Hyperspectral Image Classification Based on Sparse Superpixel Graph

Hyperspectral image (HSI) classification is one of the major problems in the field of remote sensing. Particularly, graph-based HSI classification is a promising topic and has received increasing attention in recent years. However, graphs with pixels as nodes generate large size graphs, thus increasing the computational burden. Moreover, satisfactory classification results are often not obtained without considering spatial information in constructing graph. To address these issues, this study proposes an efficient and effective semi-supervised spectral-spatial HSI classification method based on sparse superpixel graph (SSG). In the constructed sparse superpixels graph, each vertex represents a superpixel instead of a pixel, which greatly reduces the size of graph. Meanwhile, both spectral information and spatial structure are considered by using superpixel, local spatial connection and global spectral connection. To verify the effectiveness of the proposed method, three real hyperspectral images, Indian Pines, Pavia University and Salinas, are chosen to test the performance of our proposal. Experimental results show that the proposed method has good classification completion on the three benchmarks. Compared with several competitive superpixel-based HSI classification approaches, the method has the advantages of high classification accuracy (>97.85%) and rapid implementation (<10 s). This clearly favors the application of the proposed method in practice.

[1]  Li Ma,et al.  Spatial and class structure regularized sparse representation graph for semi-supervised hyperspectral image classification , 2018, Pattern Recognit..

[2]  Junjun Jiang,et al.  Label Noise Cleansing with Sparse Graph for Hyperspectral Image Classification , 2019, Remote. Sens..

[3]  Antonio J. Plaza,et al.  An Accurate Vegetation and Non-Vegetation Differentiation Approach Based on Land Cover Classification , 2020, Remote. Sens..

[4]  Dong Liu,et al.  Semi-supervised community detection based on discrete potential theory , 2014 .

[5]  Cui Jin,et al.  An Effective Classification Scheme for Hyperspectral Image Based on Superpixel and Discontinuity Preserving Relaxation , 2019, Remote. Sens..

[6]  Licheng Jiao,et al.  Adaptive sparse graph learning based dimensionality reduction for classification , 2019, Appl. Soft Comput..

[7]  Jonathan Cheung-Wai Chan,et al.  Collaborative learning of lightweight convolutional neural network and deep clustering for hyperspectral image semi-supervised classification with limited training samples , 2020 .

[8]  Fuding Xie,et al.  Hyperspectral Image Classification Based on Superpixel Pooling Convolutional Neural Network with Transfer Learning , 2021, Remote. Sens..

[9]  Yanwen Chong,et al.  Global Consistent Graph Convolutional Network for Hyperspectral Image Classification , 2021, IEEE Transactions on Instrumentation and Measurement.

[10]  Jon Atli Benediktsson,et al.  Spatially Enhanced Spectral Unmixing Through Data Fusion of Spectral and Visible Images from Different Sensors , 2020, Remote. Sens..

[11]  Linyuan Lu,et al.  Potential Theory for Directed Networks , 2012, PloS one.

[12]  Fangfei Li,et al.  Semi-Supervised Classification for Hyperspectral Images Based on Multiple Classifiers and Relaxation Strategy , 2018, ISPRS Int. J. Geo Inf..

[13]  Licheng Jiao,et al.  Hyperspectral Unmixing via Low-Rank Representation with Space Consistency Constraint and Spectral Library Pruning , 2018, Remote. Sens..

[14]  Wei He,et al.  Superpixel-based spatial-spectral dimension reduction for hyperspectral imagery classification , 2019, Neurocomputing.

[15]  Shutao Li,et al.  Super-resolution of hyperspectral image via superpixel-based sparse representation , 2018, Neurocomputing.

[16]  V. Malienė,et al.  The Influence of Seasonality on the Multi-Spectral Image Segmentation for Identification of Abandoned Land , 2021, Sustainability.

[17]  Licheng Jiao,et al.  Non-overlapping classification of hyperspectral imagery with superpixel segmentation , 2019, Appl. Soft Comput..

[18]  Bastian Siegmann,et al.  Regionalization of Uncovered Agricultural Soils Based on Organic Carbon and Soil Texture Estimations , 2016, Remote. Sens..

[19]  Emanuele Barca,et al.  A new supervised classifier exploiting spectral-spatial information in the Bayesian framework , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[20]  Saurabh Prasad,et al.  A spatial-spectral semisupervised deep learning framework using siamese networks and angular loss , 2020, Comput. Vis. Image Underst..

[21]  Mohamed Farah,et al.  Hyperspectral imagery classification based on semi-supervised 3-D deep neural network and adaptive band selection , 2019, Expert Syst. Appl..

[22]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[23]  Bo-Hu Li,et al.  A Unified Framework of Multiple Kernels Learning for Hyperspectral Remote Sensing Big Data , 2016, J. Inf. Hiding Multim. Signal Process..

[24]  Przemysław Głomb,et al.  Semi-supervised hyperspectral classification from a small number of training samples using a co-training approach , 2016 .

[25]  Cui Jin,et al.  A Novel Spectral–Spatial Classification Method for Hyperspectral Image at Superpixel Level , 2020, Applied Sciences.

[26]  Dar A. Roberts,et al.  Species-Level Differences in Hyperspectral Metrics among Tropical Rainforest Trees as Determined by a Tree-Based Classifier , 2012, Remote. Sens..

[27]  Xuelong Li,et al.  Discriminant Analysis with Graph Learning for Hyperspectral Image Classification , 2018, Remote. Sens..