Three-Channel Convolutional Neural Network for Polarimetric SAR Images Classification

Abstract

Terrain classifications is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing and interpretation. A novel PolSAR classification method based on three-channel convolutional neural network (Tc-CNN) is proposed and this method can effectively take the advantage of unlabeled samples to improve the performance of classification with a small number of labeled samples. Several strategies are included in the proposed method. (1) In order to take the advantage of unlabeled samples, a data enhancement method based on neighborhood nearest neighbor propagation (N3P) method is proposed to enlarge the number of labeled samples. (2) To increase the role of central pixel in CNN classification based on pixel, a spatial weighted method is proposed to increase the weight of central pixel features and weak the weight of other types of pixel features. (3) A specific deep model for PolSAR image classification (named as Tc-CNN) is proposed, which can obtain more scale and deep polarization information to improve the classification results. Experimental results show that the proposed method achieves a much better performance than existing classification methods when the number of labeled samples is few. Index Terms-convolutional neural network (CNN); polarimetric SAR; terrain classification; three-channel convolutional neural network (Tc-CNN)

A Novel Multi-Objective Binary Chimp Optimization Algorithm for Optimal Feature Selection: Application of Deep-Learning-Based Approaches for SAR Image Classification

“…However, the most effective model for classifying POLSAR images is not clear. Since 2006, DL has become a popular topic in the ML world [ 21 ]. DL models are superior to traditional ML models due to data availability and system processing power developments [ 22 ].…”

Dark Area Classification From Airborne SAR Images Based on Deep Margin Learning

“…The year 2012 was a significant year for every science domain since Hinton first introduced deep learning technology [30]. More and more methods based on deep neural networks (DNN) have been applied to the SAR classification task, which profits from the DNN's strong capability of feature learning and generalization [31][32][33][34][35][36][37][38]. Not only the frequency of utilizing DNN is increasing, but also the dimension of the DNN is transferring from 2D to 3D [39].…”

“…Summary of development stages of SAR land surface classification is listed in Table I. Neural networks are slow to train [35][36][37][38] Even though the number of researches on shadow effect in SAR terrain classification is not so many, the shadow for SAR target classification still drew researchers' attention. For a single target in SAR image, shadows on the ground sometimes represent much more detailed information about the target's profile, which is a critical characteristic for target classification problems [41][42][43][44][45].…”

An Object-Based Markov Random Field with Partition-Global Alternately Updated for Semantic Segmentation of High Spatial Resolution Remote Sensing Image

“…The former designs a classifier with undetermined parameters according to specific rules, and obtains a classifier that can identify specific categories by identifying training samples. This category contains many methods, such as: support vector machines (SVMs) [6][7][8], neural network-based algorithms [9][10][11][12][13][14][15], deep learning [16][17][18][19][20][21][22], etc. The latter is based on the image's own features, directly modeling the image's data and giving segmentation results, such as: super-pixel [23][24][25][26], Markov random field (MRF) [27][28][29][30][31][32][33][34], conditional random field (CRF) [35][36][37][38][39], level set [40][41][42], etc.…”