Please wait a minute...
REMOTE SENSING FOR LAND & RESOURCES    2011, Vol. 23 Issue (2) : 87-90     DOI: 10.6046/gtzyyg.2011.02.16
Technology Application |
An Improved K-means Algorithm for Remote Sensing Classification
School of Earth Sciences and Resources, China University of Geosciences, Beijing 100083, China
Download: PDF(1422 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    

 If the classification type is unknown,the K-means algorithm will randomly select the initial values,and different initial values will lead to differences in remote sensing image classification results. To solve such problems,this paper proposes an improved K-means algorithm. First, logarithmical transform is performed for the original data,and then principal component transformation is implemented. The number of principal components for the K-means algorithm is determined according to the contribution rate (≥85%). The proposed method can weaken the noise. Kernel density estimation can be used to determine the probability density function of the first principal component, from which the initial label for multi-dimensional K-means algorithm can be efficiently determined,and the sensitivity of the initial value selected at random can be avoided.  Experiments show that the accuracy of the method proposed in this paper is higher than that of the traditional K-means based on mean-variance.

Keywords Medium resolution remotely sensed data      Land use and cover      Expert system      Decision tree      Iterative mixed analysis     


  TP 751.1

Issue Date: 17 June 2011
E-mail this article
E-mail Alert
Articles by authors
Cite this article:   
ZHAO Yue, ZHOU Ping . An Improved K-means Algorithm for Remote Sensing Classification[J]. REMOTE SENSING FOR LAND & RESOURCES,2011, 23(2): 87-90.
URL:     OR

[1]Hartigan J A,Wong M A.A K-means Clustering Algorithm[J].Applied Statistics,1979,28(1):100-108.

[2]Pena J M,Lozano J A,Larranaga P.An Empirical Comparison of Four Initialization Methods for the K-means Algorithm[J].Pattern Recognition Letters,1999,20:1027-1040.

[3]Stephen J,Redmond,Heneghan C.A Method for Initialising the K-means Clustering Algorithm Using Kd-trees[J].Pattern Recognition Letters,2007,28(8):965-973.

[4]Lu J F,Tang J B,Tang Z M,et al.Hierarchical Initialization Approach for K-means Clustering[J].Pattern Recognition Letters,2008,29(6):187-795.

[5]Chang C I,Du Q,Sun T L,et al.A Joint Band Prioritization and Band Decorrelation Approach to
Band Selection for Hyperspectral Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(6):2631-2641.

[6]Bowman A W,Azzalini A.Applied Smoothing Techniques for Data Analysis:the kernel approach with S-plus illustrations[M].UK:Oxford University Press,1997.

[1] LIU Hui, QI Zengxiang, HUANG Fuqiang. Spatio-temporal difference and correlation of urbanization with avian habitats in Dongting Lake area[J]. Remote Sensing for Land & Resources, 2020, 32(3): 191-199.
[2] Gang DENG, Zhiguang TANG, Chaokui LI, Hao CHEN, Huanhua PENG, Xiaoru WANG. Extraction and analysis of spatiotemporal variation of rice planting area in Hunan Province based on MODIS time-series data[J]. Remote Sensing for Land & Resources, 2020, 32(2): 177-185.
[3] Hailing GU, Chao CHEN, Ying LU, Yanli CHU. Construction of regional economic development model based on satellite remote sensing technology[J]. Remote Sensing for Land & Resources, 2020, 32(2): 226-232.
[4] Jisheng XIA, Mengying MA, Zhongren FU. Extraction of mechanical damage surface using GF-2 remote sensing data[J]. Remote Sensing for Land & Resources, 2020, 32(2): 26-32.
[5] Chao MA, Fei YANG, Xuecheng WANG. Extracting tea plantations in southern hilly and mountainous region based on mesoscale spectrum and temporal phenological features[J]. Remote Sensing for Land & Resources, 2019, 31(1): 141-148.
[6] Xianyu GUO, Kun LI, Zhiyong WANG, Hongyu LI, Zhi YANG. Fine classification of rice with multi-temporal compact polarimetric SAR based on SVM+SFS strategy[J]. Remote Sensing for Land & Resources, 2018, 30(4): 20-27.
[7] TAO Ting, RUAN Renzong, SUI Xiuzhen, WANG Yuqiang, LIN Peng. Extraction of floating-leaved vegetation information based on HyMap data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(2): 187-192.
[8] WANG Jinjie, DING Jianli, ZHANG Cheng, CHEN Wenqian. Method of water information extraction by improved SWI based on GF-1 satellite image[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(1): 29-35.
[9] SUN Yuyi, ZHAO Junli, WANG Miaomiao, LIU Yong. Land cover information extraction from remote sensing images using object-based image analysis method integrated with decision tree[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(4): 156-163.
[10] LU Fengling, GONG Zaiwu. Construction of cloud-shadow-water mask based on Random Forests algorithm[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(3): 73-79.
[11] ZHANG Xuehong. Decision tree algorithm of automatically extracting mangrove forests information from Landsat 8 OLI imagery[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 182-187.
[12] YANG Yuhui, YAN Meichun, LI Zhijia, YU Qing, CHEN Beibei. Classification model for "same subject with different spectra" on complicated surface in Southern hilly areas[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 79-83.
[13] HU Weiguo, MENG Lingkui, ZHANG Dongying, FAN Zhiwei, CHENG Jianguo, LI Xiaohui. Methods of water extraction from ZY-1 02C satellite imagery[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(2): 43-47.
[14] GAI Yingying, ZHOU Bin, SUN Yuanfang, ZHOU Yan. Study of extraction methods for ocean surface oil spill using HJ-CCD data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2014, 26(2): 99-104.
[15] WAN Jianhua, LI Mei, REN Guangbo, MA Yi. Efficient method for updating coastal wetland map based on change detection technology[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(4): 85-90.
Full text



Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech