Superpixel-Oriented Classification of PolSAR Images Using Complex-Valued Convolutional Neural Network Driven by Hybrid Data

Qin, Xianxiang; Zou, Huanxin; Yu, Wei; Wang, Peng

doi:10.1109/tgrs.2020.3040452

Cited by 22 publications

(16 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PolSAR utilizes vertical and horizontal polarization for emitting and receiving polarized radar waves with four channels: HH, HV, VH and VV. Each pixel of a single-look PolSAR image can be represented by a 2 × 2 complex scattering (or Sinclair) matrix S as [8]…”

Section: Polsar Datamentioning

confidence: 99%

“…Currently, several airborne and spaceborne platforms continuously provide an enormous amount of PolSAR data. It is inappropriate to interpret these highly complicated images with pixel-based methods because a large number of pixels in large-scale images prevents many algorithms from being computationally feasible [7,8]. The term superpixel refers to a region of self-similar pixels with local characteristics and certain visual significance [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Superpixel Generation for Polarimetric SAR Images with Cross-Iteration and Hexagonal Initialization

Zou

Qin

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Clustering-based methods of polarimetric synthetic aperture radar (PolSAR) image superpixel generation are popular due to their feasibility and parameter controllability. However, these methods pay more attention to improving boundary adherence and are usually time-consuming to generate satisfactory superpixels. To address this issue, a novel cross-iteration strategy is proposed to integrate various advantages of different distances with higher computational efficiency for the first time. Therefore, the revised Wishart distance (RWD), which has better boundary adherence but is time-consuming, is first integrated with the geodesic distance (GD), which has higher efficiency and more regular shape, to form a comprehensive similarity measure via the cross-iteration strategy. This similarity measure is then utilized alternately in the local clustering process according to the difference between two consecutive ratios of the current number of unstable pixels to the total number of unstable pixels, to achieve a lower computational burden and competitive accuracy for superpixel generation. Furthermore, hexagonal initialization is adopted to further reduce the complexity of searching pixels for relabelling in the local regions. Extensive experiments conducted on the AIRSAR, RADARSAT-2 and simulated data sets demonstrate that the proposed method exhibits higher computational efficiency and a more regular shape, resulting in a smooth representation of land cover in homogeneous regions and better-preserved details in heterogeneous regions.

show abstract

Section: Polsar Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Efficient Superpixel Generation for Polarimetric SAR Images with Cross-Iteration and Hexagonal Initialization

Zou

Qin

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Throughout literature, CV-CNNs are the most popular CVNN architecture used for PolSAR. All References [17]- [21] identically dimensioned the model with the same amount of layers and kernels. Therefore, we decided to use the same architecture, which presents two convolutional layers, with 6 and 12 kernels, respectively, for the complex model.…”

Section: Model Architecturesmentioning

confidence: 99%

Impact of PolSAR pre-processing and balancing methods on complex-valued neural networks segmentation tasks

Barrachina¹,

Ren²,

Morisseau³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exhaustively compare both methods for six model architectures, three complex-valued, and their respective real-equivalent models. We are comparing, therefore, not only the input representation impact but also the complex-against the real-valued models. We then argue that the dataset splitting produces a high correlation between training and validation sets, saturating the task and thus achieving very high performance. We, therefore, use a different data pre-processing technique designed to reduce this effect and reproduce the results with the same configurations as before (input representation and model architectures). After seeing that the performance per class is highly different according to class occurrences, we propose two methods for reducing this gap and performing the results for all input representations, models, and dataset preprocessing.

show abstract

“…In recent years, many deep convolutional neural networks (CNNs) have been proposed in the field of computer vision and shown powerful capabilities in many classification tasks. These CNNs have subsequently been introduced and improved in the application of PolSAR image classification [ 2 , 16 , 17 , 18 , 19 ]. Different from the traditional classification methods, CNN-based methods are not required to extract explicit features, and can integrate feature extraction and classifier design as a whole to provide superior classification results.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised Classification of PolSAR Images Based on Co-Training of CNN and SVM with Limited Labeled Samples

Zhao

Cheng

Qin

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Recently, convolutional neural networks (CNNs) have shown significant advantages in the tasks of image classification; however, these usually require a large number of labeled samples for training. In practice, it is difficult and costly to obtain sufficient labeled samples of polarimetric synthetic aperture radar (PolSAR) images. To address this problem, we propose a novel semi-supervised classification method for PolSAR images in this paper, using the co-training of CNN and a support vector machine (SVM). In our co-training method, an eight-layer CNN with residual network (ResNet) architecture is designed as the primary classifier, and an SVM is used as the auxiliary classifier. In particular, the SVM is used to enhance the performance of our algorithm in the case of limited labeled samples. In our method, more and more pseudo-labeled samples are iteratively yielded for training through a two-stage co-training of CNN and SVM, which gradually improves the performance of the two classifiers. The trained CNN is employed as the final classifier due to its strong classification capability with enough samples. We carried out experiments on two C-band airborne PolSAR images acquired by the AIRSAR systems and an L-band spaceborne PolSAR image acquired by the GaoFen-3 system. The experimental results demonstrate that the proposed method can effectively integrate the complementary advantages of SVM and CNN, providing overall classification accuracy of more than 97%, 96% and 93% with limited labeled samples (10 samples per class) for the above three images, respectively, which is superior to the state-of-the-art semi-supervised methods for PolSAR image classification.

show abstract

Superpixel-Oriented Classification of PolSAR Images Using Complex-Valued Convolutional Neural Network Driven by Hybrid Data

Cited by 22 publications

References 59 publications

Efficient Superpixel Generation for Polarimetric SAR Images with Cross-Iteration and Hexagonal Initialization

Efficient Superpixel Generation for Polarimetric SAR Images with Cross-Iteration and Hexagonal Initialization

Impact of PolSAR pre-processing and balancing methods on complex-valued neural networks segmentation tasks

Semi-Supervised Classification of PolSAR Images Based on Co-Training of CNN and SVM with Limited Labeled Samples

Contact Info

Product

Resources

About