1,281 Hits in 10.0 sec

Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing [article]

Danfeng Hong and Wei He and Naoto Yokoya and Jing Yao and Lianru Gao and Liangpei Zhang and Jocelyn Chanussot and Xiao Xiang Zhu
2021 arXiv   pre-print
Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS).  ...  be a feasible solution to reduce the gap between challenging HS vision tasks and currently advanced intelligent data processing models.  ...  We focus on the non-convex low-rank regularizer of original image X .  ... 
arXiv:2103.01449v1 fatcat:jvo4pr5atvfb5kohpslvkhhmky

Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometry [article]

Lucas Drumetz, Jocelyn Chanussot, Christian Jutten, Wing-Kin Ma, Akira Iwasaki
2019 arXiv   pre-print
Hyperspectral image unmixing has proven to be a useful technique to interpret hyperspectral data, and is a prolific research topic in the community.  ...  A natural question is to wonder to what extent these concepts and tools (Intrinsic Dimensionality estimation, endmember extraction algorithms, pixel purity) can be safely used in these different scenarios  ...  In the vast majority of the studies on hyperspectral unmixing, a linear mixing model (LMM) is assumed.  ... 
arXiv:1904.03888v1 fatcat:5z37qadx5rbnxfnoxfriwbieqm

Hyperspectral Anomaly Detection Based on Improved RPCA with Non-Convex Regularization

Wei Yao, Lu Li, Hongyu Ni, Wei Li, Ran Tao
2022 Remote Sensing  
On this basis, we propose a non-convex regularized approximation model based on low-rank and sparse matrix decomposition (LRSNCR), which is closer to the original problem than RPCA.  ...  A general approach is to relax the ℓ0 operator to ℓ1-norm in the traditional RPCA model, so as to approximately transform it to the convex optimization field.  ...  Institutional Review Board Statement: Not applicable. Informed Consent Statement: Not applicable. Data Availability Statement: Not applicable.  ... 
doi:10.3390/rs14061343 fatcat:maeidcly2vcepj5m22fskkwn7m

Complexity Reduction By Convex Cone Detection For Unmixing Hyperspectral Images Of Bacterial Biosensors

Patrick Billard, David Brie, Fabrice Caland, Sebastian Miron, Christian Mustin, Charles Soussen
2009 Zenodo  
Publication in the conference proceedings of EUSIPCO, Glasgow, Scotland, 2009  ...  This forbids the use of a source separation algorithm utilizing a spatial regularization on the weight coefficients (e.g., the weight of each source is constrained to be a piecewise constant image).  ...  In Fig. 2 (a) , the image equal to the sum of the 16 hyperspectral images (in which the gray level of the i-th pixel is equal to ∑ N j=1 x i ( j)) is shown.  ... 
doi:10.5281/zenodo.41587 fatcat:k277teegmzhy3ppdg2auf67zra

A Convex Model for Nonnegative Matrix Factorization and Dimensionality Reduction on Physical Space

E. Esser, M. Moller, S. Osher, G. Sapiro, J. Xin
2012 IEEE Transactions on Image Processing  
We use l_1,∞ regularization to select the dictionary from the data and show this leads to an exact convex relaxation of l_0 in the case of distinct noise free data.  ...  We also show how to relax the restriction-to-X constraint by initializing an alternating minimization approach with the solution of the convex model, obtaining a dictionary close to but not necessarily  ...  Model outlier error by −X s diag(e) • Non-outlier case: want e j ≈ 0 • Outlier case: want e j ≈ 1, in which case regularization on T encourages corresponding column of T to be small Restrict e to the convex  ... 
doi:10.1109/tip.2012.2190081 pmid:22410332 fatcat:zzwubycbabaytgxcb36o3gbdsm

Discussion: Latent variable graphical model selection via convex optimization

Emmanuel J. Candés, Mahdi Soltanolkotabi
2012 Annals of Statistics  
Discussion of "Latent variable graphical model selection via convex optimization" by Venkat Chandrasekaran, Pablo A. Parrilo and Alan S. Willsky [arXiv:1008.1290].  ...  (Variants are possible depending upon whether or not one would want to penalize the diagonal elements.) This problem is convex.  ...  To explain our ideas, it might be best to start with two concrete examples. Suppose we are interested in the e cient acquisition of either 1) a hyper-spectral image or 2) a video sequence.  ... 
doi:10.1214/12-aos1001 fatcat:2baqfaw6srcj5eltiv73ucln7q

Anomaly Detection Based on Convex Analysis: A Survey

Tong Wang, Mengsi Cai, Xiao Ouyang, Ziqiang Cao, Tie Cai, Xu Tan, Xin Lu
2022 Frontiers in Physics  
Convex analysis (CA) is one of the fundamental methods used in anomaly detection, which contributes to the robust approximation of algebra and geometry, efficient computation to a unique global solution  ...  As a crucial technique for identifying irregular samples or outlier patterns, anomaly detection has broad applications in many fields.  ...  ) In Eq. 12, a quadratic regularization term λ 2 β T β is added, instead of the linear one λ1 T b β, since the linear penalty term can not work as a regularizer without the non-negativity constraint.  ... 
doi:10.3389/fphy.2022.873848 fatcat:ooxtghts5ffoxmu2qx743ij3eq

Nonconvex Regularization in Remote Sensing

Devis Tuia, Remi Flamary, Michel Barlaud
2016 IEEE Transactions on Geoscience and Remote Sensing  
In this paper, we study the effect of different regularizers and their implications in high dimensional image classification and sparse linear unmixing.  ...  Although kernelization or sparse methods are globally accepted solutions for processing data in high dimensions, we present here a study on the impact of the form of regularization used and its parametrization  ...  Then, in Section III, we apply the proposed nonconvex regularizers to the problem of multiand hyperspectral image classification and therefore present the specific data term for classification and study  ... 
doi:10.1109/tgrs.2016.2585201 fatcat:zrokmneykfgdhdoe3hld2rn52q

Hyperspectral Unmixing via Non-Convex Sparse and Low-Rank Constraint with Dictionary Pruning

Hongwei Han, Guxi Wang, Wang Maozhi, Jiaqing Miao, Si Guo, Ling Chen, Mingyue Zhang, Ke Guo
2020 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
In this study, adopting combined constraints imposing sparsity and low rankness, a novel algorithm called non-convex joint-sparsity and low-rank unmixing with dictionary pruning (NCJSpLRUDP) is developed  ...  in hyperspectral scenes.  ...  In a hyperspectral image, the joint-sparsity constraint [36] provides a more general assumption that neighboring pixels are composed of similar endmembers but do not necessarily have similar abundance  ... 
doi:10.1109/jstars.2020.3021520 fatcat:qc2j66c4nfektmg237rx7742rq

Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization [article]

Chong Peng, Yang Liu, Yongyong Chen, Xinxin Wu, Andrew Cheng, Zhao Kang, Chenglizhao Chen, Qiang Cheng
2022 arXiv   pre-print
In this paper, we propose a novel nonconvex approach to robust principal component analysis for HSI denoising, which focuses on simultaneously developing more accurate approximations to both rank and column-wise  ...  In particular, the new method adopts the log-determinant rank approximation and a novel ℓ_2,log norm, to restrict the local low-rank or column-wisely sparse properties for the component matrices, respectively  ...  Grants 61806106, 61802215, and 61806045, and Natural Science Foundation of Shandong Province under Grants ZR2019QF009 and ZR2019BF011; Q.C. is partially supported by NIH R21AG070909, UH3 NS100606-03 and a  ... 
arXiv:2201.02812v1 fatcat:vblvx553wzahzcgjeho66nzr3q

Convex Regularization for High-Dimensional Multi-Response Tensor Regression [article]

Garvesh Raskutti, Ming Yuan, Han Chen
2017 arXiv   pre-print
Our framework leads to upper bounds in terms of two very simple quantities, the Gaussian width of a convex set in tensor space and the intrinsic dimension of the low-dimensional tensor subspace.  ...  We consider using convex and weakly decomposable regularizers assuming that the underlying tensor lies in an unknown low-dimensional subspace.  ...  Examples include hyperspectral image analysis (Li and Li, 2010) , multi-energy computed tomography (Semerci et al., 2014) , radar signal processing (Sidiropoulos and Nion, 2010) , audio classification  ... 
arXiv:1512.01215v2 fatcat:gw64xghfbvgkrpjblgnjpo5qqm

Ordering on the Probability Simplex of Endmembers for Hyperspectral Morphological Image Processing [chapter]

Gianni Franchi, Jesús Angulo
2015 Lecture Notes in Computer Science  
This leads to the characterization of a hyperspectral image as a set of points in a probability simplex.  ...  A hyperspectral image can be represented as a set of materials called endmembers, where each pixel corresponds to a mixture of several of these materials.  ...  Basically, we compare the result of the supervised spectral classification obtained on the original hyperspectral image or the hyperspectral image filtered by a sequential filter according to one of the  ... 
doi:10.1007/978-3-319-18720-4_35 fatcat:l34p2uoqqbg6likriupicpsvty

A regularized sparse approximation method for hyperspectral image classification

Leila Belmerhnia, El-Hadi Djermoune, David Brie, Cedric Carteret
2016 2016 IEEE Statistical Signal Processing Workshop (SSP)  
A regularized sparse approximation method for hyperspectral image classification.  ...  This approach is applied to a wood wastes classification problem using NIR hyperspectral images.  ...  At low SNR, the value of the regularization parameter λ 2 has to be increased in order to achieve a minimum classification error as shown in Figure 5 .  ... 
doi:10.1109/ssp.2016.7551846 dblp:conf/ssp/BelmerhniaDBC16 fatcat:2sbst4ps2jdfreouybf2ybye4u

An Overview on Linear Unmixing of Hyperspectral Data

Jiaojiao Wei, Xiaofei Wang
2020 Mathematical Problems in Engineering  
A single pixel that leads to a hyperspectral remote sensing image usually contains more than one feature coverage type, resulting in a mixed pixel.  ...  Hyperspectral remote sensing technology has a strong capability for ground object detection due to the low spatial resolution of hyperspectral imaging spectrometers.  ...  hyperspectral image where a standard algorithm could not be used due to memory limitations.  ... 
doi:10.1155/2020/3735403 fatcat:ijkjzzp6lbavhfhkyx7rwnxngy

Hyperspectral Image Database Query Based on Big Data Analysis Technology

Beixun Qi, F. Wen, S.M. Ziaei
2021 E3S Web of Conferences  
In this paper, we extract spectral image features from a hyperspectral image database, and use big data technology to classify spectra hierarchically, to achieve the purpose of efficient database matching  ...  The experimental results show that the hyperspectral images of color hyperspectral images are highly consistent and indistinguishable, and need to be processed by the machine learning algorithm.  ...  On the one hand, most of the area in the input image corresponds to the sky or land, so without saliency detection, the color theme extracted directly must be the sky and land, not the spectrum itself.  ... 
doi:10.1051/e3sconf/202127503018 fatcat:visz74utsjernecda3ewutqjhq
« Previous Showing results 1 — 15 out of 1,281 results