Hyperspectral Image Classification Based on Sparse Superpixel Graph

Zhao, Yifei; Yan, Fengqin

doi:10.3390/rs13183592

Cited by 7 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further demonstrate the advantages of our model, we compare it with advanced methods in recent years on the Pavia University and Salinas datasets, namely MSAGE-Cal [52], MSSUG [53], SSG [50], SSPGAT [51], and MARP [18], respectively. Several algorithms mentioned above incorporate multi-feature fusion techniques.…”

Section: Comparison With Various Graph-based Modelsmentioning

confidence: 99%

“…However, the existing HSIs based on graph convolution present two problems. On the one hand, multi-feature fusion can indeed improve HSI classification accuracy [18,50,51], but few algorithms consider combining the multi-view information of HSIs. For instance, a multi-scale graph sample and aggregate network with context-aware learning (MSAGE-Cal) [52] integrates multi-scale and global information from the graph.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification

Liu,

Guan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Graph convolutional networks (GCNs) are a promising approach for addressing the necessity for long-range information in hyperspectral image (HSI) classification. Researchers have attempted to develop classification methods that combine strong generalizations with effective classification. However, the current HSI classification methods based on GCN present two main challenges. First, they overlook the multi-view features inherent in HSIs, whereas multi-view information interacts with each other to facilitate classification tasks. Second, many algorithms perform a rudimentary fusion of extracted features, which can result in information redundancy and conflicts. To address these challenges and exploit the strengths of multiple features, this paper introduces an adaptive multi-feature fusion GCN (AMF-GCN) for HSI classification. Initially, the AMF-GCN algorithm extracts spectral and textural features from the HSIs and combines them to create fusion features. Subsequently, these three features are employed to construct separate images, which are then processed individually using multi-branch GCNs. The AMG-GCN aggregates node information and utilizes an attention-based feature fusion method to selectively incorporate valuable features. We evaluated the model on three widely used HSI datasets, i.e., Pavia University, Salinas, and Houston-2013, and achieved accuracies of 97.45%, 98.03%, and 93.02%, respectively. Extensive experimental results show that the classification performance of the AMF-GCN on benchmark HSI datasets is comparable to those of state-of-the-art methods.

show abstract

Section: Comparison With Various Graph-based Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification

Liu,

Guan,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Superpixels are non‐overlapping homogeneous connected regions whose pixels have similar spectra (Ren and Malik, 2003). On top of the assumption of superpixel homogeneity, a series of superpixel‐based HSI classification methods were proposed in the past years (Zhao et al., 2020; Zhao & Yan, 2021). For example, treating each superpixel as a node, the authors investigated the graph‐based semi‐supervised HSI classification approaches at superpixel level (Bae et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral image classification based on superpixel merging and broad learning system

Xie,

Wang,

Jin

et al. 2024

The Photogrammetric Record

View full text Add to dashboard Cite

Most spectral–spatial classification methods for hyperspectral images (HSIs) can achieve satisfactory classification results. However, the common problem faced with these approaches is the need for a long training time and sufficient training samples. To address this issue, this study proposes an effective spectral–spatial HSI classification method based on superpixel merging, superpixel smoothing and broad learning system (SMS‐BLS). The newly introduced parameter‐free superpixel merging technique based on local modularity not only enhances the role of local spatial information in classification, but also maintains class boundary information as much as possible. In addition, the spectral and spatial information of HSIs is further fused during the superpixel smoothing process. As a result, with limited training samples, using merged and smoothed superpixels instead of pixels as input to the broad learning system significantly improves its classification performance. Moreover, the merged superpixels weaken the dependence of the classification results on the superpixel segmentation scale. The effectiveness of the proposed method was validated on three HSI benchmarks, namely Indian Pines, Pavia University and Salinas. Experimental and comparative results show the superiority of the method to other state‐of‐the‐art approaches in terms of overall accuracy and running time.

show abstract

“…For complicated feature objects, these semantic segmentation approaches have a pretzel effect since it is challenging to determine the correct class for each pixel 20,21 . In contrast, the above scenario is avoided from the object level using the superpixel segmentation and deep neural network classification approach 22,23 . 24 proposed a deep learning method based on CNN and energy-driven sampling for high-resolution remote sensing image classification.…”

Section: Introductionmentioning

confidence: 99%

Joint superpixel and Transformer for high resolution remote sensing image classification

Dang,

Mao,

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep neural networks combined with superpixel segmentation have proven to be superior to high-resolution remote sensingimage (HRI) classification. Currently, most HRI classification methods that combine deep learning and superpixel segmentationuse stacking on multiple scales to extract contextual information from segmented objects. However, this approach does nottake into account the contextual dependencies between each segmented object. To solve this problem, a joint superpixel andTransformer (JST) framework is proposed for HRI classification. In JST, HRI is first segmented into superpixel objects as input,and Transformer is used to model the long-range dependencies. The contextual relationship between each input superpixelobject is obtained and the class of analyzed objects is output by designing an encoding and decoding Transformer. Additionally,we explore the effect of semantic range on classification accuracy. JST is also tested by using two HRI datasets with overallclassification accuracy, average accuracy and Kappa coefficients of 0.79, 0.70, 0.78 and 0.91, 0.85, 0.89, respectively. Theeffectiveness of the proposed method is compared qualitatively and quantitatively, and the results achieve competitive andconsistently better than the benchmark comparison method.

show abstract

Hyperspectral Image Classification Based on Sparse Superpixel Graph

Cited by 7 publications

References 58 publications

Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification

Adaptive Multi-Feature Fusion Graph Convolutional Network for Hyperspectral Image Classification

Hyperspectral image classification based on superpixel merging and broad learning system

Joint superpixel and Transformer for high resolution remote sensing image classification

Contact Info

Product

Resources

About