Remote Sensing Image Classification Using Fuzzy-PSO Hybrid Approach

Remote Sensing Image Classification Using Fuzzy-PSO Hybrid Approach

Anasua Sarkar (Government College of Engineering and Leather Technology, India) and Rajib Das (Jadavpur University, India)
Copyright: © 2015 |Pages: 34
DOI: 10.4018/978-1-4666-8291-7.ch014
OnDemand PDF Download:
No Current Special Offers


Pixel classification among overlapping land cover regions in remote sensing imagery is a challenging task. Detection of uncertainty and vagueness are always key features for classifying mixed pixels. This chapter proposes an approach for pixel classification using hybrid approach of Fuzzy C-Means and Particle Swarm Optimization methods. This new unsupervised algorithm is able to identify clusters utilizing particle swarm optimization based on fuzzy membership values. This approach addresses overlapping regions in remote sensing images by uncertainties using fuzzy set membership values. PSO is a population-based stochastic optimization technique inspired from the social behavior of bird flocks. The authors demonstrate the algorithm for segmenting a LANDSAT image of Shanghai. The newly developed algorithm is compared with FCM and K-Means algorithms. The new algorithm-generated clustered regions are verified with the available ground truth knowledge. The validity and statistical analysis are performed to demonstrate the superior performance of the new algorithm with K-Means and FCM algorithms.
Chapter Preview


Remote sensing is defined as the art and science of obtaining information about an object without being in direct physical contact with the object by Cogalton and Green in 1999 (Cogalton, 1999). Several methods exist for classifying pixels into known classes (for example, an urban area or turbid water) in remote sensing images. Mathematically, a remote sensing image can be defined as a set,

(1) of 978-1-4666-8291-7.ch014.m02 information units for pixels, where 978-1-4666-8291-7.ch014.m03is the set of spectral band values for n bands associated with the pixel of coordinate (i,j). In order to find homogeneous regions in the image we model this image by fuzzy sets, that considers both the spatial image objects and the imprecision attached to them.

Let us denote the space on which the remote sensing image is defined by 978-1-4666-8291-7.ch014.m04 (usually 978-1-4666-8291-7.ch014.m05 or 978-1-4666-8291-7.ch014.m06). We denote the points of 978-1-4666-8291-7.ch014.m07 (pixels or voxels) as the spatial variables 978-1-4666-8291-7.ch014.m08. Let 978-1-4666-8291-7.ch014.m09 denotes the spatial distance between two pixels 978-1-4666-8291-7.ch014.m10. In several earlier works on remote sensing, 978-1-4666-8291-7.ch014.m11 is taken as the Euclidean distance on 978-1-4666-8291-7.ch014.m12(Maulik, 2012)(Bandyopadhyay, 2005).

A crisp object 978-1-4666-8291-7.ch014.m13in the remote sensing image is a subset of 978-1-4666-8291-7.ch014.m14. Henceforth, a fuzzy object is defined as a fuzzy subset 978-1-4666-8291-7.ch014.m15 of 978-1-4666-8291-7.ch014.m16. This fuzzy object 978-1-4666-8291-7.ch014.m17 is defined bi-univoquely by its membership function, 978-1-4666-8291-7.ch014.m18. 978-1-4666-8291-7.ch014.m19 is known as the membership function, which represents the membership degree of the point 978-1-4666-8291-7.ch014.m20 to the fuzzy set978-1-4666-8291-7.ch014.m21. When the value of 978-1-4666-8291-7.ch014.m22 is closer to 1, the degree of membership of x in 978-1-4666-8291-7.ch014.m23 will be higher. Such a representation allows for a direct mapping of mixed pixels in overlapping land cover regions in remote sensing images. Let 978-1-4666-8291-7.ch014.m24denotes the set of all fuzzy sets defined on 978-1-4666-8291-7.ch014.m25. For any two pixels978-1-4666-8291-7.ch014.m26, we denote by 978-1-4666-8291-7.ch014.m27 as their distance in fuzzy perspective. The definition of a new method utilizing the particle swarm movements over fuzzy membership matrix is the scope of this chapter.

Key Terms in this Chapter

Pixel Classification: Pixel Classification method classifies all pixels in a remote sensing image into classes.

PSO Algorithm: Particle Swam Optimization is a population-based algorithm that uses a population of individuals to probe the best position in the search space.

K-Means Algorithm: Clustering algorithm to classify n elements in k clusters, which iteratively computes the cluster centroids as the means of all elements in one cluster.

Clustering: Assigning similar elements to one group, which increases intra-cluster similarity and decreases inter-cluster similarity.

Validity Index: Index to estimate compactness of the clusters, leading to properly identified distinguishable clusters.

Remote Sensing: Remote Sensing is a method to interpret geospatial data exploring features, objects, and classes on Earth's land surface.

Fuzzy Set: Set of elements with membership values between 0 and 1 for each of the clusters to which it belongs according to fuzzy set theory by Zadeh.

Complete Chapter List

Search this Book: