Tree species classification using WorldView-2 images based on recursive texture feature elimination

LIU Huai-peng; AN Hui-jun; WANG Bing; ZHANG Qiu-liang

doi:10.13332/j.1000-1522.20140311

Journal of Beijing Forestry University > 2015 > 37(8): 53-59. > DOI: 10.13332/j.1000-1522.20140311

LIU Huai-peng, AN Hui-jun, WANG Bing, ZHANG Qiu-liang. Tree species classification using WorldView-2 images based on recursive texture feature elimination[J]. Journal of Beijing Forestry University, 2015, 37(8): 53-59. DOI: 10.13332/j.1000-1522.20140311

Citation:

PDF (1274 KB)

Tree species classification using WorldView-2 images based on recursive texture feature elimination

College of Forestry,Inner Mongolia Agricultural University,Huhhot,Inner Mongolia, 010019,P. R. China

More Information

Received Date: September 14, 2014
Revised Date: September 14, 2014
Published Date: August 30, 2015

Graphical Abstract

Abstract

Abstract

Identifying tree species by using remote sensing images is a scientific issue that remains unresolved yet, and many problems still exist in traditional methods for tree species classification using high resolution images. We extracted texture information from WorldView-2 images, constructed high-dimensional data, and reduced data dimension based on recursive texture feature elimination. Then the maximum likelihood classification hughes phenomenon was gradually relieved, and a representative subset of texture features was combined with spectral features so as to classify tree species. Results show that: after eliminating eight texture features, the maximum likelihood classification hughes phenomenon had been well avoided. In combination with spectral features, the overall accuracy of classification achieved 86.39%, Kappa coefficient reached 0.8410, which were 12.32% and 0.1436 higher than the results using only spectral features. Our study indicated that, avoiding the maximum likelihood classification hughes phenomenon by recursive texture feature elimination and fully combining image texture and spectral information would lead to more ideal results in tree species classification.

FullText(HTML)

References (23)

References

[1]	ZHANG L. Study on the hyperspectral remote sensed image classify based on PCA and SVM[J]. Optical Technique, 2008, 34(Suppl.):184-187.
[1]	MCPHERSON E G, NOWAK D J, ROWNTREE R A. Chicago's urban forest ecosystem: results of the Chicago Urban Forest Climate Project[M].Radnor, PA: Department of Agriculture, Forest Service, Northeastern Forest Experiment Station,1994.
[2]	GOUGEON F A, LECKIE D G. The individual tree crown approach applied to Ikonos images of a coniferous plantation area [J]. Photogrammetric Engineering and Remote Sensing, 2006,72:1287-1297.
[2]	YUAN L H,FU L,YANG Y, et al. Analysis of texture feature extracted by gray level co-occurrence matrix [J]. Journal of Computer Applications, 2009, 29(4): 1018-1021.
[3]	HEUMANN B W. An object-based classification of mangroves using a hybrid decision tree-support vector machine approach[J]. Remote Sensing, 2011, 3(11): 2440-2460.
[3]	LUO J C, WANG Q M, MA J H, et al. The EM-based maximum likelihood classifier for remotely sensed data[J]. Acta Geodaetica et Cartographica Sinica, 2002,31(3):234-239.
[4]	ZHANG H K, HUANG B, YU L. Kernel function in SVM-RFE based hyperspectral data band selection[J]. Remote Sensing Technology and Application, 2013,28(5):747-752,17.
[4]	IMMITZER M,ATZBERGER C,KOUKL T. Tree species classification with random forest using very high spatial resolution 8-Band WorldView-2 satellite data[J]. Remote Sensing, 2012,4:2661-2693.
[5]	IMMITZER M, ATZBERGER C, KOUKL T. Suitability of WorldView-2 data for tree species classification with special emphasis on the four new spectral bands[J]. Photogrammetrie, Fernerkundung, Geoinformation, 2012, 5:573-588.
[6]	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.
[7]	CHO M A, MATHIEU R, ASNER G P, et al. Mapping tree species composition in South African savannas using an integrated airborne spectral and LiDAR system[J]. Remote Sensing of Environment, 2012,125:214-226.
[8]	PEERBHAY K Y, MUTANGA O, ISMAIL R. Investigating the capability of few strategically placed WorldView-2 multispectral bands to discriminate forest species in KwaZulu-Natal, South Africa[J]. IEEE Geoscience & Remote Sensing Society, 2013, 7(1): 307-316.
[9]	DENG S Q, KATOH M,GUAN QW, et al. Interpretation of forest resources at the individual tree level at Purple Mountain, Nanjing City, China, using WorldView-2 imagery by combining GPS, RS and GIS technologies[J]. Remote Sensing, 2014, 6(1):87-110.
[10]	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, 26:298-311.
[11]	CLARK M L, ROBERTS D A, CLARK D B. Hyperspectral discrimination of tropicalrain forest tree species at leaf to crown scales[J]. Remote Sensing of Environment, 2005, 96(3-4):375-398.
[12]	张亮.基于PCA和SVM的高光谱遥感图像分类研究[J].光学技术,2008,34(增刊):184-187.
[13]	苑丽红,付丽,杨勇,等.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,29(4):1018-1021.
[14]	RYHERD S, WOODCOCK C E. Combining spectral and texture data in the segmentation of remotely sensed image[J]. Pohtorgammetric Engineering and Remote Sensing, 1997, 62:181-194.
[15]	骆剑承,王钦敏,马江洪,等.遥感图像最大似然分类方法的EM改进算法[J].测绘学报,2002,31(3):234-239.
[16]	GYSELS E, RENEVEY P, CELKA P. SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in brain-computer interfaces[J]. Signal Processing, 2005, 85(11):2178-2189.
[17]	张汉奎,黄波,俞乐.SVM-REF高光谱数据波段选择中核函数的研究[J].遥感技术与应用,2013,28(5):747-752,17.
[18]	SIMARD M,DE GRANDI G,SAATCHI S, et al. Mapping tropical coastal vegetation using JERS-1 and ERS-l radar data with a decision tree classifier[J]. International Journal of Remote Sensing, 2002,23(7):1461-1474.
[19]	PAL M, MATHER P M. Support vector machines for classification in remote sensing[J]. International Journal of Remote Sensing, 2005,26(5):1007-1011.

Cited By

Cited by

Periodical cited type(16)

1.	何紫玲，陈运春，郭晓飞，张莹，黄玉南，柳兴鹏，曾维军. 基于FSO算法的洱海流域土地利用分类适用性研究. 农业工程. 2024(09): 126-133 .
2.	谢天义，潘洁，孙玉琳，郑光. 应用多维遥感信息协同的森林树种分类. 东北林业大学学报. 2023(03): 73-78 .
3.	王晓洋，姜友谊，黎晓，胡亚轩，张家政，刘博伟. 基于GF-1影像的多时相多特征落叶松人工林提取研究. 林业资源管理. 2022(04): 109-118 .
4.	张悦楠，房磊，乔泽宇，陈龙池，张伟东，郑晓，江涛. 亚热带常绿林型遥感识别及尺度效应. 生态学杂志. 2020(05): 1636-1650 .
5.	毛学刚，姚瑶，陈树新，刘家倩，杜子涵，魏晶昱. 基于易康软件的QuickBird遥感影像林分类型识别——以福建省将乐林场为例. 南京林业大学学报(自然科学版). 2019(01): 127-134 .
6.	傅锋，王新杰，汪锦，王娜，佟济宏. 高分二号影像树种识别及龄组划分. 国土资源遥感. 2019(02): 118-124 .
7.	刘怀鹏，安慧君. Worldview-2树种分类T&N波段优势分析. 西部林业科学. 2019(03): 41-46 .
8.	王志辉，张乐，徐惠军，刘天阳，鲍永新. 基于高光谱遥感图像的树种(树种组)分类. 华东森林经理. 2019(02): 61-66 .
9.	刘怀鹏，安慧君. 基于Sentinel-2A的农田包围型村落提取. 内蒙古农业大学学报(自然科学版). 2019(03): 41-45 .
10.	张沁雨，李哲，夏朝宗，陈健，彭道黎. 高分六号遥感卫星新增波段下的树种分类精度分析. 地球信息科学学报. 2019(10): 1619-1628 .
11.	蔡林菲，吴达胜，方陆明，郑辛煜. 基于XGBoost的高分二号影像树种识别. 林业资源管理. 2019(05): 44-51 .
12.	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. 遥感技术与应用. 2019(05): 970-982 .
13.	林志玮，丁启禄，涂伟豪，林金石，刘金福，黄炎和. 基于多元HoG及无人机航拍图像的植被类型识别. 森林与环境学报. 2018(04): 444-450 .
14.	温小乐，钟奥，胡秀娟. 基于随机森林特征选择的城市绿化乔木树种分类. 地球信息科学学报. 2018(12): 1777-1786 .
15.	刘怀鹏，熊波，邱雪超，胡邦红，谭智勇，杨建. 森林覆被下铜仁地区环境遥感研究动向. 绿色科技. 2017(10): 205-207+214 .
16.	尹凌宇，覃先林，孙桂芬，祖笑锋，陈小中. 基于高分二号多光谱数据的树种识别方法. 林业资源管理. 2016(04): 121-127 .

Other cited types(18)

Get Citation

PDF

XML

Article views (1820) PDF downloads (45) Cited by(34)

Turn off MathJax

Article Contents

Abstract

References

Tree species classification using WorldView-2 images based on recursive texture feature elimination

Abstract

References

Cited by

Periodical cited type(16)

Other cited types(18)

Catalog

Export File

Citation

Format

Content