Fuzzy Superpixels for Polarimetric SAR Images Classification

Guo, Yuwei; Jiao, Licheng; Wang, Shuang; Wang, Shuo; Liu, Fang; Hua, Wenqiang

doi:10.1109/tfuzz.2018.2814591

Cited by 59 publications

(53 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Not all the compared methods used every data set utilized in our work, thus, the compared methods are not exactly the same for each data set. The compared approaches include classical algorithms, such as SVM [15], Wishart [16] and Mean shift [54], pixel-wised algorithms [21,51] and region-based algorithms [37,55,56]. Method in [21] applied two cascaded convolutional layers to learn hierarchical polarimetric spatial features for PolSAR image classification.…”

Section: Classification Resultsmentioning

confidence: 99%

“…Method proposed in [51] adopted the nearest neighbor and SVM classifiers to classify PolSAR images based on the features extracted by tensor local discriminant embedding method. Method in [55] utilized Fuzzy superpixels to assist PolSAR image classification. Method employed in [56] classified PolSAR images with a deep neural network restrained by superpixels.…”

Section: Classification Resultsmentioning

confidence: 99%

See 1 more Smart Citation

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

et al. 2019

View full text Add to dashboard Cite

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in various PolSAR image application. And many pixel-wise, region-based classification methods have been proposed for PolSAR images. However, most of the pixel-wise methods can not model local spatial relationship of pixels due to negative effects of speckle noise, and most of the region-based methods fail to figure out the regions with the similar polarimetric features. Considering that color features can provide good visual expression and perform well for image interpretation, in this work, based on the PolSAR pseudo-color image over Pauli decomposition, we propose a supervised PolSAR image classification approach combining learned superpixels and quaternion convolutional neural network (QCNN). First, the PolSAR RGB pseudo-color image is formed under Pauli decomposition. Second, we train QCNN with quaternion PolSAR data converted by RGB channels to extract deep color features and obtain pixel-wise classification map. QCNN treats color channels as a quaternion matrix excavating the relationship among the color channels effectively and avoiding information loss. Third, pixel affinity network (PAN) is utilized to generate the learned superpixels of PolSAR pseudo-color image. The learned superpixels allow the local information exploitation available in the presence of speckle noise. Finally, we fuse the pixel-wise classification result and superpixels to acquire the ultimate pixel-wise PolSAR image classification map. Experiments on three real PolSAR data sets show that the proposed approach can obtain 96.56%, 95.59%, and 92.55% accuracy for Flevoland, San Francisco and Oberpfaffenhofen data set, respectively. And compared with state-of-the-art PolSAR image classification methods, the proposed algorithm can obtained competitive classification results.

show abstract

Section: Classification Resultsmentioning

confidence: 99%

Section: Classification Resultsmentioning

confidence: 99%

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

et al. 2019

View full text Add to dashboard Cite

show abstract

“…To overcome the problems of handcrafted features for scene classification, unsupervised feature learning is reckoned as the potential strategy. It can automatically learn features from unlabeled input data and has made astonishing progress in remote sensing scene classification [16][17][18]. The unsupervised-learning-based features are more discriminative and better suited to the classification problem.…”

Section: Introductionmentioning

confidence: 99%

Remote sensing scene classification based on rotation-invariant feature learning and joint decision making

Zhou

Liu

Zhao

et al. 2019

J Image Video Proc.

View full text Add to dashboard Cite

With the popular use of high-resolution satellite images, remote sensing scene classification has always been a hot research topic in its related areas. However, limited to the issues of remote sensing datasets including the small scale of scene classes, the lack of rich label information and so on, it is quite challenging for deep learning methods to learn powerful feature representation. To overcome this problem, we propose a rotation-invariant feature learning and joint decision-making method based on Siamese convolutional neural networks with the combination of identification and verification models. Firstly, a novel data augmentation strategy is proposed specially for the Siamese model to learning rotation-invariant features. Secondly, a joint decision mechanism is introduced in our method, which is realized by the identification and verification model to better improve the classification performance. The proposed method can not only suppress problems caused by lack of rich label samples but also improve the robustness of Siamese convolutional neural networks. Experimental results demonstrate that the proposed method is effective and efficient for remote sensing scene classification.

show abstract

“…On the other hand, image segmentation technology has been widely used in the field of image classification, as it can simultaneously utilize spatial and spectral information of HSIs [18][19][20][21][22][23][24][25][26]. By segmenting the image into multiple homogeneous regions and performing corresponding operations on each homogeneous region, the classification performance can be greatly improved.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Zhang

Shen

2019

Remote Sensing

View full text Add to dashboard Cite

Dimensionality reduction (DR) is an important preprocessing step in hyperspectral image applications. In this paper, a superpixelwise kernel principal component analysis (SuperKPCA) method for DR that performs kernel principal component analysis (KPCA) on each homogeneous region is proposed to fully utilize the KPCA’s ability to acquire nonlinear features. Moreover, for the proposed method, the differences in the DR results obtained based on different fundamental images (the first principal components obtained by principal component analysis (PCA), KPCA, and minimum noise fraction (MNF)) are compared. Extensive experiments show that when 5, 10, 20, and 30 samples from each class are selected, for the Indian Pines, Pavia University, and Salinas datasets: (1) when the most suitable fundamental image is selected, the classification accuracy obtained by SuperKPCA can be increased by 0.06%–0.74%, 3.88%–4.37%, and 0.39%–4.85%, respectively, when compared with SuperPCA, which performs PCA on each homogeneous region; (2) the DR results obtained based on different first principal components are different and complementary. By fusing the multiscale classification results obtained based on different first principal components, the classification accuracy can be increased by 0.54%–2.68%, 0.12%–1.10%, and 0.01%–0.08%, respectively, when compared with the method based only on the most suitable fundamental image.

show abstract

Fuzzy Superpixels for Polarimetric SAR Images Classification

Cited by 59 publications

References 37 publications

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

PolSAR Image Classification via Learned Superpixels and QCNN Integrating Color Features

Remote sensing scene classification based on rotation-invariant feature learning and joint decision making

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Contact Info

Product

Resources

About