CFP last date
21 October 2024
Reseach Article

Evaluating Temporal Uncertainty of Multi-temporal Images for Geographical Deviance

by Md. Al Mamun, Md. Nazrul Islam Mondal, Boshir Ahmed
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 103 - Number 14
Year of Publication: 2014
Authors: Md. Al Mamun, Md. Nazrul Islam Mondal, Boshir Ahmed
10.5120/18141-9339

Md. Al Mamun, Md. Nazrul Islam Mondal, Boshir Ahmed . Evaluating Temporal Uncertainty of Multi-temporal Images for Geographical Deviance. International Journal of Computer Applications. 103, 14 ( October 2014), 14-18. DOI=10.5120/18141-9339

@article{ 10.5120/18141-9339,
author = { Md. Al Mamun, Md. Nazrul Islam Mondal, Boshir Ahmed },
title = { Evaluating Temporal Uncertainty of Multi-temporal Images for Geographical Deviance },
journal = { International Journal of Computer Applications },
issue_date = { October 2014 },
volume = { 103 },
number = { 14 },
month = { October },
year = { 2014 },
issn = { 0975-8887 },
pages = { 14-18 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume103/number14/18141-9339/ },
doi = { 10.5120/18141-9339 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T22:34:32.375869+05:30
%A Md. Al Mamun
%A Md. Nazrul Islam Mondal
%A Boshir Ahmed
%T Evaluating Temporal Uncertainty of Multi-temporal Images for Geographical Deviance
%J International Journal of Computer Applications
%@ 0975-8887
%V 103
%N 14
%P 14-18
%D 2014
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Multi-temporal satellite images exhibit high amount of correlation in spatial, spectral and temporal domain. This high redundancies provide a high potential and a good opportunity to explore the entropy as a funtion of natural diversity. From the information-theory point of view, the potential gain from exploiting the temporal domain correlation can be estimated by quantifying the entropy relationship between two temporally dependent images. As conditioning reduces uncertainty, knowing one of the variables reduces the average uncertainty about the others in two dependent events. So the multi-temporal images is best distributed sequentially where current images can be forecasted from previous reference image. Thus, multiple dates' remote sensed images treated as a sequential data set varies in relative distributions of the brightness values depending on the reflectivity of various features. This paper mainly reflects the fact of how various geographical features influence the temporal dependency. The initial issue treated by multi-temporal image transmission lay in the areas of data reduction that in turn depend on the quantities such as entropy and mutual information, which are functions of the probability distributions that underlie the process of communication. This paper mainly exploits the energy deviation in temporal characteristics for diverse geographical features. Mainly features for urban, forestry, desert and coastal areas have been investigated. The key measure of data compaction entropy will be exploited in this case to better understand the features dependency.

References
  1. M. A. Mamun, X. Jia and M. Ryan, "Adaptive Data Compression for Efficient Sequential Transmission and Change Updating of Remote Sensing Images", IEEE Geoscience and Remote Sensing Symposium (IGARSS '09), Cape Town, South Africa, pp. 498-501 (IV), July 2009.
  2. Richards, J. A. and Jia, X. 2006. Remote Sensing and Digital Analysis, Springer Verlag.
  3. W. Zhu, X. Tian, F. Zhou and Y. Chen, "Fast disparity estimation using spatio-temporal correlation of disparity field for multiview video coding. " IEEE Transactions on Consumer Electronics, vol. 56(2), pp. 957-964, 2010.
  4. K. Peleg and G. L. Anderson, "FFT regression and cross-noise reduction for comparing images in remote sensing. " International Journal of Remote Sensing, vol. 23(10), pp. 2097-2124, 2002.
  5. G. B. Cai, C. O. Davis and A. F. H. Goetz, "A Review of Atmospheric Correction Techniques for Hyperspectral Remote Sensing of Land Surfaces and Ocean Color. " IEEE International Conference on Geoscience and Remote Sensing Symposium (IGARSS '06), pp. 1979-1981, 2006.
  6. G. Bo-Cai, M. J. Montes, L. Rong-Rong, H. M. Dierssen and C. O. Davis, "An Atmospheric Correction Algorithm for Remote Sensing of Bright Coastal Waters Using MODIS Land and Ocean Channels in the Solar Spectral Region. " IEEE Transactions on Geoscience and Remote Sensing, vol. 45(6), pp. 1835-1843, 2007.
  7. M. Tunay and A. Atesoglu, "Effect of atmospheric correction for different land use on Landsat 7 ETM+ satellite imagery. " Presented at 4th International Conference on Recent Advances in Space Technologies (RAST '09), 2009.
  8. P. Tyagi and U. Bhosle, "Image based atmospheric correction of remotely sensed images. " International Conference on Computer Applications and Industrial Electronics (ICCAIE), pp. 63-68, 2010.
  9. Z. Wei, D. Qian and J. E. Fowler, "Multitemporal hyperspectral image compression. " IEEE Geoscience and Remote Sensing Letters, vol. 8(3), pp. 416-420, 2011.
  10. M. Mamun, X. Jia and M. J. Ryan, "Nonlinear Elastic Model for Flexible Prediction of Remotely Sensed Multitemporal Images", IEEE Geoscience and Remote Sensing Letters, vol. 11, no. 5, pp. 1005 – 1009, 2013.
  11. Fowler, J. E. , and Rucker, J. T. 2007 3-D wavelet-based compression of hyperspectral imagery in C. -I. Chang and E. Hoboken, (eds. ), Hyperspectral Data Exploitation: Theory and Applications. NJ: Wiley, pp. 379–407
  12. Cover, T. M. and Thomas, J. A. 2006 Elements of Information Theory, 2nd Ed. , John Wiley & Sons, Hoboken New Jersey.
  13. M. A. Mamun, X. Jia and M. Ryan, "Combined Time Domain and Spectral Domain Data Compression for Fast Multispectral Imagery Updating", Digital Image Computing: Techniques and Applications (DICTA), Melbourne, Australia, 2009.
Index Terms

Computer Science
Information Sciences

Keywords

Multi-temporal Image Entropy Correlation.