ABSTRACT

The main problem posed by Polarimetric Synthetic Aperture Radar (PolSAR) image classification in remote sensing is the ability to develop classifiers that can substantially discern the different classes inherent in natural and man-made targets. Emphasis has shifted from the use of conventional classifiers to modern non-parametric classifiers such as the Artificial Neural Network (ANN) and Support Vector Machine (SVM), and most recently the hybrid Deep Neural Network (DNN) which is a fusion of Deep Learning (DL) and ANN. This research therefore presents the novel application of Deep Support Vector Machine (DSVM), which is a fusion of DL and SVM to PolSAR image classification. Two PolSAR images of Flevoland region in the Netherlands and Winnipeg in Canada are used as test beds for the experiment. The Lee filter is used to filter the images to suppress the speckle noise in the images. The Pauli decomposition is applied to decompose the images into $\left|S_{HH}+S_{VV}\right|$, $\left|S_{HH}-S_{VV}\right|$, $\left|S_{HV}\right|$ polarimetric channels. Then, the Gray Level Co-occurrence Matrix (GLCM) texture feature for $\left|S_{HH}+S_{VV}\right|$, $\left|S_{HH}-S_{VV}\right|$, $\left|S_{HV}\right|$ are extracted based on correlation, contrast, energy, and homogeneity statistics, using GLCM directions 0°, 45°, 90°, and 135° with an offset distance of 60. To enhance the efficiency of the model 8, 16, 32, 64, 128, and 256 quantization levels are explored. The DSVM classifier is implemented with four kernel functions: Exponential Radial Basis Function (ERBF), Gaussian Radial Basis Function (GRBF), neural, and polynomial. The first set of results is a comparison of the DSVM and SVM. The result of Flevoland image for ERBF, GRBF, neural, and polynomial kernels are 99.17 (73.39), 99.32 (74.62), 98.64 (71.28), and 99.34 (77.21), respectively; for the Winnipeg image for ERBF, GRBF, neural, and polynomial kernels are 98.65 (72.68), 98.67 (73.54), 98.27 (70.15), and 99.46 (75.03), respectively. The second set of results is a comparison of DSVM, SVM, DNN, Gaussian Mixture Model (GMM), K Nearest Neighbour (KNN), and K Means (KM) classifiers; the results for Flevoland image for DSVM, SVM, DNN, GMM, KNN, and KM are 99.12, 74.13, 96.29, 75.06, 75.85, and 21.43, respectively, while the results for Winnipeg image for DSVM, SVM, DNN, GMM, KNN, and KM are 98.76, 72.85, 95.64, 73.20, 73.91, and 25.60, respectively. Since the Kappa coefficient is presumed to be a more accurate measure for accuracy estimation, it is used to evaluate the performances of all the models. The computed Kappa coefficients for of DSVM, SVM, DNN, GMM, KNN, and KM for Flevoland are 92.45, 70.71, 88.76, 68.59, 68.62, and 18.89, respectively; while the computed Kappa coefficients for DSVM, SVM, DNN, GMM, KNN, and KM for Winnepeg are 92.45, 70.71, 88.76, 68.59, 68.62, and 18.89, respectively. Based on the metrics used to evaluate the performances of the experiments; the results show that the DSVM outperformed the other classifiers. The high accuracy obtained with the DSVM shows it is a state-of-the-art algorithm for PolSAR image classification and a significant progress in the latest of DL applications.

摘要

遥感中偏振合成孔径雷达 (PolSAR) 图像分类带来的主要问题是开发分类器的能力，该分类器可以充分辨别自然和人造目标中固有的不同类别。重点已从使用传统分类器转向现代非参数分类器，例如人工神经网络 (ANN) 和支持向量机 (SVM)，以及最近的混合深度神经网络 (DNN)，它是深度学习的融合(DL) 和人工神经网络。因此，本研究提出了深度支持向量机 (DSVM) 的新应用，它是 DL 和 SVM 对 PolSAR 图像分类的融合。荷兰弗莱福兰地区和加拿大温尼伯的两幅 PolSAR 图像被用作实验的试验台。Lee滤波器用于对图像进行滤波以抑制图像中的斑点噪声。泡利分解用于将图像分解为$\left|{秒}_{HH}+{秒}_{伏伏}\right|$, $\left|{秒}_{HH}-{秒}_{伏伏}\right|$, $\left|{秒}_{H伏}\right|$极化通道。然后，灰度共生矩阵（GLCM）纹理特征为$\left|{秒}_{HH}+{秒}_{伏伏}\right|$, $\left|{秒}_{HH}-{秒}_{伏伏}\right|$, $\left|{秒}_{H伏}\right|$基于相关性、对比度、能量和均匀性统计，使用 GLCM 方向 0°、45°、90°和 135°，偏移距离为 60 来提取。为了提高模型的效率 8, 16, 32, 64探索了 、128 和 256 个量化级别。DSVM 分类器使用四个核函数实现：指数径向基函数 (ERBF)、高斯径向基函数 (GRBF)、神经和多项式。第一组结果是 DSVM 和 SVM 的比较。ERBF、GRBF、神经和多项式核的 Flevoland 图像结果分别为 99.17 (73.39)、99.32 (74.62)、98.64 (71.28) 和 99.34 (77.21)；对于 ERBF、GRBF、神经和多项式内核的温尼伯图像，分别为 98.65 (72.68)、98.67 (73.54)、98.27 (70.15) 和 99.46 (75.03)。第二组结果是DSVM、SVM、DNN、高斯混合模型 (GMM)、K 最近邻 (KNN) 和 K 均值 (KM) 分类器；DSVM、SVM、DNN、GMM、KNN和KM的Flevoland图像结果分别为99.12、74.13、96.29、75.06、75.85和21.43，而DSVM、SVM、DNN、GMM、KNN的Winnipeg图像结果和 KM 分别为 98.76、72.85、95.64、73.20、73.91 和 25.60。由于 Kappa 系数被认为是准确度估计的更准确度量，因此它用于评估所有模型的性能。Flevoland 的 DSVM、SVM、DNN、GMM、KNN 和 KM 的计算 Kappa 系数分别为 92.45、70.71、88.76、68.59、68.62 和 18.89；而 Winnepeg 的 DSVM、SVM、DNN、GMM、KNN 和 KM 的计算 Kappa 系数分别为 92.45、70.71、88.76、68.59、68.62 和 18.89。基于用于评估实验性能的指标；结果表明 DSVM 优于其他分类器。DSVM 获得的高精度表明它是一种最先进的 PolSAR 图像分类算法，也是最新 DL 应用的重大进展。