Post Classification Using Cellular Automata for Landsat Images

Abstract:

The research presented in this paper aims at improving the accuracy of land-use maps produced from classification of Landsat images of mega cities in developing countries. In other words, the main objective of this paper is to find a suitable post classification technique that gives optimum results for Landsat images of mega cities in developing countries. To reach our goal, the paper presents a classification of two TM-Landsat sub scenes using a traditional statistical classifier (Maximum Likelihood) into four land cover classes (vegetation-water-Desert-Urban); then the accuracy assessment for the produced land-cover map will be calculated. Following to this step, three post processing techniques- Majority Filter, Probability label Relaxation (PLR), and Cellular Automata (CA) - will be applied in order to improve the accuracy of the previously produced land cover map. Finally, the same accuracy assessment measurements will be calculated for the two land-cover maps produced by each of the above post classification techniques. Initial results will show that CA outperformed the other techniques. In this paper we propose a methodology to implement a satellite image post classification Algorithm with cellular Automata.

• Periodical: Advanced Materials Research (Volumes 433-440)
• Pages: 5431-5435
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.433-440.5431
• Online since: January 2012
• Authors: Ebada Sarhan, Eraky Khalifa, Ayman M. Nabil
• Keywords: Cellular Automata (CA), Landsat Images, Majority Filter, Probability Labeling Relaxation

References

[1] Franciscus, Johannes Maria van der we., Assessment and visualisation of uncertainty in remote sensing land cover classifications, Faculteit Ruimtelijke Wetenschappen Universiteit Utrecht Netherlands (2000).

[2] B. Mojaradi , C. Lucas , M. Varshosaz., using learning cellular automata for post classification satellite imagery, ISPRS, pp.991-995, (2004).

[3] Mather, P , Computer Processing of Remotely Sensed Images, Wiley, New York , USA, (2004).

[4] Grades, zur Erlangung des., A New Information Fusion Method for Land-Use Classification Using High Resolution Satellite Imagery, Phd. Disseration, pp.97-105, (1999).

[5] Richards, A. John, Remote sensing digital image analysis., Springer, Germany, (1993).

[6] DiZenzo, et al., Gaussian Maximum Likelihood and Contextual Classification Algorithms for Multi Crop Classification, IEEE Transactions on Geoscience and Remote Sensing, p.25: 805-814, ( 1987).

DOI: 10.1109/tgrs.1987.289752

[7] Rosin, Paul L., Training Cellular Automata for Image Processing, IEEE transactions on image processing, vol. 15, no. 7. pp.2076-2087, ( 2006).

DOI: 10.1109/tip.2006.877040

[8] Moises Espinola, et al, cellular automata applied in remote sensing to implement contextual pesudo-fuzzy classification, Lecture notes in computer science., pp.312-321, springer, Germany, (2010).

DOI: 10.1007/978-3-642-15979-4_33

[9] Neumann, J. V, , The Theory of Self-Reproducing Automata., Urbana and London : University of Illinois Press, (1966).

[10] T. Van de Voorde, et al, , a land-cover post-classification filter based on neural network end-node activations, regensburg , Germeny, ( 2003).

[11] P. Maji, C. Shaw, and N. Ganguly., Theory and Application of Cellular Automata For Pattern Classification, Fundamental Informatica, vol. 58, pp. p.321–354, ( 2003).

[12] P.L. Rosin , Image Processing using 3-State Cellular Automata, Computer Vision and Image Understanding, vol. 114, no. 7, pp.790-802, ( 2010).

DOI: 10.1016/j.cviu.2010.02.005