Polarimetric Synthetic Aperture Radar Image Segmentation Research Articles

Your Input Matters—Comparing Real-Valued PolSAR Data Representations for CNN-Based Segmentation

Inspired by the success of Convolutional Neural Network (CNN)-based deep learning methods for optical image segmentation, there is a growing interest in applying these methods to Polarimetric Synthetic Aperture Radar (PolSAR) data. However, effectively utilizing well-established real-valued CNNs for PolSAR image segmentation requires converting complex-valued data into real-valued representations. This paper presents a systematic comparison of 14 different real-valued representations used as CNN input in the literature. These representations encompass various approaches, including the use of coherency matrix elements, hand-crafted feature vectors, polarimetric features based on target decomposition, and combinations of these methods. The goal is to assess the impact of the choice of PolSAR data representation on segmentation performance and identify the most suitable representation. Four test configurations are employed to achieve this, involving different CNN architectures (U-Net with ResNet-18 or EfficientNet backbone) and PolSAR data acquired in different frequency bands (S- and L-band). The results emphasize the importance of selecting an appropriate real-valued representation for CNN-based PolSAR image segmentation. This study’s findings reveal that combining multiple polarimetric features can potentially enhance segmentation performance but does not consistently improve the results. Therefore, when employing this approach, careful feature selection becomes crucial. In contrast, using coherency matrix elements with amplitude and phase representation consistently achieves high segmentation performance across different test configurations. This representation emerges as one of the most suitable approaches for CNN-based PolSAR image segmentation. Notably, it outperforms the commonly used alternative approach of splitting the coherency matrix elements into real and imaginary parts.

MASA-SegNet: A Semantic Segmentation Network for PolSAR Images

Semantic segmentation of Polarimetric SAR (PolSAR) images is an important research topic in remote sensing. Many deep neural network-based semantic segmentation methods have been applied to PolSAR image segmentation tasks. However, a lack of effective means to deal with the similarity of object features and speckle noise in PolSAR images exists. Thisstudy aims to improve the discriminative capability of neural networks for various intensities of backscattering coefficients while reducing the effects of noise in PolSAR semantic segmentation tasks. Firstly, we propose pre-processing methods for PolSAR image data, which consist of the fusion of multi-source data and false color mapping. Then, we propose a Multi-axis Sequence Attention Segmentation Network (MASA-SegNet) for semantic segmentation of PolSAR data, which is an encoder–decoder framework. Specifically, within the encoder, a feature extractor is designed and implemented by stacking Multi-axis Sequence Attention blocks to efficiently extract PolSAR features at multiple scales while mitigating inter-class similarities and intra-class differences from speckle noise. Moreover, the process of serialized residual connection design enables the propagation of spatial information throughout the network, thereby improving the overall spatial awareness of MASA-SegNet. Within the decoder, it is used to accomplish the semantic segmentation task. The superiority of this algorithm for semantic segmentation will be explored through feature visualization. The experiments show that our proposed spatial sequence attention mechanism can effectively extract features and reduce noise interference and is thus able to obtain the best results on two large-scale public datasets (the AIR-POlSAR-Seg and FUSAR-Map datasets).

Comparison Between Equivalent Architectures of Complex-valued and Real-valued Neural Networks - Application on Polarimetric SAR Image Segmentation

Comparison Between Equivalent Architectures of Complex-valued and Real-valued Neural Networks - Application on Polarimetric SAR Image Segmentation

Superpixel segmentation of PolSAR images based on improved local iterative clustering

ABSTRACT In order to solve the problem that the simple linear iterative clustering (SLIC) cannot segment the noisy image well, the local iterative clustering (LIC) is improved and successfully applied to the superpixel segmentation of polarimetric synthetic aperture radar (PolSAR) image. However, this algorithm still has two problems: the computation of edge graph is too large and the content of superpixel cannot guarantee the homogeneity. In this article, the LIC algorithm is improved to segment PolSAR image better and faster. For the first problem, the algorithm introduces the integral graph into edge graph calculation to remove the redundant operation; for the second problem, the algorithm adds hypothesis testing to test the homogeneity of superpixel content, and re-segment the superpixel that does not meet the homogeneity hypothesis. The experiment is carried out with the measured data of AIRSAR system and GaoFen-3 system, and the experimental result shows that the algorithm can double the calculation speed of edge graph and significantly improves the superpixel segmentation effect.

Segmentation of multi-temporal polarimetric SAR data based on mean-shift and spectral graph partitioning.

Polarimetric SAR (PolSAR) image segmentation is a key step in its interpretation. For the targets with time series changes, the single-temporal PolSAR image segmentation algorithm is difficult to provide correct segmentation results for its target recognition, time series analysis and other applications. For this, a new algorithm for multi-temporal PolSAR image segmentation is proposed in this paper. Firstly, the over-segmentation of single-temporal PolSAR images is carried out by the mean-shift algorithm, and the over-segmentation results of single-temporal PolSAR are combined to get the over-segmentation results of multi-temporal PolSAR images. Secondly, the edge detectors are constructed to extract the edge information of single-temporal PolSAR images and fuse them to get the edge fusion results of multi-temporal PolSAR images. Then, the similarity measurement matrix is constructed based on the over-segmentation results and edge fusion results of multi-temporal PolSAR images. Finally, the normalized cut criterion is used to complete the segmentation of multi-temporal PolSAR images. The performance of the proposed algorithm is verified based on three temporal PolSAR images of Radarsat-2, and compared with the segmentation algorithm of single-temporal PolSAR image. Experimental results revealed the following findings: (1) The proposed algorithm effectively realizes the segmentation of multi-temporal PolSAR images, and achieves ideal segmentation results. Moreover, the segmentation details are excellent, and the region consistency is good. The objects which can’t be distinguished by the single-temporal PolSAR image segmentation algorithm can be segmented. (2) The segmentation accuracy of the proposed multi-temporal algorithm is up to 86.5%, which is significantly higher than that of the single-temporal PolSAR image segmentation algorithm. In general, the segmentation result of proposed algorithm is closer to the optimal segmentation. The optimal segmentation of farmland parcel objects to meet the needs of agricultural production is realized. This lays a good foundation for the further interpretation of multi-temporal PolSAR image.

MP-ResNet: Multipath Residual Network for the Semantic Segmentation of High-Resolution PolSAR Images

There are limited studies on the semantic segmentation of high-resolution Polarimetric Synthetic Aperture Radar (PolSAR) images due to the scarcity of training data and the inference of speckle noises. The Gaofen contest has provided open access of a high-quality PolSAR semantic segmentation dataset. Taking this chance, we propose a Multi-path ResNet (MP-ResNet) architecture for the semantic segmentation of high-resolution PolSAR images. Compared to conventional U-shape encoder-decoder convolutional neural network (CNN) architectures, the MP-ResNet learns semantic context with its parallel multi-scale branches, which greatly enlarges its valid receptive fields and improves the embedding of local discriminative features. In addition, MP-ResNet adopts a multi-level feature fusion design in its decoder to make the best use of the features learned from its different branches. Ablation studies show that the MPResNet has significant advantages over its baseline method (FCN with ResNet34). It also surpasses several classic state-of-the-art methods in terms of overall accuracy (OA), mean F1 and fwIoU, whereas its computational costs are not much increased. This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images. The code is available at: https://github.com/ggsDing/SARSeg.

DENet: Double-Encoder Network With Feature Refinement and Region Adaption for Terrain Segmentation in PolSAR Images

Recently, many studies exploit deep neural networks to promote terrain segmentation in polarimetric synthetic aperture radar (PolSAR) images. However, these works usually inherit the nature-scene approaches directly and may not be robust for the PolSAR image segmentation task. The main limitations include single-type feature construction, weak feature consistency, and geometry-agnostic collection of scattering information. In this article, we present the DENet, a double-encoder network with feature refinement and region adaption for the terrain segmentation in PolSAR images. First, a double-encoder architecture is proposed to leverage the multitype information of PolSAR images, which can provide more discriminative features than the previous methods using the single-type feature. Second, considering that the polarization information has strong consistency over the category-identical regions, a polarization-guided refinement module is proposed to maintain the feature consistency in the PolSAR segmentation model. This design alleviates the phenomenon of incomplete and fragmented segmentation results. Third, in view of the rich targets’ characteristics in the scattering information, a region-adaptive convolution module is developed to facilitate the scattering information collected over the geometry-irregular regions. This design can improve the segmentation accuracy on the geometry-irregular regions. Extensive experiments are conducted on six PolSAR images to verify the effectiveness of the DENet. Compared with the previous works, our method achieves competitive performance.

PSRN: Polarimetric Space Reconstruction Network for PolSAR Image Semantic Segmentation

To accurately extract various ground objects from polarimetric synthetic aperture radar (PolSAR) images is a challenging research topic. The deep convolutional neural networks are widely used in SAR segmentation due to their remarkable performance in optical remote sensing images. However, they are still limited by the geometric deformation of the objects, the strong scattering interference among adjacent objects, and the difficulty in distinguishing similar things. A large part of the reason lies in the insufficient utilization and the damage of feature mining for PolSAR data. In this article, focusing on the scattering matrix and the polarimetric coherency matrix, a polarimetric space reconstruction network is proposed. First, to maintain the relatively initial spatial constraints and the complete polarimetric information, the inputs are arranged by a spatial amplification coding method for the polarimetric coherency and scattering matrices. Second, a statistics enhancement module based on scattering characteristics is proposed to mine the differential expression among multiple scattering and polarimetric components, which supplements the local feature representation of convolutional operators. Third, the designed dual self-attention mechanism can capture the amplitude and phase relations of matrix element context adaptively. The proposed method keeps the spatiality of each scattering vector and fully explores the complementary information involved in the fully polarimetric data. Moreover, it accomplishes the accurate land cover classification for PolSAR images, especially the traditional confusing categories, such as water and roads. The experimental results on the E-SAR, AIRSAR, Gaofen-3, and RADARSAT-2 datasets show that the proposed method is effective and promising for PolSAR image segmentation.

Polarimetric Semivariogram-Based Spatial Scale Selection for PolSAR Image Segmentation With Mean-Shift Algorithm

Image segmentation has been an important procedure in object-based image analysis (OBIA), which takes image object as a processing unit. The spatial scale in image segmentation has great importance in OBIA. Due to the high heterogeneity and large dynamic range of polarimetric synthetic aperture radar (PolSAR) images, it is often difficult to choose optimal spatial scales. This letter proposes a polarimetric semivariogram-based spatial scale selection method for PolSAR image segmentation. The optimal spatial bandwidth parameter in the mean-shift algorithm is pre-estimated based on the combined polarimetric and statistical analysis of PolSAR images. By implementing a quantitative evaluation of segmentation result, the effectiveness of the proposed method in optimal spatial bandwidth selection for PolSAR image segmentation is verified. Experiments on both the EMISAR and UAVSAR L-band PolSAR data sets testify the validity of the proposed adaptive optimal bandwidth selection strategy for PolSAR images.

PolSAR image segmentation based on feature extraction and data compression using Weighted Neighborhood Filter Bank and Hidden Markov random field-expectation maximization

Despite the good performance of methods such as wavelet transform, Gabor filter bank, and scale-invariant feature transform (SIFT) as the first step of image segmentation, they have been some difficulties in the selection of suitable numbers of scales and directions for them. In this paper, a novel method is presented for Polarimetric Synthetic Aperture Radar (PolSAR) image segmentation, in which there is no need for any parameter initialization. The proposed method, called POLWHE is based on Lossy Minimum Descriptive Length (LMDL), Zero Padding Weighted Neighborhood Filter Bank (ZPWNFB) and Hidden Markov Random Field-Expectation Maximization (HMRF-EM). In the proposed method, first, Simple Linear Iterative Clustering (SLIC) and entropy are used for the adaptive generation of superpixels. Then, these superpixels are merged based on the learned texture and color features and the ZPWNFB edge-map. This procedure results in the image being segmented automatically. Next, the initial labels of the image are assigned by k-means and improved by HMRF-EM and ZPWNFB (KWHE). Finally, the automatic method and KWHE are combined and the final segmentation result is obtained. The proposed method is tested on real PolSAR images. The results prove the superiority of the proposed method as it improves both the performance and the noise resistance with the mean accuracy of 92.30%.

Adaptive Statistical Superpixel Merging With Edge Penalty for PolSAR Image Segmentation

This article proposes an efficient and adaptive statistical superpixel merging approach with edge penalty for polarimetric synthetic aperture radar (PolSAR) image segmentation. Based on the initial superpixel over-segmentation result obtained by our previously proposed adaptive polarimetric superpixel generation algorithm (Pol-ASLIC), this work achieves efficient and accurate PolSAR image segmentation by merging superpixels using the statistical region merging (SRM) framework. This article proposes to define a new dissimilarity measure between superpixels, which takes the edge penalty into consideration, leading to a reasonable and accurate merging order for superpixel pairs. With regard to the merging predicate of superpixels, a polarimetric homogeneity measurement (HoM) is used to define the merging threshold, making the merging predicate and merging threshold adaptive to the PolSAR image content. Experimental results on three airborne and one spaceborne PolSAR data sets demonstrate that the proposed approach can effectively improve the computation efficiency and segmentation accuracy in comparison with state-of-the-art merging-based methods for PolSAR data. More importantly, the proposed approach is free of parameters and easy to use.

Unsupervised Segmentation of Multilook Polarimetric Synthetic Aperture Radar Images

This paper proposes a new unsupervised image segmentation method for multilook polarimetric synthetic aperture radar (PolSAR) data. The statistical model for the PolSAR data is considered as a finite mixture of non-Gaussian compound distributions considered as the product of two statistically independent random variates, speckle, and texture. With different texture distributions, the product model leads to various expressions of the compound distribution. The method uses a Markov random field (MRF) model for pixel class labels. The expectation–maximization/maximization of the posterior marginals (EM/MPM) algorithm is used for the simultaneous estimation of texture and speckle parameters and for the segmentation of multilook PolSAR images. Simulated and real PolSAR data are shown to demonstrate the method.

Superpixel-Based Segmentation of Polarimetric SAR Images through Two-Stage Merging

Image segmentation plays a fundamental role in image understanding and region-based applications. This paper presents a superpixel-based segmentation method for Polarimetric SAR (PolSAR) data, in which a two-stage merging strategy is proposed. First, based on the initial superpixel partition, the Wishart-merging stage (WMS) simultaneously merges the regions in homogeneous areas. The edge penalty is combined with the Wishart energy loss to ensure that the superpixels to be merged are from the same land cover. The second stage follows the iterative merging procedure, and applies the doubly flexible KummerU distribution to better characterize the resultant regions from WMS, which are usually located in heterogeneous areas. Moreover, the edge penalty and the proposed homogeneity penalty are adopted in the KummerU-merging stage (KUMS) to further improve the segmentation accuracy. The two-stage merging strategy applies the general statistical model for the superpixels without ambiguity, and more advanced model for the regions with ambiguity. Therefore, the implementing efficiency can be improved based on the WMS, and the accuracy can be increased through the KUMS. Experimental results on two real PolSAR datasets show that the proposed method can effectively improve the computation efficiency and segmentation accuracy compared with the classical merging-based methods.

A contextual-based segmentation of compact PolSAR images using Markov Random Field (MRF) model

ABSTRACTAs the first major step in each object-oriented feature extraction approach, segmentation plays an essential role as a preliminary step towards further and higher levels of image processing. The primary objective of this paper is to illustrate the potential of Polarimetric Synthetic Aperture Radar (PolSAR) features extracted from Compact Polarimetry (CP) SAR data for image segmentation using Markov Random Field (MRF). The proposed method takes advantage of both spectral and spatial information to segment the CP SAR data. In the first step of the proposed method, k-means clustering was applied to over-segment the image using the appropriate features optimally selected using Genetic Algorithm (GA). As a similarity criterion in each cluster, a probabilistic distance was used for an agglomerative hierarchical merging of small clusters into an appropriate number of larger clusters. In the agglomerative clustering approach, the estimation of the appropriate number of clusters using the data log-likelihood algorithm differs depending on the distance criterion used in the algorithm. In particular, the Wishart Chernoff distance which is independent of samples (pixels) tends to provide a higher appropriate number of clusters compared to the Wishart test statistic distance. This is because the Wishart Chernoff distance preserves detailed data information corresponding to small clusters. The probabilistic distance used in this study is Wishart Chernoff distance which evaluates the similarity of clusters by measuring the distance between their complex Wishart probability density functions. The output of this step, as the initial segmentation of the image, is applied to a Markov Random Field model to improve the final segmentation using vicinity information. The method combines Wishart clustering and enhanced initial clusters in order to access the posterior MRF energy function. The contextual image classifier adopts the Iterated Conditional Mode (ICM) approach to converge to a local minimum and represent a good trade-off between segmentation accuracy and computation burden. The results showed that the PolSAR features extracted from CP mode can provide an acceptable overall accuracy in segmentation when compared to the full polarimetry (FP) and Dual Polarimetry (DP) data. Moreover, the results indicated that the proposed algorithm is superior to the existing image segmentation techniques in terms of segmentation accuracy.

Superpixel Segmentation of Polarimetric Synthetic Aperture Radar (SAR) Images Based on Generalized Mean Shift

The mean shift algorithm has been shown to perform well in optical image segmentation. However, the conventional mean shift algorithm performs poorly if it is directly used with Synthetic Aperture Radar (SAR) images due to the large dynamic range and strong speckle noise. Recently, the Generalized Mean Shift (GMS) algorithm with an adaptive variable asymmetric bandwidth has been proposed for Polarimetric SAR (PolSAR) image filtering. In this paper, the GMS algorithm is further developed for PolSAR image segmentation. A new merging predicate that is defined in the joint spatial-range domain is derived based on the GMS algorithm. A pre-sorting strategy and a post-processing step are also introduced into the GMS segmentation algorithm. The proposed algorithm can be directly used for PolSAR image superpixel segmentation without any pre-processing steps. Experiments using Airborne SAR (AirSAR) and Experimental SAR (ESAR) L-band PolSAR data demonstrate the effectiveness of the proposed superpixel segmentation algorithm. The parameter settings, stability, quality, and efficiency of the GMS algorithm are also discussed at the end of this paper.

A PolSAR Image Segmentation Algorithm Based on Scattering Characteristics and the Revised Wishart Distance.

A novel segmentation algorithm for polarimetric synthetic aperture radar (PolSAR) images is proposed in this paper. The method is composed of two essential components: a merging order and a merging predicate. The similarity measured by the complex-kind Hotelling–Lawley trace (HLT) statistic is used to decide the merging order. The merging predicate is determined by the scattering characteristics and the revised Wishart distance between adjacent pixels, which can greatly improve the performance in speckle suppression and detail preservation. A postprocessing step is applied to obtain a satisfactory result after the merging operation. The decomposition and merging processes are iteratively executed until the termination criterion is met. The superiority of the proposed method was verified with experiments on two RADARSAT-2 PolSAR images and a Gaofen-3 PolSAR image, which demonstrated that the proposed method can obtain more accurate segmentation results and shows a better performance in speckle suppression and detail preservation than the other algorithms.

A Two-Phase Fuzzy Clustering Algorithm Based on Neurodynamic Optimization With Its Application for PolSAR Image Segmentation

This paper presents a two-phase fuzzy clustering algorithm based on neurodynamic optimization with its application for polarimetric synthetic aperture radar (PolSAR) remote sensing image segmentation. The two-phase clustering algorithm starts with the linear-assignment initialization phase with the least similar cluster representatives to remedy the inconsistency of clustering results from random initialization and is, then, followed with multiple-kernel fuzzy C-means clustering. By incorporating multiple kernels in the clustering framework, various features are incorporated cohesively. A winner-takes-all neural network is employed to acquire the highest kernel weights and associated cluster centers and membership matrices, which enables better characterization and adaptability in each individual cluster. Simulation results for UCI benchmark datasets and PolSAR remote sensing image segmentation are reported to substantiate the effectiveness and the superiority of the proposed clustering algorithm.

Spectral Clustering with Eigenvalue Similarity Metric Method for POL-SAR Image Segmentation of Land Cover

A simple and fast approach based on eigenvalue similarity metric for Polarimetric SAR image segmentation of Land Cover is proposed in this paper. The approach uses eigenvalues of the coherency matrix as to construct similarity metric of clustering algorithm to segment SAR image. The Mahalanobis distance is used to metric pairwise similarity between pixels to avoid the manual scale parameter tuning in previous spectral clustering method. Furthermore, the spatial coherence constraints and spectral clustering ensemble are employed to stabilize and improve the segmentation performance. All experiments are carried out on three sets of Polarimetric SAR data. The experimental results show that the proposed method is superior to other comparison methods.

Unsupervised PolSAR Image Classification and Segmentation Using Dirichlet Process Mixture Model and Markov Random Fields With Similarity Measure

The Markov random fields (MRF) is skillful in incorporating the spatial-contextual information of images and has been widely applied to remote-sensing image classification and segmentation. However, the traditional MRF-based method is unable to determine the precise number of clusters automatically. It is known that the Dirichlet process mixture model (DPMM) takes the number of clusters as a model parameter and estimates it in image classification. Therefore, the DPMM is a powerful and potential method for classification tasks. Then, in this paper, by fusing the DPMM model and a similarity measure scheme into the MRF framework, we propose a novel unsupervised classification and segmentation method for polarimetric synthetic aperture radar (PolSAR) images, abbreviated as DPMM-SMMRF. First, the DPMM built by the multidimensional Gaussian distribution is introduced into the MRF framework, which enables the proposed DPMM-SMMRF model to identify the underlying number of clusters automatically. Second, to utilize the polarization information adequately and modulate the spatial correlation, the similarity measure between the neighboring polarimetric covariance matrices is utilized to construct the interaction term; thus, providing strong noise immunity and enhancing the ability of the classification of the sample pixels. Then, for updating the class labels and the parameters in the proposed DPMM-SMMRF model, we propose a detailed sampling procedure based on the Gibbs sampling. Experiments on real PolSAR images demonstrate that the proposed DPMM-SMMRF model can automatically recognize the number of clusters and simultaneously obtain higher classification accuracy, more accurate edge location, and smoother homogeneous areas compared to several recent MRF models.

Multi-Feature Segmentation for High-Resolution Polarimetric SAR Data Based on Fractal Net Evolution Approach

Segmentation techniques play an important role in understanding high-resolution polarimetric synthetic aperture radar (PolSAR) images. PolSAR image segmentation is widely used as a preprocessing step for subsequent classification, scene interpretation and extraction of surface parameters. However, speckle noise and rich spatial features of heterogeneous regions lead to blurred boundaries of high-resolution PolSAR image segmentation. A novel segmentation algorithm is proposed in this study in order to address the problem and to obtain accurate and precise segmentation results. This method integrates statistical features into a fractal net evolution algorithm (FNEA) framework, and incorporates polarimetric features into a simple linear iterative clustering (SLIC) superpixel generation algorithm. First, spectral heterogeneity in the traditional FNEA is substituted by the G0 distribution statistical heterogeneity in order to combine the shape and statistical features of PolSAR data. The statistical heterogeneity between two adjacent image objects is measured using a log likelihood function. Second, a modified SLIC algorithm is utilized to generate compact superpixels as the initial samples for the G0 statistical model, which substitutes the polarimetric distance of the Pauli RGB composition for the CIELAB color distance. The segmentation results were obtained by weighting the G0 statistical feature and the shape features, based on the FNEA framework. The validity and applicability of the proposed method was verified with extensive experiments on simulated data and three real-world high-resolution PolSAR images from airborne multi-look ESAR, spaceborne single-look RADARSAT-2, and multi-look TerraSAR-X data sets. The experimental results indicate that the proposed method obtains more accurate and precise segmentation results than the other methods for high-resolution PolSAR images.