Advances In Satellite Image Processing: Enhancement, Segmentation, Classification, And Change Detection
DOI:
https://doi.org/10.29284/epanh336Keywords:
remote sensing; change detection; fusion; feature extraction; segmentation; classification.Abstract
The accurate classification of the field and territorial boundaries is becoming increasingly important in the face of the dynamic nature of the modern land and water fronts. Historical maps often contain changes in administrative boundaries, vegetation patterns and water bodies, thus reliable tools to detect these changes are important. Satellite imagery has become the main means of observing such changes and therefore a thorough understanding of satellite image processing techniques is needed when dealing with historical cartographic data. The present study gives a thorough assessment of the pros and cons of a wide variety of image processing techniques in this field. There are a number of computational approaches, but their relative effectiveness can vary greatly depending on the nature of the imagery and the needs of the specific application. The application of incorrect technique may produce suboptimal results. This highlights the importance of matching the method to the objectives of the analysis. This work therefore describes the relevant processing techniques and satellite imaging methods suitable for different use cases. Moreover, some comparative evaluations are performed to demonstrate the performances of different approaches under different conditions. The aim of this synthesis is to facilitate the development of informed and innovative solutions to common problems encountered in satellite based image processing applications.
References
[1] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd ed. Pearson, 2008.
[2] N. Sengee and H. Choi, “Brightness preserving histogram equalization,” IEEE Transactions on Consumer Electronics, vol. 54, no. 4, pp. 1803–1810, 2008.
[3] X. Li and Y. Wang, “Image enhancement using modified differential evolution algorithm,” Expert Systems with Applications, vol. 37, no. 7, pp. 6025–6032, 2010.
[4] C. Fu, Y. Zhao, and M. Zhou, “Fractional differential and its application in image enhancement,” Signal Processing, vol. 92, no. 9, pp. 2143–2151, 2012.
[5] P. Lewis et al., “Image fusion using rational polynomial coefficients,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 78, pp. 109–118, 2013.
[6] D. Lowe, “Distinctive image features from scale-invariant keypoints,” IJCV, vol. 60, no. 2, pp. 91–110, 2004.
[7] F. Maes et al., “Multimodality image registration by maximization of mutual information,” IEEE Trans. Medical Imaging, vol. 16, no. 2, pp. 187–198, 1997.
[8] D. G. Lowe, “Object recognition using scale invariant features,” Proc. ICCV, 1999.
[9] J. Quinlan, “C4.5 decision trees and improvements,” Machine Learning, Springer, 1993.
[10] X. Hou and L. Zhang, “Saliency detection using spectral residual,” CVPR, 2007.
[11] J. A. Richards, “Angular feature–based classification of urban structures,” IEEE Trans. Geoscience and Remote Sensing, vol. 38, no. 6, pp. 2643–2654, 2000.
[12] J. Green and P. Revesz, “Reversible jump Markov chain Monte Carlo for image feature extraction,” Pattern Recognition, vol. 35, pp. 999–1012, 2002.
[13] R. Adams and L. Bischof, “Seeded region growing,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 6, pp. 641–647, 1994.
[14] X.-S. Yang and S. Deb, “Cuckoo search: A metaheuristic optimization algorithm,” Nature Inspired Cooperative Strategies, 2009.
[15] J. Sethian, “Markov random fields for image segmentation,” SIAM Review, vol. 39, no. 1, pp. 1–17, 1997.
[16] V. Badrinarayanan, A. Kendall, and R. Cipolla, “SegNet: A deep convolutional encoder-decoder architecture for image segmentation,” IEEE Trans. PAMI, 2017.
[17] X. Yang, “Firefly algorithm for multi-thresholding,” Applied Soft Computing, vol. 12, no. 11, pp. 3632–3643, 2012.
[18] Z. Wang and B. Zheng, “Graph-based segmentation using Gabor filters,” Pattern Recognition Letters, vol. 32, no. 15, pp. 2010–2023, 2011.
[19] Otsu N., “A threshold selection method from gray-level histograms,” IEEE Trans. SMC, 1979.
[20] J. Kittler and J. Illingworth, “Minimum error thresholding,” Pattern Recognition, 1986.
[21] J. Long et al., “Fully convolutional networks for semantic segmentation,” CVPR, 2015.
[22] S. Sahoo et al., “A survey on multilevel thresholding,” Computer Vision and Image Understanding, 2015.
[46] A. Singh, “Digital change detection techniques using remotely-sensed data,” International Journal of Remote Sensing, 1989.
[47] P. Coppin and M. Bauer, “Digital change detection in forest ecosystems,” Remote Sensing Reviews, 1996.
[48] J. Franklin, “Mapping vegetation using GIS and remote sensing,” Wiley, 2001.
[49] Y. Chen et al., “Land cover change detection using GIS and remote sensing,” Remote Sensing of Environment, 2003.
[50] Roberts et al., “Temporal unmixing for vegetation analysis using spectral mixture models,” Remote Sensing of Environment, 1998.
[51] P. Gamba et al., “Urban DSM for change detection,” IEEE Trans. Geoscience and Remote Sensing, 2000.
[52] J. Richards, “Maximum likelihood classification,” Remote Sensing Digital Image Analysis, Springer, 2013.
[53] J. Verbesselt et al., “Forest change detection using time-series,” Remote Sensing of Environment, 2010.
[54] J. Verbesselt et al., “BFAST: Monitoring change in time-series of satellite imagery,” Remote Sensing of Environment, 2012.
[55] Y. Zhang, “Multi-step image matching for change detection,” Photogrammetric Engineering, 2001.
[56] X. Huang, “Object-based temporal analysis for change detection,” IEEE GRSL, 2011.
[66] T. M. Lillesand, R. W. Kiefer, and J. Chipman, Remote Sensing and Image Interpretation, Wiley, 2008.
[67] Gislason et al., “Random forests for land cover classification,” Remote Sensing of Environment, 2006.
[68] T. Cover and P. Hart, “Nearest neighbor classification,” IEEE Trans. Information Theory, 1967.
[69] J. Corcoran et al., “Wetland classification using random forests,” Remote Sensing, 2013.
[70] N. Keshava, “Spectral unmixing of multispectral images,” IEEE Signal Processing Magazine, 2003.
[71] Plaza et al., “Hybrid spectral unmixing for land cover classification,” IEEE Trans. Geoscience and Remote Sensing, 2009.
[72] Roberts et al., “MESMA for urban land cover,” Remote Sensing of Environment, 1998.
[73] Moody and Darken, “Radial basis function networks,” Neural Computing Surveys, 1989.
[74] F. Melgani, “Classification error correction using wavelets,” IEEE GRSL, 2004.
[75] He et al., “Deep feature learning for satellite image classification,” CVPR, 2014.
[76] S. Kokhanovsky, “Cloud classification using Bayesian networks,” Atmospheric Research, 2004.
[77] Shafer and Dempster, “A mathematical theory of evidence,” Princeton Univ. Press, 1976.
[78] D. Dubois and H. Prade, “Fuzzy logic approaches in image edge detection,” IEEE Trans. SMC, 1992.
[79] J. Long et al., “Fully Convolutional Networks for dense prediction,” CVPR, 2015.
[82] M. Hollaus et al., “DSM generation from image matching,” ISPRS Journal of Photogrammetry, 2010.
[83] J. Shi et al., “Jitter detection in satellite imagery using Kalman filters,” IEEE Trans. Aerospace and Electronic Systems, 2012.
[84] Solberg et al., “Machine-learning-based oil spill detection,” IEEE Trans. Geoscience and Remote Sensing, 2006.
[85] Zou et al., “Vehicle detection in aerial images using transfer learning,” IEEE Trans. Image Processing, 2015.
[86] J. Stehman, “Confusion matrices in classification accuracy,” Remote Sensing of Environment, 1997.
[87] Congalton, “Accuracy assessment of remote sensing-derived classifications,” Photogrammetric Engineering, 1991.
[88] Powers, “Evaluation: Precision, recall, F-measure,” Journal of Machine Learning Technologies, 2011.
[89] J. Lu et al., “Land cover change mapping using Landsat ETM+,” Remote Sensing, 2016.
[90] Agresti and Coull, “Statistics for multinomial distributions,” The American Statistician, 1998.
[91] Pontius and Millones, “Quality-Control Column Sets (QCCS),” Landscape Ecology, 2011.
[92] van Rijsbergen, Information Retrieval, 2nd ed., Butterworths, 1979.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
