Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

Zhang, Yaokang; Chen, Yunjie

doi:10.3390/rs13040820

Cited by 6 publications

(3 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that H 1 ∈ R m×m is the pre-calculated superpixel spatial weighting matrix, and H 2 ∈ R m×n is the spatial neighborhood weighting matrix. As stated earlier, superpixel segmentation technology [43,50] refers to a method utilized for extracting spatial information from hyperspectral images. This technique allows for the analysis and characterization of the spatial structure within the image.…”

Section: Proposed Rdswsu Methodsmentioning

confidence: 99%

Robust Dual Spatial Weighted Sparse Unmixing for Remotely Sensed Hyperspectral Imagery

et al. 2023

View full text Add to dashboard Cite

Sparse unmixing plays a crucial role in the field of hyperspectral image unmixing technology, leveraging the availability of pre-existing endmember spectral libraries. In recent years, there has been a growing trend in incorporating spatial information from hyperspectral images into sparse unmixing models. There is a strong spatial correlation between pixels in hyperspectral images (that is, the spatial information is very rich), and many sparse unmixing algorithms take advantage of this to improve the sparse unmixing effect. Since hyperspectral images are susceptible to noise, the feature separability of ground objects is reduced, which makes most sparse unmixing methods and models face the risk of degradation or even failure. To address this challenge, a novel robust dual spatial weighted sparse unmixing algorithm (RDSWSU) has been proposed for hyperspectral image unmixing. This algorithm effectively utilizes the spatial information present in the hyperspectral images to mitigate the impact of noise during the unmixing process. For the proposed RDSWSU algorithm, which is based on ℓ1 sparse unmixing framework, a pre-calculated superpixel spatial weighting factor is used to smooth the noise, so as to maintain the original spatial structure of hyperspectral images. The RDSWSU algorithm, which builds upon the ℓ1 sparse unmixing framework, employs a pre-calculated spatial weighting factor at the superpixel level. This factor aids in noise smoothing and helps preserve the inherent spatial structure of hyperspectral images throughout the unmixing process. Additionally, another spatial weighting factor is utilized in the RDSWSU algorithm to capture the local smoothness of abundance maps at the sub-region level. This factor helps enhance the representation of piecewise smooth variations within different regions of the hyperspectral image. Specifically, the combination of these two spatial weighting factors in the RDSWSU algorithm results in an enhanced sparsity of the abundance matrix. The RDSWSU algorithm, which is a sparse unmixing model, offers an effective solution using the alternating direction method of multiplier (ADMM) with reduced requirements for tuning the regularization parameter. The proposed RDSWSU method outperforms other advanced sparse unmixing algorithms in terms of unmixing performance, as demonstrated by the experimental results on synthetic and real hyperspectral datasets.

show abstract

Section: Proposed Rdswsu Methodsmentioning

confidence: 99%

Robust Dual Spatial Weighted Sparse Unmixing for Remotely Sensed Hyperspectral Imagery

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Calculate the E(S i ) through Equation ( 23); 10: end for 11: Determine the final fusion scale pool S F by Equation (24); 12: Create multiple graphical models of S F by Equation (26) . 13: Fuse multiple scale maps to obtain the final classification result by Equations ( 27) and (28).…”

Section: A Pixel-level Fusion Strategy For Multiple Graphical Modelsmentioning

confidence: 99%

“…Recently, superpixel (SP) segmentation has been widely applied to HSIC [26,27]. SP-based methods can generate an irregular homogeneous region with similar spatial information [28,29].…”

Section: Introductionmentioning

confidence: 99%

Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification

et al. 2022

View full text Add to dashboard Cite

Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a pixel-wise way. Therefore, how to overcome the problem of insufficient accuracy and stability under the condition of small labeled training sample size (SLTSS) is still a challenge for HSIC. In this paper, we proposed a novel multiple superpixel graphs learning method based on adaptive multiscale segmentation (MSGLAMS) for HSI classification to address this problem. First, the multiscale-superpixel-based framework can reduce the adverse effect of improper selection of a superpixel segmentation scale on the classification accuracy while saving the cost to manually seek a suitable segmentation scale. To make full use of the superpixel-level spatial information of different segmentation scales, a novel two-steps multiscale selection strategy is designed to adaptively select a group of complementary scales (multiscale). To fix the bias and instability of a single model, multiple superpixel-based graphical models obatined by constructing superpixel contracted graph of fusion scales are developed to jointly predict the final results via a pixel-level fusion strategy. Experimental results show that the proposed MSGLAMS has better performance when compared with other state-of-the-art algorithms. Specifically, its overall accuracy achieves 94.312%, 99.217% ,98.373% and 92.693% on Indian Pines, Salinas and University of Pavia, and the more challenging dataset Houston2013, respectively.

show abstract

Multi-scale superpixel-based nearest subspace classifier for mucilage detection from hyperspectral PRISMA data

Toker,

Yuksel

2024

Digital Signal Processing

View full text Add to dashboard Cite

Multiscale Weighted Adjacent Superpixel-Based Composite Kernel for Hyperspectral Image Classification

Cited by 6 publications

References 58 publications

Robust Dual Spatial Weighted Sparse Unmixing for Remotely Sensed Hyperspectral Imagery

Robust Dual Spatial Weighted Sparse Unmixing for Remotely Sensed Hyperspectral Imagery

Multiple Superpixel Graphs Learning Based on Adaptive Multiscale Segmentation for Hyperspectral Image Classification

Multi-scale superpixel-based nearest subspace classifier for mucilage detection from hyperspectral PRISMA data

Contact Info

Product

Resources

About