Pattern Statistics Network for Classification of High-Resolution SAR Images

The classification of synthetic aperture radar (SAR) images is of great importance for rapid scene understanding. Recently, convolutional neural networks (CNNs) have been applied to the classification of single-polarized SAR images. However, it is still difficult due to the random and complex spatial patterns lying in SAR images, especially in the case of finite training data. In this paper, a pattern statistics network (PSNet) is proposed to address this problem. PSNet borrows the idea from the statistics and probability theory and explicitly embeds the random nature of SAR images in the representation learning. In the PSNet, both fluctuation and pattern representations are extracted for SAR images. More specifically, the fluctuation representation does not consider the rigorous relationships between local pixels and only describes the average fluctuation of local pixels. By contrast, the pattern representation is devoted to hierarchically capturing the interactions between local pixels, namely, the spatial patterns of SAR images. The proposed PSNet is evaluated on three real SAR data, including spaceborne and airborne data. The experimental results indicate that the fluctuation representation is useful and PSNet achieves superior performance in comparison with related CNN-based and texture-based methods.

• Publication year

  2019

• Venue

  Remote Sensing

• Publication date

  2019-08-20

• Fields of study

  Geology, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.3390/RS11161942
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Generative Adversarial Networks

  2021cited by this paper
• Polarimetric SAR Image Classification Using Geodesic Distances and Composite Kernels

  2018cited by this paper
• SAR Image Classification via Deep Recurrent Encoding Neural Networks

  2018cited by this paper
• The Deep Regression Bayesian Network and Its Applications: Probabilistic Deep Learning for Computer Vision

  2018cited by this paper
• SAR Targets Classification Based on Deep Memory Convolution Neural Networks and Transfer Parameters

  2018cited by this paper
• Random forest wetland classification using ALOS-2 L-band, RADARSAT-2 C-band, and TerraSAR-X imagery

  2017cited by this paper
• Matrix Analysis and Applications

  2017cited by this paper
• Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification

  2017cited by this paper
• Remote Sensing Image Scene Classification: Benchmark and State of the Art

  2017cited by this paper
• Remote Sensing Image Classification: A survey of support-vector-machine-based advanced techniques

  2017cited by this paper
• Multi-Scale Dense Networks for Resource Efficient Image Classification

  2017cited by this paper
• Statistical Modeling of Polarimetric SAR Data: A Survey and Challenges

  2017cited by this paper
• Discriminant deep belief network for high-resolution SAR image classification

  2017cited by this paper
• Deep Supervised and Contractive Neural Network for SAR Image Classification

  2017cited by this paper
• Deep learning in remote sensing: a review

  2017cited by this paper
• Opening the Black Box of Deep Neural Networks via Information

  2017cited by this paper
• Unsupervised Learning of Generalized Gamma Mixture Model With Application in Statistical Modeling of High-Resolution SAR Images

  2016cited by this paper
• POL-SAR Image Classification Based on Wishart DBN and Local Spatial Information

  2016cited by this paper
• Convolutional Neural Networks Analyzed via Convolutional Sparse Coding

  2016cited by this paper
• Deep Discriminative and Generative Models for speech Pattern Recognition

  2016cited by this paper
• Optimization Methods for Large-Scale Machine Learning

  2016cited by this paper
• Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks

  2016cited by this paper
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

  2016cited by this paper
• Densely Connected Convolutional Networks

  2016cited by this paper
• Urban Land Use and Land Cover Classification Using Remotely Sensed SAR Data through Deep Belief Networks

  2015cited by this paper
• High-Resolution SAR Image Classification via Deep Convolutional Autoencoders

  2015cited by this paper
• Deep Learning

  2015cited by this paper
• Overview of China Earth Observation Satellite Programs [Space Agencies]

  2015cited by this paper
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• Multi-scale Recognition with DAG-CNNs

  2015cited by this paper
• Remote Sensing Image Classification: No Features, No Clustering

  2015cited by this paper
• Evolution of the RADARSAT Program

  2014cited by this paper
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

  2014cited by this paper
• Caffe: Convolutional Architecture for Fast Feature Embedding

  2014cited by this paper
• Texture Classification of PolSAR Data Based on Sparse Coding of Wavelet Polarization Textons

  2013cited by this paper
• A tutorial on synthetic aperture radar

  2013cited by this paper
• Land-Cover Mapping by Markov Modeling of Spatial–Contextual Information in Very-High-Resolution Remote Sensing Images

  2013cited by this paper
• Recent Trend and Advance of Synthetic Aperture Radar with Selected Topics

  2013cited by this paper
• Scalable Object Detection Using Deep Neural Networks

  2013cited by this paper
• A Tutorial on Speckle Reduction in Synthetic Aperture Radar Images

  2013cited by this paper
• Representation Learning: A Review and New Perspectives

  2012cited by this paper
• The European Earth monitoring (GMES) programme: Status and perspectives

  2012cited by this paper
• Characterization of Land Cover Types in TerraSAR-X Images by Combined Analysis of Speckle Statistics and Intensity Information

  2011cited by this paper
• TerraSAR-X SAR Processing and Products

  2010cited by this paper
• Delineation of Urban Footprints From TerraSAR-X Data by Analyzing Speckle Characteristics and Intensity Information

  2010cited by this paper
• Image Segmentation with a Unified Graphical Model

  2010cited by this paper
• Efficient Learning of Deep Boltzmann Machines

  2010cited by this paper
• Class segmentation and object localization with superpixel neighborhoods

  2009cited by this paper
• Estimation of the Equivalent Number of Looks in Polarimetric Synthetic Aperture Radar Imagery

  2009cited by this paper
• Visualizing Data using t-SNE

  2008cited by this paper
• Image statistics and the perception of surface qualities

  2007cited by this paper
• Target Detection and Texture Segmentation in Polarimetric SAR Images Using a Wavelet Frame: Theoretical Aspects

  2007cited by this paper
• Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

  2006cited by this paper
• A Fast Learning Algorithm for Deep Belief Nets

  2006cited by this paper
• Gaussian MRF rotation-invariant features for image classification

  2004cited by this paper
• A new statistical model for Markovian classification of urban areas in high-resolution SAR images

  2004cited by this paper
• Unsupervised classification of radar images using hidden Markov chains and hidden Markov random fields

  2003cited by this paper
• Gamma mixture modeled with "second kind statistics": application to SAR image processing

  2002cited by this paper
• Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

  2002influential reference
• What are Textons?

  2002cited by this paper
• High resolution radar clutter statistics

  1999cited by this paper
• Filtering for Texture Classification: A Comparative Study

  1999cited by this paper
• Gradient-based learning applied to document recognition

  1998influential reference
• Scale-Space Theory : A Basic Tool for Analysing Structures at Different Scales

  1994cited by this paper
• Speckle filtering of synthetic aperture radar images : a review

  1994cited by this paper
• The Handbook of Pattern Recognition and Computer Vision

  1993cited by this paper
• A review of assessing the accuracy of classifications of remotely sensed data

  1991cited by this paper
• Multichannel Texture Analysis Using Localized Spatial Filters

  1990cited by this paper
• A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

  1989cited by this paper
• Modern signal processing

  1988cited by this paper
• Lognormal random field models and their applications to radar image synthesis

  1987cited by this paper
• Textural Infornation in SAR Images

  1986cited by this paper
• Amplitude distribution of composite terrain radar clutter and the κ-Distribution

  1984cited by this paper
• The Laplacian Pyramid as a Compact Image Code

  1983cited by this paper
• Markov Random Field Texture Models

  1983cited by this paper
• Textural Features for Radar Image Analysis

  1981cited by this paper
• Tutorial review of synthetic-aperture radar (SAR) with applications to imaging of the ocean surface

  1978cited by this paper
• Some fundamental properties of speckle

  1976influential reference
• Textural Features for Image Classification

  1973influential reference

• PAHD: perception-action-based human decision making using explainable graph neural networks on SAR images

  2023cites this paper
• Statistical Convolutional Neural Network for Land-Cover Classification From SAR Images

  2020cites this paper
• Remote-sensing image super-resolution using classifier-based generative adversarial networks

  2020cites this paper