion影像森林类型精细分类方法.浙江农林大学学报, 2018. 35 (4): 724- 734.
	Wang H J , Tan B X , Fang X F , et al. Precise classification of forest types use Hyperion image based on the C5.0 decision tree algorithm. Journal of Zhejiang A&F University, 2018. 35 (4): 724- 734.
	王二丽, 李存军, 周静平, 等. 基于多时相遥感影像的北京平原人工林树种分类. 北京工业大学学报, 2017. 43 (5): 710- 718.
	Wang E L , Li C J , Zhou J P , et al. Classification of Beijing afforestation species based on multi-temporal images. Journal of Beijing University of Technology, 2017. 43 (5): 710- 718.
	邢丽玮,牛振国,王华斌,等. 2018.基于优选特征及月合成Landsat数据湿地提取研究.地理与地理信息科学, 34(3):4, 86-92.
	Xing L W, Niu Z G, Wang H B, et al. 2018. Study on wetland extraction using optimal features and monthly synthetic Landsat data. Geography and Geo-Information Science, 34(3):4, 86-92.[in Chinese]
	徐凯健, 田庆久, 岳继博, 等. 基于多光谱影像的森林树种识别及其空间尺度响应. 应用生态学报, 2018. 29 (12): 3986- 3994.
	Xu K J , Tian Q J , Yue J B , et al. Forest tree species identification and its response to spatial scale based on multispectral and multi-resolution remotely sensed data. Chinese Journal of Applied Ecology, 2018. 29 (12): 3986- 3994.
	于丽柯, 于颖, 柳向宇, 等. 基于高光谱影像的树种分类. 东北林业大学学报, 2016. 44 (9): 40- 43.
	Yu L K , Yu Y , Liu X Y , et al. Tree species classification with hyperspectral image. Journal of Northeast Forestry University, 2016. 44 (9): 40- 43.
	Alonzo M , Bookhagen B , Roberts D A . Urban tree species mapping using hyperspectral and lidar data fusion. Remote Sensing of Environment, 2014. 148, 70- 83. doi: 10.1016/j.rse.2014.03.018
	Kamal M , Phinn S R . Hyperspectral data for mangrove species mapping, a comparison of pixel-based and object-based approach. Remote Sensing, 2011. 3 (10): 2222- 2242. doi: 10.3390/rs3102222
	Koukal T , Atzberger C , Schneider W . Evaluation of semi-empirical BRDF models inverted against multi-angle data from a digital airborne frame camera for enhancing forest type classification. Remote Sensing of Environment, 2014. 151, 27- 43. doi: 10.1016/j.rse.2013.12.014
	Lucas R , Bunting P , Paterson M , et al. Classification of Australian forest communities using aerial photography, CASI and HyMap data. Remote Sensing of Environment, 2008. 112 (5): 2088- 2103. doi: 10.1016/j.rse.2007.10.011
	Pu RL , Landry S . A comparative analysis of high spatial resolution IKONOS and WorldView-2 imagery for mapping urban tree species. Remote Sensing of Environment, 2012. 124, 516- 533. doi: 10.1016/j.rse.2012.06.011
	Tang L N , Shao G F . Drone remote sensing for forestry research and practices. Journal of Forestry Research, 2015. 26 (4): 791- 797. doi: 10.1007/s11676-015-0088-y
	Yang X H , Rochdi N , Zhang J K , et al. Mapping tree species in a boreal forest area using RapidEye and LiDAR data. International Geoscience and Remote Sensing Symposium, 2014. 69- 71.
	Yu X W , Hyyppa J , Litkey P , et al. Single-sensor solution to tree species classification using multispectral airborne laser scanning. Remote Sensing, 2017. 9 (2): 108- 123. doi: 10.3390/rs9020108

影像 Image	产品号 Product ID	中心经纬度 Center coordinate	成像时间 Imaging date	幅宽 Width/km	空间分辨率 Spatial resolution/m	光谱分辨率 Spectral resolution/nm
GF-5 AHSI	45157	118.02°E，32.30°N	2019-05-22	60	30	5/10
GF-6 PMS	1119873930	117.90°E，32.10°N	2019-05-01	90	2/8	450/70

1级类型 The first level category	2级类型 The second level category	3级类型 The third level category
林地 Forest land	可识别林地 Identifiable forest types	麻栎Quercus acutissima
		朴树 Celtis sinensis
		黄檀 Dalbergia hupeana
		马尾松 Pinus massoniana
		湿地松 Pinus elliottii
		杉木 Cunninghamia lanceolata
	其他林地 Other forest types
非林地 Non-forest land	耕地 Farmland
	水域 Water
	建筑用地 Construction land
	未利用地 Unused land

类型Category	特征Features
光谱特征 Spectral features(SF)	VNIR₁-VNIR₁₅₀、SWIR₁-SWIR₄₂、SWIR₅₁-SWIR₉₅、SWIR₁₁₃-SWIR₁₇
纹理特征 Texture features(TEF)	HOM_1-0、HOM_1-45、HOM_1-90、HOM_1-135、HOM_2-0、HOM_2-45、HOM_2-90、HOM_2-135、HOM_3-0、HOM_3-45、HOM_3-90、HOM_3-135、HOM_4-0、HOM_4-45、HOM_4-90、HOM_4-135、CON_1-0、CON_1-45、CON_1-90、CON_1-135、CON_2-0、CON_2-45、CON_2-90、CON_2-135、CON_3-0、CON_3-45、CON_3-90、CON_3-135、CON_4-0、CON_4-45、CON_4-90、CON_4-135、DIS_1-0、DIS_1-45、DIS_1-90、DIS_1-135、DIS_2-0、DIS_2-45、DIS_2-90、DIS_2-135、DIS_3-0、DIS_3-45、DIS_3-90、DIS_3-135、DIS_4-0、DIS_4-45、DIS_4-90、DIS_4-135、ENT_1-0、ENT_1-45、ENT_1-90、ENT_1-135、ENT_2-0、ENT_2-45、ENT_2-90、ENT_2-135、ENT_3-0、ENT_3-45、ENT_3-90、ENT_3-135、ENT_4-0、ENT_4-45、ENT_4-90、ENT_4-135、MEA_1-0、MEA_1-45、MEA_1-90、MEA_1-135、MEA_2-0、MEA_2-45、MEA_2-90、MEA_2-135、MEA_3-0、MEA_3-45、MEA_3-90、MEA_3-135、MEA_4-0、MEA_4-45、MEA_4-90、MEA_4-135、STD_1-0、STD_1-45、STD_1-90、STD_1-135、STD_2-0、STD_2-45、STD_2-90、STD_2-135、STD_3-0、STD_3-45、STD_3-90、STD_3-135、STD_4-0、STD_4-45、STD_4-90、STD_4-135、COR_1-0、COR_1-45、COR_1-90、COR_1-135、COR_2-0、COR_2-45、COR_2-90、COR_2-135、COR_3-0、COR_3-45、COR_3-90、COR_3-135、COR_4-0、COR_4-45、COR_4-90、COR_4-135、ASM_1-0、ASM_1-45、ASM_1-90、ASM_1-135、ASM_2-0、ASM_2-45、ASM_2-90、ASM_2-135、ASM_3-0、ASM_3-45、ASM_3-90、ASM_3-135、ASM_4-0、ASM_4-45、ASM_4-90、ASM_4-135
植被指数特征Vegetation index features(VIF)	NDVI、SR、EVI、ARVI、NDVI₇₀₅、mSR₇₀₅、mNDVI₇₀₅、VOG1、VOG2、VOG3、REP、PRI、SIPI、RG、NDNI、NDLI、CAI、PSRI、CRI1、CRI2、ARI1、ARI2、WBI、NDWI、MSI、NDII
地形特征Terrain features(TRF)	DEM、ASP、SLO

分类方案 Classification scheme	属性类型 Type of feature
方案1 Scheme 1	光谱特征+纹理特征+植被指数特征+地形特征SF+TEF+VIF+TRF
方案2 Scheme 2	光谱特征+纹理特征+植被指数特征 SF+TEF+VIF
方案3 Scheme 3	光谱特征+纹理特征+地形特征SF+TEF+TRF
方案4 Scheme 4	光谱特征+植被指数特征+地形特征 SF+VIF+TRF
方案5 Scheme 5	光谱特征+纹理特征SF+TEF
方案6 Scheme 6	光谱特征+植被指数特征SF+VIF
方案7 Scheme 7	光谱特征+地形特征SF+TRF
方案8 Scheme 8	光谱特征SF
方案9 Scheme 9	纹理特征TEF
方案10 Scheme 10	植被指数特征VIF

算法 Algorithms	参数 Parameters	树种 Tree species
算法 Algorithms	参数 Parameters	麻栎 Quercus acutissima	朴树 Celtis sinensis	黄檀 Dalbergia hupeana	马尾松 Pinus massoniana	湿地松 Pinus elliottii	杉木 Cunninghamia lanceolata	其他 Others
WACC	制图精度 PA(%)	97.50	77.50	92.50	85.00	92.50	80.00	87.50
	用户精度 UA(%)	90.70	77.50	90.24	91.89	92.50	88.89	77.78
	总体精度 OA(%)	87.51
	Kappa	0.854
SVM	制图精度 PA(%)	87.50	77.50	92.50	95.00	72.50	82.50	91.67
	用户精度 UA(%)	94.59	83.78	94.87	86.36	72.50	86.84	75.86
	总体精度 OA(%)	85.22
	Kappa	0.827
RF	制图精度 PA(%)	90.00	75.00	95.00	67.50	77.50	85.00	95.83
	用户精度 UA(%)	92.31	88.24	88.37	67.50	73.81	85.00	88.46
	总体精度 OA(%)	83.14
	Kappa	0.803
CART	制图精度 PA(%)	80.00	87.50	72.50	82.50	75.00	67.50	91.67
	用户精度 UA(%)	78.05	89.74	76.32	73.33	71.43	79.41	88.00
	总体精度 OA(%)	78.82
	Kappa	0.752
Bayesian	制图精度 PA(%)	85.00	65.00	80.00	87.50	72.50	62.50	87.50
	用户精度 UA(%)	89.47	68.42	72.73	85.37	76.32	67.57	75.00
	总体精度 OA(%)	76.49
	Kappa	0.725

Multiple Classifiers Combination Method for Tree Species Identification Based on GF-5 and GF-6

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 0

Related Articles 2

Recommended Articles

Metrics

Comments

树种 Tree species	实地样点 Field plots	对象样点 Object plots	扩展样点 Extended plots
麻栎 Quercus acutissima	64	42	100
朴树 Celtis sinensis	72	53	100
黄檀 Dalbergia hupeana	66	60	100
马尾松 Pinus massoniana	70	49	100
湿地松 Pinus elliottii	77	71	100
杉木 Cunninghamia lanceolata	78	69	100
其他 Others	52	42	60

[1]	Dakun Lin,Shiguo Huang,Feiping Zhang,Guanghong Liang,Songqing Wu,xia Hu,Rong Wang. Method of Image Recognition for Lepidopteran Insects Based on Improved Differential Evolution Algorithm [J]. Scientia Silvae Sinicae, 2020, 56(3): 73-81.
[2]	Han Zongtao, Jiang Hong, Wang Wei, Li Zengyuan, Chen Erxue, Yan Min, Tian Xin. Forest Above-Ground Biomass Estimation Using KNN-FIFS Method Based on Multi-Source Remote Sensing Data [J]. Scientia Silvae Sinicae, 2018, 54(9): 70-79.