Abstract
Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA) is commonly used for unsupervised image classification in remote sensing applications. Although parallelized approaches were explored, previous works mostly utilized the power of CPU clusters. We deploy the many-cores in the Graphics Processing Unit (GPU) to accelerate the unsupervised image classification over GPU. The proposed solution is scalable and satisfactory to speed up the computational time, while the quality of classification is almost the same as that from ERDAS, a well known remote sensing software.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bo Li; Hui Zhao; ZhenHua Lv. 2010. Parallel ISODATA Clustering of Remote Sensing Images Based on MapReduce. In Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2010 International Conference on, pp. 380-383, 10–12 Oct. 2010. doi: 10.1109/CyberC.2010.75.
Dean, Jeffrey and Ghemawat, Sanjay. 2004. MapReduce: Simplified Data Processing on Large Clusters. OSDI’04: Sixth Symposium on Operating System Design and Implementation, 2004. http://labs.google.com/papers/mapreduce-osdi04.pdf
Dhodhi M.K., Saghri J.A., Ahmad I., Ul-Mustafa R. 1999. D-ISODATA: A Distributed Algorithm for Unsupervised Classification of Remotely Sensed Data on Network of Workstations. Journal of Parallel and Distributed Computing, 59 (2), pp. 280–301.
Riccardi, Schow. 1988. Adaptation of the ISODATA clustering algorithm for vector supercomputer execution. Proceedings of the 1988 ACM/IEEE conference on Supercomputing vol. 2, 1988 pp.141–150
Snir, Marc; Otto, Steve; Huss-Lederman, Steven; Walker, David; Dongarra, Jack. 1995. MPI: The Complete Reference. MIT Press Cambridge.
Victor Pankratius, Wolfram Schulte, and Kurt Keutzer. 2011. Guest Editors’ Introduction: Parallelism on the Desktop. IEEE Software, vol. 28, no. 1, pp. 14–16, Jan./Feb. 2011.
Weizhong Zhao, Huifang Ma, Qing He. 2009. Parallel K-Means Clustering Based on MapReduce. CloudCom ’09 Proceedings of the 1st International Conference on Cloud Computing.
Zhenhua Lv, Yingjie Hu, Haidong Zhong, Jianping Wu, Bo Li, Hui Zhao. 2010. Parallel K-means clustering of remote sensing images based on mapreduce. Proceedings of the 2010 international conference on Web information systems and mining, October 23–24, 2010, Sanya, China
Acknowledgements
This research was supported partially by the National Science Foundation through the award OCI-1047916.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this chapter
Cite this chapter
Ye, F., Shi, X. (2013). Parallelizing ISODATA Algorithm for Unsupervised Image Classification on GPU. In: Shi, X., Kindratenko, V., Yang, C. (eds) Modern Accelerator Technologies for Geographic Information Science. Springer, Boston, MA. https://doi.org/10.1007/978-1-4614-8745-6_11
Download citation
DOI: https://doi.org/10.1007/978-1-4614-8745-6_11
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4614-8744-9
Online ISBN: 978-1-4614-8745-6
eBook Packages: Computer ScienceComputer Science (R0)