Parallel K-Means Clustering of Remote Sensing Images Based on MapReduce

  • Zhenhua Lv
  • Yingjie Hu
  • Haidong Zhong
  • Jianping Wu
  • Bo Li
  • Hui Zhao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6318)

Abstract

The K-Means clustering is a basic method in analyzing RS (remote sensing) images, which generates a direct overview of objects. Usually, such work can be done by some software (e.g. ENVI, ERDAS IMAGINE) in personal computers. However, for PCs, the limitation of hardware resources and the tolerance of time consuming present a bottleneck in processing a large amount of RS images. The techniques of parallel computing and distributed systems are no doubt the suitable choices. Different with traditional ways, in this paper we try to parallel this algorithm on Hadoop, an open source system that implements the MapReduce programming model. The paper firstly describes the color representation of RS images, which means pixels need to be translated into a particular color space CIELAB that is more suitable for distinguishing colors. It also gives an overview of traditional K-Means. Then the programming model MapReduce and a platform Hadoop are briefly introduced. This model requires customized ‘map/reduce’ functions, allowing users to parallel processing in two stages. In addition, the paper detail map and reduce functions by pseudo-codes, and the reports of performance based on the experiments are given. The paper shows that results are acceptable and may also inspire some other approaches of tackling similar problems within the field of remote sensing applications.

Keywords

K-Means remote sensing parallel MapReduce Hadoop 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gursoy, A.: Data Decomposition for Parallel K-means Clustering. Parallel Processing and Applied Mathematics 14, 241–248 (2004)CrossRefMATHGoogle Scholar
  2. 2.
    Li-shun, J., Ding-sheng, L.: Research on K-Means Clustering Parallel Algorithm of Remote Sensing Image. Remote Sensing Information 01, 27–30 (2008)Google Scholar
  3. 3.
    Matlab R2008a Product Help. Demos/Toolboxes/Image Processing/Image Segmentation/Color-Based Segmentation Using the L*a*b* Color SpaceGoogle Scholar
  4. 4.
    Kartikeyan, B., Sarkar, A., et al.: A segmentation approach to classification of remote sensing imagery. International Journal of Remote Sensing 19, 1695–1709 (1998)CrossRefGoogle Scholar
  5. 5.
    MATLAB Central - File detail - RGB2Lab, http://www.mathworks.com /matlabcentral/fileexchange/24009
  6. 6.
  7. 7.
    Zhaoqi, B., Xuegong, Z.: Pattern Recognition, 2nd edn., pp. 235–237. Tsinghua University Press, Beijing (2000)Google Scholar
  8. 8.
    Dean, J., Ghemawat, S.: Mapreduce: Simplified data processing on large clusters. Communications of the ACM 51, 107–113 (2008)CrossRefGoogle Scholar
  9. 9.
    Hadoop Website, http://hadoop.apache.org/
  10. 10.
    Yao, K.T., Lucas, R.F., et al.: Data Analysis for Massively Distributed Simulations. Interservice/Industry Training, Simulation, and Education Conference(I/ITSEC) (Got from Google Scholar) (2009)Google Scholar
  11. 11.
    Zhao, W., Ma, H., et al.: Parallel K-Means Clustering Based on MapReduce. In: CloudCom 2009. LNCS, vol. 5931, pp. 674–679 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Zhenhua Lv
    • 1
  • Yingjie Hu
    • 1
  • Haidong Zhong
    • 1
  • Jianping Wu
    • 1
  • Bo Li
    • 2
  • Hui Zhao
    • 2
  1. 1.Key Laboratory of Geographic Information Science, Ministry of Education;, Geography DepartmentEast China Normal UniversityShanghaiChina
  2. 2.Institute of Software EngineeringEast China Normal UniversityShanghaiChina

Personalised recommendations