202 Hits in 7.0 sec

Hyperspectral Band Selection via Spatial-Spectral Weighted Region-wise Multiple Graph Fusion-Based Spectral Clustering

Chang Tang, Xinwang Liu, En Zhu, Lizhe Wang, Albert Zomaya
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
In this paper, we propose a hyperspectral band selection method via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering, referred to as RMGF briefly.  ...  Then, a multiple graph diffusion strategy with theoretical convergence guarantee is designed to learn a unified graph for partitioning the whole hyperspectral cube into several subcubes via spectral clustering  ...  Conclusion In this paper, we present a hyperspectral band selection method via spatial-spectral weighted region-wise multiple graph fusion-based spectral clustering (RMGF).  ... 
doi:10.24963/ijcai.2021/418 fatcat:t7dz35ii6zhfhb2j7a4x5gtjhu

An outlook: machine learning in hyperspectral image classification and dimensionality reduction techniques

Tatireddy Reddy, Jonnadula Harikiran
2022 Journal of Spectral Imaging  
As a result, this paper reviews three different types of hyperspectral image machine learning classification methods: cluster analysis, supervised and semi-supervised classification.  ...  Hyperspectral imaging is used in a wide range of applications.  ...  For hyperspectral images, an Expectation-Maximisation (EM) algorithm-based clustering with band fusion is offered by Prabukumar and Shrutika, 76 and a Band Correlation Clustering (BCC)-based feature  ... 
doi:10.1255/jsi.2022.a1 fatcat:rue5klkmlfcrzftepc6lzfcbfe

Machine learning based hyperspectral image analysis: A survey [article]

Utsav B. Gewali, Sildomar T. Monteiro, Eli Saber
2019 arXiv   pre-print
This paper reviews and compares recent machine learning-based hyperspectral image analysis methods published in literature.  ...  regression, support vector machines, Gaussian mixture model, latent linear models, sparse linear models, Gaussian mixture models, ensemble learning, directed graphical models, undirected graphical models, clustering  ...  It has been used primarily for band selection by clustering the bands in an image and selecting a representative band for each cluster [157, 326] .  ... 
arXiv:1802.08701v2 fatcat:bfi6qkpx2bf6bowhyloj2duugu

Spectral and Spatial Classification of Hyperspectral Images Based on Random Multi-Graphs

Feng Gao, Qun Wang, Junyu Dong, Qizhi Xu
2018 Remote Sensing  
In this paper, we propose a spectral and spatial classification framework for hyperspectral images based on Random Multi-Graphs (RMGs).  ...  The RMG is a graph-based ensemble learning method, which is rarely considered in hyperspectral image classification.  ...  IFRF combines spatial and spectral information via image fusion and recursive filtering.  ... 
doi:10.3390/rs10081271 fatcat:onawzc6cyjdyjmxdl4kg32wnoa


S. Srinivasan, Dr. K. Rajakumar
2017 International Journal on Smart Sensing and Intelligent Systems  
The spectral and spatial information reflected from the original Hyperspectral Images with four various features.  ...  A new technique Multiple-feature-based adaptive sparse representation (MFASR) has been demonstrated for Hyperspectral Images (HSI's) classification.  ...  Rajakumar A review on multiple-feature-based adaptive sparse representation (MFASR) and other classification types Figure. 2 . 2 (a) Pixel-wise multiple-feature-based joint sparse model (b) Pixel-wise  ... 
doi:10.21307/ijssis-2017-224 fatcat:k2x24hgfkjctxh3jwjssq5esle

Regularized Sparse Band Selection via Learned Pairwise Agreement

Zhixi Feng, Shuyuan Yang, Xiaolong Wei, Quanwei Gao, Licheng Jiao
2020 IEEE Access  
Desired by sparse subset learning, in this paper, a hyperspectral band selection method via pairwise band agreement with spatial-spectral graph regularier, referred as Regularized Band Selection via Learned  ...  In RBS-LPA, a spatial-spectral informative graph, constructed by spatial-spectral neighbor relationship, is incorporated to encode both the spatial and spectral geometrical structure.  ...  bands are reselected to preserve the graph structure. (4) By incorporating the geometrical information of the data space via constructing a neighbor graph regularizer, we ensure that the spatial spectral  ... 
doi:10.1109/access.2020.2971556 fatcat:72u7qlvq75cpnatvv773xlpxcq

Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization [article]

Chandrajit Bajaj, Tianming Wang
2019 arXiv   pre-print
Fusing a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) of the same scene leads to a super-resolution image (SRI), which is information rich spatially and spectrally  ...  Experiments on various datasets demonstrate the advantages of the proposed algorithm in the quality of fusion and its capability in dealing with unknown spatial degradation.  ...  The spectral degradation from the SRI to the MSI can be modeled by a weighted summation of the hyperspectral bands according to the spectral responses of the multispectral sensor.  ... 
arXiv:1902.08224v1 fatcat:csmycrol5bg3pnvft4tgov6dyq

Diverse-Region Hyperspectral Image Classification via Superpixelwise Graph Convolution Technique

Yan Huang, Xiao Zhou, Bobo Xi, Jiaojiao Li, Jian Kang, Shiyang Tang, Zhanye Chen, Wei Hong
2022 Remote Sensing  
Specifically, the proposed method is operated on non-Euclidean graphs, which are constructed by superpixel segmentation methods for diverse regions to cluster irregularly local-region pixels.  ...  hyperspectral data correctly.  ...  In these years, multiple superpixel-based methods were proposed to extract the spectral-spatial features via segmentation methods [41] [42] [43] [44] .  ... 
doi:10.3390/rs14122907 fatcat:2oeomww76vh2zhuzt4mhxvtuju

Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art

Pedram Ghamisi, Naoto Yokoya, Jun Li, Wenzhi Liao, Sicong Liu, Javier Plaza, Behnood Rasti, Antonio Plaza
2017 IEEE Geoscience and Remote Sensing Magazine  
Recent advances in airborne and spaceborne hyperspectral imaging technology have provided end users with rich spectral, spatial, and temporal information, which make a plethora of applications for the  ...  This paper offers a comprehensive tutorial/overview focusing specifically on hyperspectral data analysis, which is categorized into seven broad topics: classification, spectral unmixing, dimensionality  ...  Technical Committee for organizing the 2013 Data Fusion Contest.  ... 
doi:10.1109/mgrs.2017.2762087 fatcat:6ezzye7yyvacbouduqv2f2c7gi

Semisupervised Hyperspectral Band Selection Via Spectral–Spatial Hypergraph Model

Xiao Bai, Zhouxiao Guo, Yanyang Wang, Zhihong Zhang, Jun Zhou
2015 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
We show that hypergraph can captures relationship among pixels in both spectral and spatial domain.  ...  Band selection is an essential step towards effective and efficient hyperspectral image classification.  ...  This is due to the better measurement of similarities between hyperspectral pixels via capturing of both spectral and spatial relationship between multiple samples. G.  ... 
doi:10.1109/jstars.2015.2443047 fatcat:wxtmoeoke5hobavexp7wdyyns4

A Survey on Superpixel Segmentation as a Preprocessing Step in Hyperspectral Image Analysis

Subhashree Subudhi, Ram Narayan Patro, Pradyut Kumar Biswal, Fabio Dell'Acqua
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Recent developments in hyperspectral sensors have made it possible to acquire HyperSpectral Images (HSI) with higher spectral and spatial resolution.  ...  Because of this, superpixels have been successfully applied to various fields of HSI processing like Classification, Spectral Unmixing, Dimensionality Reduction, Band Selection, Active Learning, Denoising  ...  classification via multiple kernels (SCMK).  ... 
doi:10.1109/jstars.2021.3076005 fatcat:smfb6jeox5eldbv6ys7ioeoko4

Spectral-Spatial Hyperspectral Imagery Classification Using Robust Dual-Stage Spatial Embedding

Peng Shan, Zhenqiang Li, Yi Li, Wentao Fu
2021 IEEE Access  
ERS is a graph-based clustering method that generates superpixels by performing graph partitioning.  ...  The image has a spatial dimension of 145 × 145 and 220 spectral bands with a spatial resolution of 20 m per pixel (20 water absorption bands were removed before experiments).  ... 
doi:10.1109/access.2021.3099631 fatcat:zus2rvnfcvgjnns4chdae7k6wy

2019 Index IEEE Transactions on Geoscience and Remote Sensing Vol. 57

2019 IEEE Transactions on Geoscience and Remote Sensing  
., Insect Biological Parameter Estimation Based on the Invariant Target Parameters of the Scattering Matrix; TGRS Aug. 2019 6212-6225 Hu, C., see Zhang, M., TGRS Sept. 2019 6666-6674 Hu, C., Zhang,  ...  Incorporating Temporary Coherent Li, X., Yeo, T.S., Yang, Y., Chi, C., Zuo, F., Hu, X., and Pi, Y., Refo-cusing and Zoom-In Polar Format Algorithm for Curvilinear Spotlight SAR Imaging on Arbitrary Region  ...  ., +, TGRS May 2019 2741-2753 Multiple-Feature Kernel-Based Probabilistic Clustering for Unsupervised Band Selection.  ... 
doi:10.1109/tgrs.2020.2967201 fatcat:kpfxoidv5bgcfo36zfsnxe4aj4

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Shengliang Pu, Yuanfeng Wu, Xu Sun, Xiaotong Sun
2021 Remote Sensing  
In this regard, we present a novel method that performs the localized graph convolutional filtering on HSIs based on spectral graph theory.  ...  Compared to conventional convolutional neural networks, graph-based deep learning has the advantages of illustrating class boundaries and modeling feature relationships.  ...  a graph-based model considering both spatial and spectral information [46] .  ... 
doi:10.3390/rs13030526 fatcat:y7bp3lgrazdtlclamfdqpgdhfe

Data Augmentation and Spectral Structure Features for Limited Samples Hyperspectral Classification

Wenning Wang, Xuebin Liu, Xuanqin Mou
2021 Remote Sensing  
Second, an effective spectral structure extraction method is designed, and the effective spectral structure features have a better classification accuracy than the true spectral features.  ...  First, the unsupervised data augmentation for all hyperspectral samples not only improves the classification accuracy greatly with the newly added training samples, but also further improves the classification  ...  (c) RVCANET, (d), hyperspectral images based on random multi-graphs (HC-RMG), (e), spectral-spatial hyperspectral classification via structural-kernel collaborative representation (SKCR) (f) HS_AGU, and  ... 
doi:10.3390/rs13040547 fatcat:dlyfs4fxj5bcpknnoxku4z6rjy
« Previous Showing results 1 — 15 out of 202 results