Novel fuzzy uncertainty modeling for land cover classification based on clustering analysis
- 18 Downloads
It is well known that there is a degree of fuzzy uncertainty in land cover classification using remote sensing (RS) images. In this article, we propose a novel fuzzy uncertainty modeling algorithm for representing the features of land cover patterns, and present an adaptive interval type-2 fuzzy clustering method. The proposed fuzzy uncertainty modeling method is performed in two main phases. First, the segmentation units of the input multi-spectral RS image data are subjected to object-based interval-valued symbolic modeling. As a result, features for each land cover type are represented in the form of an interval-valued symbolic vector, which describes the intra-class uncertainty better than the source data and improves the separability between different classes. Second, interval type-2 fuzzy sets are generated for each cluster based on the distance metric of the interval-valued vectors. This step characterizes the inter-class high-order fuzzy uncertainty and improves the classification accuracy. To demonstrate the advantages and effectiveness of the proposed approach, extensive experiments are conducted on two multispectral RS image datasets from regions with complex land cover characteristics, and the results are compared with those given by well-known fuzzy and conventional clustering algorithms.
KeywordsInterval-valued data Type-2 fuzzy sets Type reduction Type-2 fuzzy clustering Land cover classification
Unable to display preview. Download preview PDF.
The authors would like to thank the Institute of RS and Geographic Information Systems in Guangdong Province, China, for providing the experimental data for this article, YING Shuowen & CHEN Juping from the Surveying & Mapping Institute in Zhuhai City, China, and WANG Lin & LI Fei from the Department of Communications in Qinghai, China, for the reference data support. This work was supported by the National Natural Science Foundation of China (Grant No. 41672323), the Major Scientific Research Project for Universities of Guangdong Province (Grant Nos. 2016KTSCX167, 201612008QX & 2017KTSCX207), the Natural Science Foundation of Guangdong Province, China (Grant Nos. 2016A030313384 & 2016A030313385), and the Hainan Provincial Natural Science Foundation of China (Grant Nos. 20156227 & 618MS058).
- Cheng J C, Guo H D, Shi W Z. 2004. The Uncertainty of Remote Sensing Data. Beijing: Science PressGoogle Scholar
- He H, Yu X C, Hu D. 2016b. Land cover classification based on adaptive interval-valued type-2 fuzzy clustering analysis. Chin J Geol, 712–720Google Scholar
- Li B, Zhao H, Lv Z H. 2010. Parallel ISODATA clustering of remote sensing images based on MapReduce. In: International Conference on Web Information Systems and Mining. Huangshan. 162–170Google Scholar
- Long T N, Nguyen D D. 2012. Land cover classification using interval type-2 fuzzy clustering for multi-spectral satellite imagery. In: IEEE International Conference on Systems, Man, and Cybernetics (SMC). Seoul 2371–2376Google Scholar
- Long T N, Mai D S, Pedrycz W. 2015. Semi-supervising interval type-2 fuzzy C-means clustering with spatial information for multi-spectral satellite image classification and change detection. Comput Geosci, 2015, 83: 1–16Google Scholar
- Lucas L A, Centeno T M, Delgado M R. 2008. Land cover classification based on general type-2 fuzzy classifiers. Int J Fuzz Syst, 10: 207–216Google Scholar
- Mai S D, Long T N. 2015. Interval type-2 fuzzy C-means clustering with spatial information for land-cover classification. In: Asian Conference on Intelligent Information and Database Systems. Springer Int Publishing. 387–397Google Scholar
- Nie M, Tan W W. 2008. Towards an efficient type reduction method for interval type-2 fuzzy logic system. In: IEEE World Congress on Computational Intelligence, Hong Kong. 1425–1432Google Scholar
- Moore R E. 1966. Interval Analysis. Englewood Cliffs: Prentice-HallGoogle Scholar
- Wu D, Tan W W. 2005. Computationally efficient type-reduction strategies for a type-2 fuzzy logic controller. In: The 14th IEEE International Conference on Fuzzy Systems, 2005. FUZZ '05. Reno. 353–358Google Scholar
- Xie J, Zhang X. 2012. Clustering of hyper spectral image based on improved fuzzy C means algorithm. J Converg Inf Tech, 7: 320–327Google Scholar
- Yu X C, An W J, He H. 2012. A method of auto classification based on object oriented unsupervised classification. Progress Geophys, 27: 744–749Google Scholar
- Zeng J, Liu Z Q. 2007. Type-2 Fuzzy Sets for Pattern Classification: A Review. In: IEEE Symposium on Foundations of Computational Intelligence, 2007. FOCI 2007. Honolulu. 193–200Google Scholar
- Zhou D, Li J, Zha H. 2005. A new Mallows distance based metric for comparing clusterings. In: Proceedings of the Twenty-Second International Conference (ICML 2005). Bonn. 1028–1035Google Scholar