Abstract
Based on margin sampling (MS) strategy, an active learning approach was introduced for proposed sample selection from large quantities of labeled samples using a Landsat-7 ETM+ image to solve remote sensing image classification problems for large number of training samples. As a breakthrough from conventional random sampling and stratified systematic sampling methods, this approach ensures classification of only using a few hundred training samples to be as effective as that of using several thousand and even tens of thousands of samples by conventional methods, thereby avoiding enormous calculations, substantially reducing operating time and improving training efficiency. The test results of the proposed approach was compared with those of random sampling and stratified systematic sampling, and the effects of training samples on classification under optimized and non-optimized selection conditions was analyzed.
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
Huang, C., Kim, S., Altstatt, A., et al.: Rapid loss of paraguay’s atlantic forest and the status of protected areas — a landsat assessment. J. Remote Sens. Environ. 106(4), 460–466 (2007)
Huang, C., Song, K., Kim, S., et al.: Use of a dark object concept and support vector machines to automate forest cover change analysis. J. Remote Sens. Environ. 112(3), 970–985 (2008)
Huang, C., Kim, S., Song, K., et al.: Assessment of paraguay’s forest cover change using landsat observations. J. Global Planet. Change 67(1), 1–12 (2009)
Huang, C., Thomas, N., Goward, S.N., et al.: Automated masking of cloud and cloud shadow for forest change analysis using landsat images. J. Int. J. Remote Sens. 31(20), 5449–5464 (2010)
Sexton, J.O., Song, X., Feng, M., et al.: Global, 30-m resolution continuous fields of tree cover: landsat-based rescaling of MODIS vegetation continuous fields with lidar-based estimates of error. J. Int. J. Digit. Earth 6(5), 427–448 (2013)
Townshend, J.R., Masek, J.G., Huang, C., et al.: Global characterization and monitoring of forest cover using landsat data: opportunities and challenges. J. Int. J. Digit. Earth 5(5), 373–397 (2012)
Li, H., Wang, C., Yuan, B., et al.: A learning strategy for SVM-based large-scale training sets. J. Chin. J. Comput. 27(5), 715–719 (2004)
Zhai, J., Li, S., Wang, X.: Comparative research of condense nearest rules based on fuzzy rough sets. J. Comput. Sci. 39(2), 236–239 (2012)
Vapnik, V.N.: Statistical Learning Theory, pp. 231–244. Wiley, New York (1998)
Schohn, G., Cohn, D.: Less is more: active learning with support vector machines. In: International Conference on Machine Learning, pp. 839–846. Morgan Kaufmann Publishers Inc. (2000)
Jiang, W.: Research on the selection of samples for pattern recognition and its application. D. Nanjing University of Science and Technology (2008)
Tuia, D., Ratle, F., Pacifici, F., et al.: Active learning methods for remote sensing image classification. J. IEEE Trans. Geosci. Remote Sens. 47(7), 2218–2232 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this paper
Cite this paper
Guo, Y., Ma, L., Zhu, F., Liu, F. (2016). Selecting Training Samples from Large-Scale Remote-Sensing Samples Using an Active Learning Algorithm. In: Li, K., Li, J., Liu, Y., Castiglione, A. (eds) Computational Intelligence and Intelligent Systems. ISICA 2015. Communications in Computer and Information Science, vol 575. Springer, Singapore. https://doi.org/10.1007/978-981-10-0356-1_5
Download citation
DOI: https://doi.org/10.1007/978-981-10-0356-1_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-0355-4
Online ISBN: 978-981-10-0356-1
eBook Packages: Computer ScienceComputer Science (R0)