我们的网站为什么显示成这样?

可能因为您的浏览器不支持样式,您可以更新您的浏览器到最新版本,以获取对此功能的支持,访问下面的网站,获取关于浏览器的信息:

|Table of Contents|

基于非参数分类算法和多源遥感数据的单木树种分类(PDF)

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

Issue:
2019年05期
Page:
103-112
Column:
研究论文
publishdate:
2019-09-20

Article Info:/Info

Title:
Individual tree species classification based on nonparametric classification algorithms and multi-source remote sensing data
Article ID:
1000-2006(2019)05-0103-10
Author(s):
ZHAO Yinghui ZHANG Dali ZHEN Zhen*
(School of Forestry, Northeast Forestry University, Harbin 150040, China)
Keywords:
light detection and ranging(LiDAR) individual tree crown delineation random forest feature selection support vector machine(SVM)
Classification number :
S771; TP751.1
DOI:
10.3969/j.issn.1000-2006.201810041
Document Code:
A
Abstract:
【Objective】 Forest vegetation is a principal part of forest resources. Accurate identification of forest vegetation types is important for research and utilization of forest resources. The combination of different characteristics of remote sensing data has great advantages for determining forest vegetation types and forest parameter estimation, which could be used to classify tree species more effectively. In the face of massive feature data, the use of classifiers that are insensitive to dimensionality could also result in a decrease in classification accuracy. At the same time, nonparametric classifiers [random forest(RF)and support vector machine(SVM)] will improve classification accuracy by adding non-spectral data to the classification process. In this study, the main impact of feature selection on classification results was explored, the importance of different features for tree species classification was studied, and the effectiveness of multi-source data for individual tree species classification was investigated. 【Method】 Two plots(100 m × 100 m)in the Zhonglin District of Maoershan Forest Farm of Northeast Forestry University, Heilongjiang Province, China, were used as the study area, multi-spectral remote sensing charge coupled device(CCD)images and airborne light detection and ranging(LiDAR)data were taken as data resources, and forest resource survey data from 2016 were taken as the basis of forest types classification system. First, LiDAR data were preprocessed and a canopy height model(CHM)was generated using the separated point cloud data. Then, CHM was optimized using the Khosravipour algorithm and individual tree crowns were segmented by region-based hierarchical cross-section analysis; subsequently, an accuracy assessment was performed. Second, 37 features, such as height, intensity and canopy size, were extracted based on airborne LiDAR data and a total of 21 texture and spectral features were extracted based on CCD images. Feature selection was performed using the RF method. Next, two kinds of nonparametric classifiers, including RF and SVM, were used for classification by combining with the segmented image object and selected features and 12 classification schemes. Finally, 40% of the data from each tree species were randomly selected to test the overall accuracy(OA), user's accuracy, and producer accuracy based on stratified sampling. Classification results were compared and evaluated. 【Result】 The detection accuracy of individual tree crown segmentation was over 80%, which conforms to forestry production requirements. In total, 12 features were retained using only airborne LiDAR data, 11 features were retained using only CCD images, and 11 features were retained by combining with the two datasets after RF feature selection. Then, the importance ranking of mean decrease accuracy was performed. After RF feature selection, the tree species classification results were better than those without RF feature selection. OA can be increased by an average of 3.47%. The average accuracy of combining CCD images and airborne LiDAR was increased by 6.07% compared with the average accuracy of using only CCD images. 【Conclusion】 RF feature selection could optimize features, reduce feature redundancy, and improve tree species classification accuracy. Multi-source data could also improve tree species classification accuracy. When combined with multi-source data, spectral features were the most important feature, and intensity features extracted from LiDAR data were more stable than height features. In the future, the combination of more band images and LiDAR data for different study areas will be considered and further studies will be conducted by adding more crown structure and spectral features.

References

[1] 刘旭升, 张晓丽. 森林植被遥感分类研究进展与对策[J]. 林业资源管理, 2004(1): 61-64. DOI:10.3969/j.issn.1002-6622.2004.01.016. LIU X S, ZHANG X L. Research advances and countermeasures of remote sensing classification of forest vegetation[J]. Forest Resources Management, 2004(1): 61-64. [2] WULDER M A, HALL R J, COOPS N C, et al. High spatial resolution remotely sensed data for ecosystem characterization[J]. BioScience, 2004, 54(6): 511-521. DOI: 10.1641 /0006-3568(2004)054 [0511:hsrrsd] 2.0.co; 2. [3] VAUHKONEN J, MALTAMO M, MCROBERTS R E, et al. Introduction to forestry applications of airborne laser scanning[C]//VAUHKONEN J, MALTAMO M, MCROBERTS R E, et al. Forestry Applications of Airborne Laser Scanning. Dordrecht: Springer Netherlands, 2013: 1-16. DOI: 10.1007 /978-94-017-8663-8 _1. [4] ZHANG Z Y, LIU X Y. Support vector machines for tree species identification using LiDAR-derived structure and intensity variables[J]. Geocarto International, 2013, 28(4): 364-378. DOI:10.1080/10106049. 2012. 710653. [5] SWATANTRAN A, DUBAYAH R, ROBERTS D, et al. Mapping biomass and stress in the Sierra Nevada using lidar and hyperspectral data fusion[J]. Remote Sensing of Environment, 2011, 115(11): 2917-2930. DOI:10.1016/j.rse.2010.08.027. [6] 李春干, 邵国凡. Landsat 7 ETM+图像用作SPOT5图像森林分类的辅助数据研究[J]. 北京林业大学学报, 2010, 32(4): 1-5. LI C G, SHAO G F. Using Landsat 7 ETM+ images as ancillary data for forest cover classification of SPOT5 images[J]. Journal of Beijing Forestry University, 2010, 32(4): 1-5. [7] 魏晶昱, 毛学刚, 方本煜, 等. 基于Landsat 8 OLI辅助的亚米级遥感影像树种识别[J]. 北京林业大学学报, 2016, 38(11): 23-33. DOI:10.13332/j.1000-1522.20160054. WEI J Y, MAO X G, FANG B Y, et al. Submeter remote sensing image recognition of trees based on Landsat 8 OLI support[J]. Journal of Beijing Forestry University, 2016, 38(11): 23-33. [8] HAN N, WANG K, YU L, et al. Integration of texture and landscape features into object-based classification for delineating Torreya using IKONOS imagery[J]. International Journal of Remote Sensing, 2012, 33(7): 2003-2033. DOI:10.1080/01431161.2011.605084. [9] BLASCHKE T. Object based image analysis for remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1): 2-16. DOI:10.1016/j.isprsjprs.2009.06.004. [10] KE Y H, QUACKENBUSH L J, IM J. Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification[J]. Remote Sensing of Environment, 2010, 114(6): 1141-1154. DOI:10.1016/j.rse.2010.01.002. [11] OLOFSSON K, WALLERMAN J, HOLMGREN J, et al. Tree species discrimination using Z/I DMC imagery and template matching of single trees[J]. Scandinavian Journal of Forest Research, 2006, 21(S7): 106-110. DOI:10.1080/14004080500486955. [12] BUNTING P, LUCAS R. The delineation of tree crowns in Australian mixed species forests using hyperspectral compact airborne spectrographic imager(CASI)data[J]. Remote Sensing of Environment, 2006, 101(2): 230-248. DOI:10.1016/j.rse.2005.12.015. [13] ZHEN Z, QUACKENBUSH L, ZHANG L J. Impact of tree-oriented growth order in marker-controlled region growing for individual tree crown delineation using airborne laser scanner(ALS)data[J]. Remote Sensing, 2014, 6(1): 555-579. DOI:10.3390/rs6010555. [14] CHEN Q, BALDOCCHI D, GONG P, et al. Isolating individual trees in a savanna woodland using small footprint lidar data[J]. Photogrammetric Engineering & Remote Sensing, 2006, 72(8): 923-932. DOI: 10.14358 /pers.72.8.923. [15] ZHAO Y H, HAO Y S, ZHEN Z, et al. A region-based hierarchical cross-section analysis for individual tree crown delineation using ALS data[J]. Remote Sensing, 2017, 9(10): 1084. DOI:10.3390/rs9101084. [16] DALPONTE M, BRUZZONE L, VESCOVO L, et al. The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas[J]. Remote Sensing of Environment, 2009, 113(11): 2345-2355. DOI:10.1016/j.rse.2009.06.013. [17] PANG Y, LI Z Y, JU H B, et al. LiCHy: the CAF's LiDAR, CCD and hyperspectral integrated airborne observation system[J]. Remote Sensing, 2016, 8(5): 398. DOI:10.3390/rs8050398. [18] ZHAO D, PANG Y, LI Z Y, et al. Filling invalid values in a lidar-derived canopy height model with morphological crown control[J]. International Journal of Remote Sensing, 2013, 34(13): 4636-4654. DOI:10.1080/01431161.2013.779398. [19] KHOSRAVIPOUR A, SKIDMORE A K, ISENBURG M, et al. Generating pit-free canopy height models from airborne lidar[J]. Photogrammetric Engineering & Remote Sensing, 2014, 80(9): 863-872. DOI: 10. 14358 /pers.80.9.863. [20] ANDERSEN H E, MCGAUGHEY R J, REUTEBUCH S E. Estimating forest canopy fuel parameters using LIDAR data[J]. Remote Sensing of Environment, 2005, 94(4): 441-449. DOI: 10. 1016/j.rse. 2004. 10.013. [21] LIN Y, HYYPPÄ J. A comprehensive but efficient framework of proposing and validating feature parameters from airborne LiDAR data for tree species classification[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 46: 45-55. DOI:10.1016/j.jag.2015.11.010 [22] YAO W, KRZYSTEK P, HEURICH M. Tree species classification and estimation of stem volume and DBH based on single tree extraction by exploiting airborne full-waveform LiDAR data[J]. Remote Sensing of Environment, 2012, 123: 368-380. DOI:10.1016/j.rse.2012.03.027. [23] SHI Y F, WANG T J, SKIDMORE A K, et al. Important LiDAR metrics for discriminating forest tree species in Central Europe[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 137: 163-174. DOI: 10.1016 /j.isprsjprs.2018.02.002. [24] ZHANG C Q, FRANKLIN S E, WULDER M A. Geostatistical and texture analysis of airborne-acquired images used in forest classification[J]. International Journal of Remote Sensing, 2004, 25(4): 859-865. DOI: 10.1080/01431160310001618059. [25] PAL M, FOODY G M. Feature selection for classification of hyperspectral data by SVM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(5): 2297-2307. DOI: 10.1109 /tgrs.2009. 2039484. [26] 季金胜. 高分辨率遥感影像典型地物目标的特征选择及其稳定性研究[D]. 上海: 上海交通大学, 2015. JI J S. Feature selection and its stability for typical geoobjects of the high-resolution remote sensing image[D]. Shanghai: Shanghai Jiaotong University, 2015. [27] BAKSHI B R. Multiscale PCA with application to multivariate statistical process monitoring[J]. AIChE Journal, 1998, 44(7): 1596-1610. DOI:10.1002/aic.690440712. [28] HASSANAT A B A, ESRA'N A, ALKAFAWEEN A. On enhancing genetic algorithms using new crossovers[J]. International Journal of Computer Applications in Technology, 2017, 55(3): 202. DOI:10.1504/ijcat.2017.084774. [29] ARCHER K J, KIMES R V. Empirical characterization of random forest variable importance measures[J]. Computational Statistics & Data Analysis, 2008, 52(4): 2249-2260. DOI:10.1016/j.csda.2007.08.015. [30] ADELE C, RICHARD C, JOHN R S. Random forests[J]. Machine Learning, 2004, 45(1): 157-176. DOI: DOI:10.1007/978-1-4419-9326-7_5. [31] BELGIU M, DRAGU 瘙 塃 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. DOI: 10.1016 /j.isprsjprs. 2016. 01. 011 [32] MOUNTRAKISM J, OGOLE C. Support vector machines in remote sensing: a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011, 66(3): 247-259. DOI:10.1016/j.isprsjprs.2010.11.001. [33] HUANG C L, WANG C J. A GA-based feature selection and parameters optimization for support vector machines[J]. Expert Systems with Applications, 2006, 31(2): 231-240.DOI:10.1016/j.eswa. 2005.09. 024. [34] 李星祥. 超高维数据的特征筛选研究[D]. 南京: 南京信息工程大学, 2016. LI X X. Study on ultrahigh dimensional feature screening[D]. Nanjing: Nanjing University of Information Science & Technology, 2016. [35] PHAM L T H, BRABYN L, ASHRAF S. Combining QuickBird, LiDAR, and GIS topography indices to identify a single native tree species in a complex landscape using an object-based classification approach[J]. International Journal of Applied Earth Observation and Geoinformation, 2016, 50: 187-197. DOI:10.1016/j.jag.2016.03.015. [36] ADELABU S, DUBE T. Employing ground and satellite-based QuickBird data and random forest to discriminate five tree species in a Southern African Woodland[J]. Geocarto International, 2015, 30(4): 457-471. DOI:10.1080/10106049.2014.885589. [37] HOVI A, KORHONEN L, VAUHKONEN J, et al. LiDAR waveform features for tree species classification and their sensitivity to tree-and acquisition related parameters[J]. Remote Sensing of Environment, 2016, 173: 224-237. DOI:10.1016/j.rse.2015.08.019. [38] SUMNALL M J, HILL R A, HINSLEY S A. Comparison of small-footprint discrete return and full waveform airborne lidar data for estimating multiple forest variables[J]. Remote Sensing of Environment, 2016, 173: 214-223. DOI:10.1016/j.rse.2015.07.027. [39] ØRKA H O, NÆSSET E, BOLLANDSÅS O M. Effects of different sensors and leaf-on and leaf-off canopy conditions on echo distributions and individual tree properties derived from airborne laser scanning[J]. Remote Sensing of Environment, 2010, 114(7): 1445-1461. DOI:10.1016/j.rse.2010.01.024. [40] KORPELA I, HOVI A, KORHONEN L. Backscattering of individual LiDAR pulses from forest canopies explained by photogrammetrically derived vegetation structure[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 83: 81-93. DOI:10.1016/j.isprsjprs.2013.06.002. [41] DENG S Q, KATOH M, YU X W, et al. Comparison of tree species classifications at the individual tree level by combining ALS data and RGB images using different algorithms[J]. Remote Sensing, 2016, 8(12): 1034. DOI:10.3390/rs8121034. [42] HOLMGREN J, PERSSON Å. Identifying species of individual trees using airborne laser scanner[J]. Remote Sensing of Environment, 2004, 90(4): 415-423. DOI:10.1016/s0034-4257(03)00140-8. [43] 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[J]. 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[J]. Journal of Remote Sensing, 2013, 17(3): 679-695. [44] DALPONTE M, ØRKA H O, ENE L T, et al. Tree crown delineation and tree species classification in boreal forests using hyperspectral and ALS data[J]. Remote Sensing of Environment, 2014, 140: 306-317. DOI:10.1016/j.rse.2013.09.006.

Last Update: 2019-10-08