- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Constrained Nonnegative Tensor Factorization for Spectral Unmixing of Hyperspectral Images: A Case Study of Urban Impervious Surface Extraction
摘要： In recent years, a new genre of hyperspectral unmixing methods based on nonnegative matrix factorization (NMF) have been proposed. Unlike traditional spectral unmixing methods, the NMF-based hyperspectral unmixing methods no longer depend on pure pixels in the original image. The NMF is based on linear algebra, which requires that the hyperspectral data cube is converted from 3-D cube to a 2-D matrix. Due to this conversion, the spatial information in the relative positions of the pixels is lost. With the emergence of multilinear algebra, the tensorial representation of hyperspectral imagery that preserves spectral and spatial information has become popular. The tensor-based spectral unmixing was first realized in 2017 using the matrix-vector nonnegative tensor factorization (MVNTF) decomposition. Using the construction of MVNTF spectral unmixing, this letter proposes to integrate three additional constraints (sparseness, volume, and nonlinearity) to the cost function. As we show in this letter, we found that the three constraints greatly improved the impervious surface area fraction/classification results. The constraints also shortened the processing time.
关键词： hyperspectral imagery,spectral unmixing,Constraints,nonnegative tensor factorization
更新于2025-09-23 15:22:29
-
Analysis of High-Temperature Carrier Transport Mechanisms for High Al-Content Al <sub/>0.6</sub> Ga <sub/>0.4</sub> N MSM Photodetectors
摘要： We propose a generative model for robust tensor factorization in the presence of both missing data and outliers. The objective is to explicitly infer the underlying low-CANDECOMP/PARAFAC (CP)-rank tensor capturing the global information and a sparse tensor capturing the local information (also considered as outliers), thus providing the robust predictive distribution over missing entries. The low-CP-rank tensor is modeled by multilinear interactions between multiple latent factors on which the column sparsity is enforced by a hierarchical prior, while the sparse tensor is modeled by a hierarchical view of Student-t distribution that associates an individual hyperparameter with each element independently. For model inference under a fully Bayesian treatment, which can effectively prevent the overfitting problem and scales linearly with data size. In contrast to existing related works, our method can perform model selection automatically and implicitly without the need of tuning parameters. More specifically, it can discover the groundtruth of CP rank and automatically adapt the sparsity inducing priors to various types of outliers. In addition, the tradeoff between the low-rank approximation and the sparse representation can be optimized in the sense of maximum model evidence. The extensive experiments and comparisons with many state-of-the-art algorithms on both synthetic and real-world data sets demonstrate the superiorities of our method from several perspectives.
关键词： tensor factorization,robust factorization,tensor completion,video background modeling,variational Bayesian (VB) inference,Rank determination
更新于2025-09-23 15:21:01
-
[IEEE 2019 International Conference on Communication and Electronics Systems (ICCES) - Coimbatore, India (2019.7.17-2019.7.19)] 2019 International Conference on Communication and Electronics Systems (ICCES) - Saturation Optimization and Extrinsic Timing Analysis for Optically Controlled GFET
摘要： We propose a generative model for robust tensor factorization in the presence of both missing data and outliers. The objective is to explicitly infer the underlying low-CANDECOMP/PARAFAC (CP)-rank tensor capturing the global information and a sparse tensor capturing the local information (also considered as outliers), thus providing the robust predictive distribution over missing entries. The low-CP-rank tensor is modeled by multilinear interactions between multiple latent factors on which the column sparsity is enforced by a hierarchical prior, while the sparse tensor is modeled by a hierarchical view of Student-t distribution that associates an individual hyperparameter with each element independently. For model inference under a fully Bayesian treatment, which can effectively prevent the overfitting problem and scales linearly with data size. In contrast to existing related works, our method can perform model selection automatically and implicitly without the need of tuning parameters. More specifically, it can discover the groundtruth of CP rank and automatically adapt the sparsity inducing priors to various types of outliers. In addition, the tradeoff between the low-rank approximation and the sparse representation can be optimized in the sense of maximum model evidence. The extensive experiments and comparisons with many state-of-the-art algorithms on both synthetic and real-world data sets demonstrate the superiorities of our method from several perspectives.
关键词： tensor factorization,video background modeling,variational Bayesian (VB) inference,tensor completion,Rank determination,robust factorization
更新于2025-09-19 17:13:59
-
Coupled Higher-Order Tensor Factorization for Hyperspectral and LiDAR Data Fusion and Classification
摘要： Hyperspectral and light detection and ranging (LiDAR) data fusion and classi?cation has been an active research topic, and intensive studies have been made based on mathematical morphology. However, matrix-based concatenation of morphological features may not be so distinctive, compact, and optimal for classi?cation. In this work, we propose a novel Coupled Higher-Order Tensor Factorization (CHOTF) model for hyperspectral and LiDAR data classi?cation. The innovative contributions of our work are that we model different features as multiple third-order tensors, and we formulate a CHOTF model to jointly factorize those tensors. Firstly, third-order tensors are built based on spectral-spatial features extracted via attribute pro?les (APs). Secondly, the CHOTF model is de?ned to jointly factorize the multiple higher-order tensors. Then, the latent features are generated by mode-n tensor-matrix product based on the shared and unshared factors. Lastly, classi?cation is conducted by using sparse multinomial logistic regression (SMLR). Experimental results, conducted with two popular hyperspectral and LiDAR data sets collected over the University of Houston and the city of Trento, respectively, indicate that the proposed framework outperforms the other methods, i.e., different dimensionality-reduction-based methods, independent third-order tensor factorization based methods, and some recently proposed hyperspectral and LiDAR data fusion and classi?cation methods.
关键词： attribute pro?les,classi?cation,hyperspectral remote sensing image (HSI),data fusion,light detection and ranging (LiDAR),coupled tensor factorization
更新于2025-09-19 17:13:59
-
[Paper] A 3-D Display Pipeline: Capture, Factorize, and Display the Light Field of a Real 3-D Scene
摘要： Inspired by pioneering work on modern light field displays, we developed a prototype display in which three liquid crystal display (LCD) panels are stacked in front of a backlight. The stacked LCD panels constitute a set of semi-transparent layers, which modulate the out-going light rays. Even though only three layers are used, this display can emit a light field, i.e., a dense set of many multi-view images, in different viewing directions simultaneously. We established a process pipeline from capture to display of the light field of a real 3-D scene. We analyzed the amount of pop-out and motion parallax that can be presented by the display using a given light field data. We used a light field camera (Lytro Illum) and a multi-view camera (ViewPLUS ProFUSIOIN 25) to capture the light field, which was then factorized into layer representations to be displayed. We show several successful results using our prototype display.
关键词： light field,non-negative tensor factorization,image based rendering,3-D display,light field camera
更新于2025-09-04 15:30:14