Collective Network of Binary Classifier Framework for Polarimetric SAR Image Classification: An Evolutionary Approach

Abstract

Abstract-Terrain classification over polarimetric synthetic aperture radar (SAR) images has been an active research field where several features and classifiers have been proposed up to date. However, some key questions, e.g., 1) how to select certain features so as to achieve highest discrimination over certain classes?, 2) how to combine them in the most effective way?, 3) which distance metric to apply?, 4) how to find the optimal classifier configuration for the classification problem in hand?, 5) how to scale/adapt the classifier if large number of classes/features are present?, and finally, 6) how to train the classifier efficiently to maximize the classification accuracy?, still remain unanswered. In this paper, we propose a collective network of (evolutionary) binary classifier (CNBC) framework to address all these problems and to achieve high classification performance. The CNBC framework adapts a "Divide and Conquer" type approach by allocating several NBCs to discriminate each class and performs evolutionary search to find the optimal BC in each NBC. In such an (incremental) evolution session, the CNBC body can further dynamically adapt itself with each new incoming class/feature set without a full-scale retraining or reconfiguration. Both visual and numerical performance evaluations of the proposed framework over two benchmark SAR images demonstrate its superiority and a significant performance gap against several major classifiers in this field.Index Terms-Evolutionary classifiers, multidimensional particle swarm optimization (MD-PSO), polarimetric synthetic aperture radar (SAR).

Unsupervised Classification of Fully Polarimetric SAR Image Based on Polarimetric Features and Spatial Features

“…Haralick proposed fourteen statistics calculated with the gray level co-occurrence matrix. With many experiments [12], Baraldi thought that the following statistics are the best for SAR image Where, P (i, j) is the value of the element in the place (i, j) of the gray level cooccurrence matrix. To every element of an image, the gray level co-occurrence matrix of some kind of neighborhood is calculated, then some statistics are calculated, and texture image can be gotten, several statistics can form feature vector [14].…”

A two-pass unsupervised clustering algorithm for polarimetric SAR image segmentation

“…The original four-look fully PolSAR data of the San Francisco Bay, having a dimension of 900 × 1024 pixels, provides good coverage of both natural. This image is the NASA/Jet Propulsion Laboratory AIRSAR L-band image [1]. Five distinct classes are defined as water, mountain, forest, flat zones and urban area.…”

“…Polarimetric synthetic aperture radar (PolSAR) imagery provides useful information in a diverse number of applications from sea ice monitoring to oil spill monitoring [1]. Therer is now an increasing volume of fully polarimetric data due to the launch of sensors capable of fully polarimetric imaging such as Radarsat-2 and TerraSAR-X [2].…”

Polarimetric synthetic aperture radar image unsupervised classification method based on artificial immune system

“…9 It is designed to solve complex problems by exploring the biological immune system, obtaining its processing mechanisms, and developing appropriate engineering models. 10 Unlike other evolutionary computation algorithms, the characteristics of the AIS, such as biological diversity, memory, tolerance, distributed parallel processing, and robustness, ensure a balance between exploration and exploitation. 11 In recent studies, AISs have been applied to computer security, pattern recognition, machine learning, data mining, and function optimization.…”