Abstract
Feature extraction is an essential task in the classification of high-resolution remote sensing images, with the primary technique being the object-oriented classification method. Current research describes object-oriented classification methods by using remote sensing data, wherein how to reduce the redundant feature information to achieve good classification results is the most challenging problem. The high-resolution remote sensing image is characteristic of a large amount of data and high feature dimensions, which also exist particularly in the forestry remote sensing. Feature information redundancy can reduce the extraction accuracy and make the classification results worse. To address this problem, in this paper we propose a framework that uses the rough set theory and the membership function to establish the classification rule set. In our approach, we first select an optimal segmentation scale to segment the remote sensing image with multi-scale and apply the rough set theory to reduce the feature dimensions of objects. We then use the selected features to establish classification rule set and classify image objects. This paper also presents a detailed study of the proposed framework for species classification with ALOS images, wherein 13 most effective feature parameters are selected from 34 feature parameters of objects, such as band ratio, brightness value, and average gray value. Our experimental results demonstrate that the proposed framework, applied to classify tree species, achieves a classification accuracy of 80.4509%, which is an improvement over both the classification accuracy of 77.2408% achieved with the traditional supervised classification and that of 75.5068% achieved with the nearest neighbor classification. The research proves that the proposed framework can effectively take advantage of tree species information in remote sensing images, and provides an auxiliary means for forest resources investigation and monitoring.
Similar content being viewed by others
References
Brauner N, Shacham M (2000) Considering precision of data in reduction of dimensionality and PCA. Comput Chem Eng 24(12):2603–2611
Bruzzone L, Carlin L (2006) A multilevel context-based system for classification of very high spatial resolution images. IEEE Trans Geosc Remote Sens 44(9):2587–2600
Cao X, Ke CQ (2006) Classification of high-resolution remote sensing images using object-oriented method. Remote Sens Info 58(5):27–28
Chen YH, Feng T, Shi PJ, et al. (2006) Classification of Remote Sensing Image Based on Object Oriented and Class Rules. Geomatics Inf Sci Wuhan Univ
Chen ZQ, Shi JS, Bai FX (2013) Automatic image classification based on fuzzy-rough set. J Jilin Univ 43:209–212
Dash M, Liu H (1997) Feature selection for classification. Intelligent Data Anal 1(3):131–156
Guo YG, Yu XF, Jiang D (2012) Study on forest classification based on object oriented technique. J Geogr Inf Sci 14(4):514–522
Hu QT, Yuan ZP, Zhou ZH (2008) Data extraction based on rough set and genetic algorithm. J Jiangxi Blue Sky Univ 11:336–340
Huang L (2011) Laplacian Eigenmaps for hyperspectral remote sensing image dimensionality reduction. Remote Sens Info 39(6):37–41
Huang QY (2012) RS image classification based on rough sets theory and SVM classification algorithm. Kunming Univ Sci Technol
Law MHC, Jain AK (2006) Incremental nonlinear dimensionality reduction by manifold learning. IEEE Trans Pattern Anal Mac Intell 28(3):377–391
Leung Y, Fung T, Mi JS et al (2007) A rough set approach to the discovery of classification rules in spatial data[J]. Int J Geogr Inf Sci 21(9):1033–1058
Li HM, Zhou GH, Wang KQ (2007) A knowledge discovery method based on rough set theory and genetic algorithm. Comput Appl 8(1):76–78
Li M, Cui SY, Li CM et al (2008) Object oriented information extraction from high resolution remote sensing imagery—taking the extraction of farmland for an example. Remote Sens Info 18(6):63–65
Licciardi GA, Khan MM, Chanussot J et al (2011) Fusion of hyperspectral and panchromatic images using multiresolution analysis and nonlinear PCA band reduction. Eurasip J Adv Signal Process 2012(1):1–17
Lin C, Gong ZN, Zhao WJ (2010) The extraction of wetland hydrophytes types based on medium resolution TM data. Acta Ecol Sin 30(23):6460–6469
Liu P, Choo KKR, Wang L, et al. (2016) SVM or deep learning? A comparative study on remote sensing image classification. Soft Comput
Ma Y, Wu H, Wang L et al (2015) Remote sensing big data computing: challenges and opportunities. Futur Gener Comput Syst 51:47–60
Maaten LJPVD, Postma EO, Herik HJVD (2007) Dimensionality reduction: a comparative review. J Mach Learn Res 10(1)
Mu HJ, Er X, Jing CM (2006) Discretization algorithm applied to interval numbers. Comput Eng Appl
Myint SW, Lam NS-N, Tyler JM (2004) Wavelets for urban spatial feature discrimination: comparisons with fractal, spatial autocorrelation, and spatial Co-occurrence approaches. Photogramm Eng Remote Sens 70(7):803–812
Nie Q, Ye XT (2012) Classification of high-resolution remote sensing image based on object oriented and feature combination. Urban Geotech Investig Surv
Pawlak Z (1982) Rough sets. Int J Comput Inform Sci 11:314–356
Puri AB, Bhattacharyya B (2015) Remote sensing classification information extraction based on rough set theory. J Jilin Univ 45(4):1246–1256
Susmaga R, Słowiński R, Greco S et al (2000) Generation of reducts and rules in multi-attribute and multi-criteria classification. Control Cybern 29(4):969–988
Tang TQ (2015) Research on vegetation information extraction using high-resolution remotely sensed image object-oriented method based. Jilin Univ
Tian XG, Zhang JX, Zhang YH (2007) Extraction of mangrove information using object-oriented method. Hydrogr Surv Chart 27(2):41–44
Wang QL (2008) Study on object-oriented remote sensing image classification and its application-taking urban vegetation extraction in Fujian, Shenzhen City for example, Nanjing Forestry University
Wang L, Song W, Liu P (2016a) Link the remote sensing big data to the image features via wavelet transformation. Clust Comput 19(2):793–810
Wang L, Ma Y, Yan J, et al. (2016b) pipsCloud: High performance cloud computing for remote sensing big data management and processing. Futur Gener Comput Syst
Wang L, Zhang J, Liu P, et al. (2016c) Spectral–spatial multi-feature-based deep learning for hyperspectral remote sensing image classification. Soft Comput
Xiao HG, Sang L, Ding SZ, Gong Y (2006) Rough set attribute reduction algorithm based on GA and its application. Comput Eng Appl
Zhang ZC (2007) The wetland research with remote sensing image based on object-oriented classification in Xixi, Hangzhou. Zhejiang Univ
Zhang Z, Wang J, Zha H (2012) Adaptive manifold learning. IEEE Trans Pattern Anal Mach Intell 34(2):253–265
Zhu ZJ (2010) Study on mine area information extraction based on object-oriented high-resolution remote sensing image classification and its application, China University of Geosciences
Acknowledgments
This work was Supported by Beijing Natural Science Foundation (NO. 6164038) and China Fundamental Research Funds for the Central Universities (NO. TD2014-2). The authors would like to express their gratitude to the funds for the financial support.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zeng, Y., Wang, S., Zhao, T. et al. An application of tree species classification using high-resolution remote sensing image based on the rough set theory. Multimed Tools Appl 76, 22999–23015 (2017). https://doi.org/10.1007/s11042-016-4210-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-4210-8