Results 171 to 180 of about 2,397 (207)

Recursive Convolution Neural Network for PolSAR Image Classification

2020 35th Youth Academic Annual Conference of Chinese Association of Automation (YAC), 2020
Considering the limited of the training samples and the effect of speckle noise in PolSAR images, which further affects the learning performance of the classifier, a recursive convolution neural network model (CNN) is proposed. Samples with high confidence of each classification result will be used as the training samples of the next training.
Shuyin Zhang, Xudong Jing, Hongming Zhang, Huan Chen, Jianbang Zhao   +4 more
openaire   +1 more source

Unsupervised PolSAR Image Classification Using Discriminative Clustering

IEEE Transactions on Geoscience and Remote Sensing, 2017
This paper presents a novel unsupervised image classification method for polarimetric synthetic aperture radar (PolSAR) data. The proposed method is based on a discriminative clustering framework that explicitly relies on a discriminative supervised classification technique to perform unsupervised clustering. To implement this idea, we design an energy
Haixia Bi, Jian Sun, Zongben Xu
openaire   +1 more source

Weighted Wishart distance learning for PolSAR image classification

International Journal of Remote Sensing, 2017
ABSTRACTAn approach of weighted Wishart distance learning, shorted for W2-based distance learning, is proposed for polarimetric synthetic aperture radar (PolSAR) image classification. It aims to adjust the Wishart distance by enhancing discrimination as well as exploiting spatial information. The proposed distance learning keeps samples within the same
Chen Sun, Licheng Jiao, Liye Cheng, Hongying Liu   +3 more
openaire   +1 more source

Supervised Polsar Image Classification by Combining Multiple Features

2019 IEEE International Conference on Image Processing (ICIP), 2019
For polarimetric synthetic aperture radar (PolSAR) image classification, each pixel can be represented by multiple features from different perspectives, such as polarimetric feature (PF), texture feature (TF) and color feature (CF). Both multi-view canonical correlation analysis (MCCA) and multi-view spectral embedding (MSE) are two unsupervised multi ...
Xiayuan Huang, Xiangli Nie, Hong Qiao, Bo Zhang   +3 more
openaire   +1 more source

Adaptive Graph Convolutional Network for PolSAR Image Classification

IEEE Transactions on Geoscience and Remote Sensing, 2022
Polarimetric synthetic aperture radar (PolSAR) image classification is one of the hottest issues in remote sensing, where studies on pixel-level information and relationship are of great significance. In this article, graph convolutional network (GCN) is employed to accomplish this pixel-level task benefiting from its excellent capability in structure ...
Fang Liu, Jingya Wang, Xu Tang, Jia Liu, Xiangrong Zhang, Liang Xiao   +5 more
openaire   +1 more source

Riemannian sparse coding for classification of PolSAR images

2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016
Hermitian positive definite (HPD) covariance matrices form one of the most widely-used data representations in PolSAR applications. However, most of these applications either use statistical distribution models on the PolSAR covariance matrices or polarimetric target decomposition. In this paper, we study HPD matrices for PolSAR image classification in
Wen Yang, Neng Zhong, Xiangli Yang, Anoop Cherian   +3 more
openaire   +1 more source

Classification-oriented hyperspectral and PolSAR images synergic processing

2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS, 2013
Classification is one of the most important applications in the field of remote sensing. How to improve the accuracy of classification is the critical topic that has long obsessed the researchers. In this paper, a fusion method based on a synergic use of hyperspectral data and Polarimetric SAR (PolSAR) data is presented.
Tong Li, Junping Zhang, Honglei Zhao, Cuiping Shi   +3 more
openaire   +1 more source

PolSAR image speckle reduction based on pixels classification

2012 IEEE 11th International Conference on Signal Processing, 2012
An effective algorithm for PolSAR image speckle reduction is developed in this paper. First, pixels in the image are classified through three steps: i) HH/α plane is used for image initial classification based on the polarization difference; ii) anisotropy A and total backscattering power after PWF are combined for further classification; iii ...
Ping Han, Xiaohong Yu, Fei Dong
openaire   +1 more source

PolSAR image fast classification based on random similarity

2017 Progress In Electromagnetics Research Symposium - Spring (PIERS), 2017
Random similarity is used to construct an entropy/alpha-like classification of PolSAR image in terms of two parameters, i.e., the similarity-based angle α s and entropy H s . α s and H s are analogous to the Cloude-Pottier angle α and entropy H to characterize scattering mechanism and randomness, respectively.
Dong Li, Yunhua Zhang, Feiya Zhu
openaire   +1 more source

Fuzzy Support Vector Machine for PolSAR Image Classification

Advanced Materials Research, 2013
Fully Polarimetric Synthetic Aperture Radar (PolSAR) image classification, with the complexity for its data’s scattering mechanism and statistical property, has expected to be performed by an automatic categorization. This paper presents a supervised method called Fuzzy support vector machine (FSVM), which is a variant of the SVM algorithm to classify ...
Hong Xia Ke, Guo Dong Liu, Guo Bing Pan
openaire   +1 more source