Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Pu, Shengliang; Wu, Yuanfeng; Sun, Xingming; Sun, Xiaotong

doi:10.3390/rs13030526

Cited by 18 publications

(9 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2 Wireless Communications and Mobile Computing recommendations. Also, users expect recommendation algorithms to discover their potential sides and surprise them [20] (3) Privacy and security issues. Recommendation systems have such a contradictory problem.…”

Section: Related Workmentioning

confidence: 99%

Research on the Spectral Domain Graph Convolution Collaborative Filtering Algorithm Based on Reinforcement Learning and Chebyshev

Wang

Zeng

Song

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

To solve the abovementioned problem, we propose a collaborative filtering recommendation algorithm that incorporates singular value decomposition (SVD) and Chebyshev truncation in spectral domain convolution. Firstly, the SVD algorithm is used to optimize the adjacency matrix, mine the potential association information between users and items, and expand the user-item adjacency matrix. Finally, based on the MovieLens-1M public dataset, the proposed algorithm (CBSVD-SCF) is compared with other commonly used algorithms. The results show that the article optimizes the recommendation effect of the algorithm based on the traditional collaborative filtering algorithm by combining the temporal order and sequence of user interaction information, as well as the popularity of items and the activity of users; the experimental results on MovieLens show that the optimized collaborative filtering recommendation algorithm can effectively improve the recommendation effect.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on the Spectral Domain Graph Convolution Collaborative Filtering Algorithm Based on Reinforcement Learning and Chebyshev

Wang

Zeng

Song

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Qin et al [22] extended the GCNs by considering spatial and spectral neighbors. Pu et al [23] proposed a localized graph convolutional filtering-based GCNs method for hyper-spectral image classification. Traditional GCNs are computationally expensive because the spatial matrices are constructed.…”

Section: An Overview Of Cloud Detection Approachesmentioning

confidence: 99%

Cloud Detection Using an Ensemble of Pixel-Based Machine Learning Models Incorporating Unsupervised Classification

Lary

2021

Remote Sensing

View full text Add to dashboard Cite

Remote sensing imagery, such as that provided by the United States Geological Survey (USGS) Landsat satellites, has been widely used to study environmental protection, hazard analysis, and urban planning for decades. Clouds are a constant challenge for such imagery and, if not handled correctly, can cause a variety of issues for a wide range of remote sensing analyses. Typically, cloud mask algorithms use the entire image; in this study we present an ensemble of different pixel-based approaches to cloud pixel modeling. Based on four training subsets with a selection of different input features, 12 machine learning models were created. We evaluated these models using the cropped LC8-Biome cloud validation dataset. As a comparison, Fmask was also applied to the cropped scene Biome dataset. One goal of this research is to explore a machine learning modeling approach that uses as small a training data sample as possible but still provides an accurate model. Overall, the model trained on the sample subset (1.3% of the total training samples) that includes unsupervised Self-Organizing Map classification results as an input feature has the best performance. The approach achieves 98.57% overall accuracy, 1.18% cloud omission error, and 0.93% cloud commission error on the 88 cropped test images. By comparison to Fmask 4.0, this model improves the accuracy by 10.12% and reduces the cloud omission error by 6.39%. Furthermore, using an additional eight independent validation images that were not sampled in model training, the model trained on the second largest subset with an additional five features has the highest overall accuracy at 86.35%, with 12.48% cloud omission error and 7.96% cloud commission error. This model’s overall correctness increased by 3.26%, and the cloud omission error decreased by 1.28% compared to Fmask 4.0. The machine learning cloud classification models discussed in this paper could achieve very good performance utilizing only a small portion of the total training pixels available. We showed that a pixel-based cloud classification model, and that as each scene obviously has unique spectral characteristics, and having a small portion of example pixels from each of the sub-regions in a scene can improve the model accuracy significantly.

show abstract

“…Through randomly sampling from the labelled data of each category, large numbers of small‐size graphs are constructed, which can obtain an enormous quantity of graphs and be conducive to the full learning of the HSI features. Again, there are also some other references on the HSI classification based on GCN, such as HSI classification with localized graph convolutional filtering [48], non‐local GCN for HSI classification [49], and global consistent GCN for HSI classification [50]. Although these methods improve the classification performance of HSI, they could not extract topological information and pixel‐level information at the same time, which limits the further improvement of classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

CNN‐combined graph residual network with multilevel feature fusion for hyperspectral image classification

Guo

Liu

et al. 2021

IET Computer Vision

View full text Add to dashboard Cite

The application of graph convolutional networks (GCN) in hyperspectral image (HSI) classification has become a promising method, thanks to its flexible convolution operation in any irregular image region. For the classification of HSI, GCN can extract more superpixel‐level features with a topological structure, in comparison to the traditional convolutional neural networks (CNNs) using fixed square kernels distilling pixel‐level features. To fully leverage the different levels of features, this study proposes a novel deep network referred to as a CNN‐combined graph residual network (normalC2GRN), which integrates the multilevel graph residual module and spectral‐spatial features continuous learning module. During the extraction of topology information using the former module, HSI pixels are divided into superpixels and served as input nodes of the module to reduce the computational complexity and obtain the multilevel spatial relevance between adjacent superpixels. Besides, for the latter module, the spectral‐spatial features are learnt continuously, which could obtain the finer pixel‐level features. Finally, the captured spectral‐spatial features of different levels are concatenated. This strategy could not only adequately utilize the correlation and difference of adjacent spatial but also obtain the finer and more valuable spectral‐spatial information, which makes a significant boost in the HSI classification. Additionally, the experiment results demonstrate the superiority and availability of the normalC2GRN on three benchmark datasets of HSI, compared with the state‐of‐the‐art methods for the classification of HSI.

show abstract

Hyperspectral Image Classification with Localized Graph Convolutional Filtering

Cited by 18 publications

References 57 publications

Research on the Spectral Domain Graph Convolution Collaborative Filtering Algorithm Based on Reinforcement Learning and Chebyshev

Research on the Spectral Domain Graph Convolution Collaborative Filtering Algorithm Based on Reinforcement Learning and Chebyshev

Cloud Detection Using an Ensemble of Pixel-Based Machine Learning Models Incorporating Unsupervised Classification

CNN‐combined graph residual network with multilevel feature fusion for hyperspectral image classification

Contact Info

Product

Resources

About