Fast Spatial Preprocessing for Spectral Unmixing of Hyperspectral Data on Graphics Processing Units

Delgado, Jaime; Martín, Gabriel; Plaza, Javier; Jiménez, Luis Ignacio

doi:10.1109/jstars.2015.2495128

Cited by 17 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fast-growing video game industry exerts strong economic pressure for constant innovation. This has motivated the extended use of GPUs for accelerating many different hyperspectral imaging related tasks [317,[325][326][327][328][329][330][331][332][333][334][335][336].…”

Section: B Hardware Acceleratorsmentioning

confidence: 99%

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

Ghamisi

Yokoya

et al. 2017

IEEE Geosci. Remote Sens. Mag.

Self Cite

632

266

View full text Add to dashboard Cite

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 analysis of large areas of the Earth surface feasible. However, a huge number of factors, such as high dimensions and size of the hyperspectral data, the lack of training samples, mixed pixels, light scattering mechanisms in the acquisition process, and different atmospheric and geometric distortions, make such data inherently nonlinear and complex, which poses extreme challenges for existing methodologies to effectively process and analyze the data sets. Hence, rigorous and innovative methodologies are required for hyperspectral image and signal processing and have become a center of attention for researchers worldwide. This paper offers a comprehensive tutorial/overview focusing specifically on hyperspectral data analysis, which is categorized into seven broad topics: classification, spectral unmixing, dimensionality reduction, resolution enhancement, hyperspectral image denoising and restoration, change detection, and fast computing. For each topic, we provide a synopsis of the state-of-the-art approaches and numerical results for validation and evaluation of different methodologies, followed by a discussion of future challenges and research directions.

show abstract

Section: B Hardware Acceleratorsmentioning

confidence: 99%

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

Ghamisi

Yokoya

et al. 2017

IEEE Geosci. Remote Sens. Mag.

Self Cite

632

266

View full text Add to dashboard Cite

show abstract

“…) ( denotes the value for the i-th row and j-th column of the matrix. More details of this process can be found in [29].…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, Sevilla et al [28] presented a new, computationally efficient content-based image retrieval system for hyperspectral data, which uses sparse unmixing concepts to retrieve hyperspectral scenes based on their content. Delgado et al [29] presented parallel implementations of spatial preprocessing that have been specifically developed for commodity graphics processing units.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Unmixing Based on Adaptive Region Segmentation for Hyperspectral Imagery

Zhang

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Unmixing is an important issue of hyperspectral images. Most unmixing methods adopt linear mixing models for simplicity. However, multiple scattering usually occurs between vegetation and soil in a bilinear scene. Thus, non-linear mixing problems which are difficult to be solved should be taken into consideration under this circumstance. In practice, both linear and non-linear spectral mixtures exist in hyperspectral scenes. Considering the characteristics of different regions in images, we propose a hybrid unmixing algorithm for hyperspectral images based on region adaptive segmentation (RASU). Our method uses a standard K-means clustering algorithm to obtain different regions, including homogeneous regions and detailed regions. The model of the homogeneous regions is assumed to be linear, which will be pursued using the method of sparse constrained non-negative matrix factorization (SNMF), and the mixing in the detailed regions is assumed to be based on a non-linear model. We also propose a new non-linear unmixing method, called graph regularized semi-nonnegative matrix factorization (GNMF), which considers the manifold structure of hyperspectral data as the unmixing method to deal with the detailed regions. Finally, by combining the two regions, we obtain the abundance of the whole hyperspectral image. The proposed method cannot only achieve more precise abundance, but also be good at keeping the edge information of the bilinear abundance. The experimental results on both synthetic and real data also show that the proposed method is effective for improving the unmixing accuracy of hyperspectral remote sensing images.

show abstract

“…Spectral unmixing is a significant technique for addressing this challenge [10][11][12][13][14]. In the available literature, spectral unmixing techniques [15][16][17] have been comprehensively investigated for the purpose of extracting endmembers and estimating their corresponding abundances, allowing for the processing of HSI scenes at the sub-pixel scale [18]. In fact, these techniques decompose each mixed pixel into a proportional composition of endmembers, where the constituent proportion with respect to different types of materials [19] for each pixel is defined as the abundance.…”

Section: Introductionmentioning

confidence: 99%

Endmember Estimation with Maximum Distance Analysis

et al. 2021

Self Cite

View full text Add to dashboard Cite

Endmember estimation plays a key role in hyperspectral image unmixing, often requiring an estimation of the number of endmembers and extracting endmembers. However, most of the existing extraction algorithms require prior knowledge regarding the number of endmembers, being a critical process during unmixing. To bridge this, a new maximum distance analysis (MDA) method is proposed that simultaneously estimates the number and spectral signatures of endmembers without any prior information on the experimental data containing pure pixel spectral signatures and no noise, being based on the assumption that endmembers form a simplex with the greatest volume over all pixel combinations. The simplex includes the farthest pixel point from the coordinate origin in the spectral space, which implies that: (1) the farthest pixel point from any other pixel point must be an endmember, (2) the farthest pixel point from any line must be an endmember, and (3) the farthest pixel point from any plane (or affine hull) must be an endmember. Under this scenario, the farthest pixel point from the coordinate origin is the first endmember, being used to create the aforementioned point, line, plane, and affine hull. The remaining endmembers are extracted by repetitively searching for the pixel points that satisfy the above three assumptions. In addition to behaving as an endmember estimation algorithm by itself, the MDA method can co-operate with existing endmember extraction techniques without the pure pixel assumption via generalizing them into more effective schemes. The conducted experiments validate the effectiveness and efficiency of our method on synthetic and real data.

show abstract

Fast Spatial Preprocessing for Spectral Unmixing of Hyperspectral Data on Graphics Processing Units

Cited by 17 publications

References 17 publications

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

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

Hybrid Unmixing Based on Adaptive Region Segmentation for Hyperspectral Imagery

Endmember Estimation with Maximum Distance Analysis

Contact Info

Product

Resources

About