Automatic Feature Selection for Operational Scenarios of Satellite Image Understanding using Measures of Mutual Information

Dragos Bratasanu, Ion Nedelcu, Mihai Datcu

Abstract

The Earth Observation processing tools operating in the recent scenario need to be tailored to the new products offered by the sub-meter spatial resolution imaging sensors. The new methods should provide the image analysts the essential automatic support to discover relevant information and identify significant elements in the image. We advocate an automatic technique to select the optimum number features used in classification, object detection and analysis of optical satellite images. Using measures of mutual information between the target classes and the available features, we investigate the criterions of maximum-relevance and maximum-relevance-minimumredundancy for automatic feature selection at very-low cost. Following a comprehensive set of experiments on multiple sensors, applications and classifiers, the results demonstrate the possible operational use of the method in future scenarios of human-machine interactions in support of Earth Observation technologies.

References

  1. Peng, H., Long, F., Ding, C.: Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance and Min-Redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 27. No.8. 2005. Pp 1226-1238
  2. Bratasanu, D., Nedelcu, I., Datcu, M.: Bridging the gap for satellite image annotation and automatic mapping applications. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, accepted paper 2010
  3. Ding, C., Peng, H.: Minimum Redundancy Feature Selection from Microarray Gene Expression Data. Proc. Second IEEE Computational Systems Bioinformatics Conference. 2003. Pp 523-528
  4. Richards, J., Jia, X.: Remote Sensing Digital Image Analysis. 4th Edition. Springer, 2006.
Download


Paper Citation


in Harvard Style

Bratasanu D., Nedelcu I. and Datcu M. (2010). Automatic Feature Selection for Operational Scenarios of Satellite Image Understanding using Measures of Mutual Information . In Proceedings of the International Workshop on Semantic Sensor Web - Volume 1: SSW, (IC3K 2010) ISBN 978-989-8425-33-1, pages 109-117. DOI: 10.5220/0003143101090117


in Bibtex Style

@conference{ssw10,
author={Dragos Bratasanu and Ion Nedelcu and Mihai Datcu},
title={Automatic Feature Selection for Operational Scenarios of Satellite Image Understanding using Measures of Mutual Information},
booktitle={Proceedings of the International Workshop on Semantic Sensor Web - Volume 1: SSW, (IC3K 2010)},
year={2010},
pages={109-117},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003143101090117},
isbn={978-989-8425-33-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Workshop on Semantic Sensor Web - Volume 1: SSW, (IC3K 2010)
TI - Automatic Feature Selection for Operational Scenarios of Satellite Image Understanding using Measures of Mutual Information
SN - 978-989-8425-33-1
AU - Bratasanu D.
AU - Nedelcu I.
AU - Datcu M.
PY - 2010
SP - 109
EP - 117
DO - 10.5220/0003143101090117