Superpixel-Based Unsupervised Classification of Polsar Images with Adaptive Number of Terrain Classes

Zou, Huanxin; Shao, Ningyuan; Li, Meilin; Chen, Cheng; Qin, Xianxiang

doi:10.1109/igarss.2018.8519365

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three methods for NoC estimation considered in the comparison are the VATdtf method [53], the VATpdt method, and the iVATdt method. The VATpdt and iVATdt methods are ablation methods of the Pol-iVATpdt method.…”

Section: B Noc Estimation Resultsmentioning

confidence: 99%

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Li,

Zou,

Dong

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Semantic segmentation is an essential task in polarimetric synthetic aperture radar (PolSAR) image interpretation. To address the issue of insufficient measurement ability of singleview similarity, an unsupervised semantic segmentation method for PolSAR images based on multiview similarity is proposed to estimate the number-of-classes (NoC) and perform classification. NoC estimation is commonly neglected in semantic segmentation methods, to ensure rationality, a NoC estimation method before clustering is proposed based on multiview polarimetric rotation domain features and the visual assessment of tendency (VAT) method for PolSAR images without supervision. Then, the norm distance, geodesic distance, maximum likelihood distance and generalized likelihood ratio test distance based on the statistical characteristics of PolSAR images are comprehensively analyzed. Various advantages of different distances are integrated to combine the multiview vector information and scattering information to construct six multi-kernel similarity matrices. Subsequently, the consensus similarity network fusion method is utilized to further strengthen the discriminative ability of the similarity matrices. In addition, efficient superpixel segmentation is also adopted to reduce the speckle noise. Finally, based on the estimated NoC and the fused similarity matrix, spectral clustering is utilized to obtain semantic segmentation results. Extensive experiments conducted on two AIRSAR data sets and one Gaofen-3 data set demonstrate that the proposed method can effectively combine the spatial neighborhood similarity information and achieve higher semantic segmentation accuracy.

show abstract

Section: B Noc Estimation Resultsmentioning

confidence: 99%

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Li,

Zou,

Dong

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, the proposed scheme exhibits excellent change detection performance on five real SAR datasets with significant differences. We would like to further extend the proposed method to other application fields, such as target identification (Tatem et al, 2002) and PolSAR image classification (Zou et al, 2018;Tang et al, 2021), as well as change detection in optical sensor imagery such as Landsat and Sentinel-2 satellite images.…”

Section: Discussionmentioning

confidence: 99%

Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery

Zhang²,

Luo³

et al. 2022

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…Their approach first partitioned the PolSAR image into superpixels, which are local, coherent regions that preserve most of the characteristics necessary for image information extraction, before using the VAT and DBE algorithm for clustering and classification operations. Zou et al [106] proposed an alternate approach to cluster superpixels based on mean Freeman decomposition and hyperspectral-image color feature vectors using the VATdt approach [57], [58] to adaptively estimate the number of terrain classes and automatically capture the cluster structure.…”

Section: Image Processingmentioning

confidence: 99%

Visual Approaches for Exploratory Data Analysis: A Survey of the Visual Assessment of Clustering Tendency (VAT) Family of Algorithms

Kumar

Bezdek

2020

IEEE Syst. Man Cybern. Mag.

View full text Add to dashboard Cite

Superpixel-Based Unsupervised Classification of Polsar Images with Adaptive Number of Terrain Classes

Cited by 6 publications

References 10 publications

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Unsupervised Semantic Segmentation of PolSAR Images Based on Multiview Similarity

Nonlocal feature learning based on a variational graph auto-encoder network for small area change detection using SAR imagery

Visual Approaches for Exploratory Data Analysis: A Survey of the Visual Assessment of Clustering Tendency (VAT) Family of Algorithms

Contact Info

Product

Resources

About