Hyperspectral image classification based on superpixel segmentation and extended multi-attribute profiles

doi:10.6046/zrzyyg.2022304

Abstract
Figures/Tables
References
Related Articles
Metrics

Download: PDF(5254 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Superpixel segmentation-based image processing has been extensively used for the classification of hyperspectral images (HSI) in recent years. However, it fails to fully extract the HSI information at a single scale, and its classification process highly depends on parameters. Given the insufficient spatial information utilization by the superpixel segmentation-based HSI classification technology, this study proposed an HSI classification method that combines the superpixel segmentation method and the extended multi-attribute profile (EMAP) method. First, the superpixel segmentation and EMAP methods were employed to extract superpixel-level and pixel-level HSI features, respectively. By fusing the two types of features, the resulting images displayed complete HSI structural characteristics. To eliminate information redundancy, the fused images were subjected to spectral filtering through the recursive filtering method. Finally, the features were input to the support vector machine (SVM) for pixel tag determination. Experiments on the Indian Pines and University of Pavia datasets analyzed the effects of parameter variations on classification accuracy. Compared with the S3-PCA algorithm, the method proposed in this study exhibited superior classification accuracy and Kappa coefficient, which were improved by 3.55 and 2.88 percentage points, respectively.

Keywords hyperspectral image classification information fusion feature extraction superpixel segmentation

ZTFLH:

TP751.1

Issue Date: 21 December 2023

	Service

	E-mail this article
	E-mail Alert
	RSS
	Articles by authors

	Lei LI
	Xiyan SUN
	Yuanfa JI
	Wentao FU

Cite this article:

Lei LI,Xiyan SUN,Yuanfa JI, et al. Hyperspectral image classification based on superpixel segmentation and extended multi-attribute profiles[J]. Remote Sensing for Natural Resources, 2023, 35(4): 114-121.

URL:

https://www.gtzyyg.com/EN/10.6046/zrzyyg.2022304 OR https://www.gtzyyg.com/EN/Y2023/V35/I4/114

Fig.1 Schematic diagram of classification framework

Fig.2 Obtaining super pixel level features

Fig.3 Obtaining pixel-level features

Fig.4 Indian Pines data set

Fig.5 University of Pavia data set

Fig.6 classification results of Indian Pines dataset

Tab.1 Comparison of classification accuracy of Indian Pines data set (%)

Fig.7 Classification results of data set of University of Pavia

Tab.2 Comparison of classification accuracy of University of Pavia data set (%)

Fig.8 Classification accuracy changes with training set

Fig.9 Kappa coefficient versus the number of superpixels

Fig.10 Ablation test analysis in Indian Pines data set

[1]	Camps-Valls G, Tuia D, Bruzzone L, et al. Advances in hyperspectral image classification:Earth monitoring with statistical learning methods[J]. IEEE Signal Processing Magazine, 2014, 31(1):45-54.
[2]	Yan L, Zhu R, Mo N, et al. Cross-domain distance metric learning framework with limited target samples for scene classification of aerial images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(6):3840-3857. doi: 10.1109/TGRS.36 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36
[3]	Lu X, Zhang W, Li X. A hybrid sparsity and distance-based discrimination detector for hyperspectral images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(3):1704-1717. doi: 10.1109/TGRS.2017.2767068 url: http://ieeexplore.ieee.org/document/8128904/
[4]	Horstrand P, Diaz M, Guerra R, et al. A novel hyperspectral anomaly detection algorithm for real-time applications with push-broom sensors[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(12):4787-4797. doi: 10.1109/JSTARS.2019.2919911
[5]	Shimoni M, Haelterman R, Perneel C. Hypersectral imaging for military and security applications:Combining myriad processing and sensing techniques[J]. IEEE Geoscience and Remote Sensing Magazine, 2019, 7(2):101-117. doi: 10.1109/MGRS.2019.2902525
[6]	Tong X Y, Xia G S, Lu Q, et al. Land-cover classification with high-resolution remote sensing images using transferable deep models[J/OL]. arXiv, 2018(2018-07-16)[2022-10-04]. https://arxiv.org/abs/1807.05713v2. url: https://arxiv.org/abs/1807.05713v2
[7]	Krupnik D, Khan S-D. Close-range,ground-based hyperspectral imaging for mining applications at various scales:Review and case studies[J]. Earth-Science Reviews, 2019, 198:102952. doi: 10.1016/j.earscirev.2019.102952 url: https://linkinghub.elsevier.com/retrieve/pii/S001282521930251X
[8]	Li W, Du Q, Zhang F, et al. Hyperspectral image classification by fusing collaborative and sparse representations[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(9):4178-4187. doi: 10.1109/JSTARS.4609443 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=4609443
[9]	Kang X, Li S, Benediktsson J A. Spectral-spatial hyperspectral image classification with edge-preserving filtering[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(5):2666-2677. doi: 10.1109/TGRS.2013.2264508 url: http://ieeexplore.ieee.org/document/6553593/
[10]	Liang J, Zhou J, Gao Y. Tensor morphological profile for hyperspectral image classification[C]// IEEE International Conference on Image Processing.IEEE, 2016, 20(6):25-39
[11]	付航, 孙根云, 赵云华, 等. 多尺度超像素分割和奇异谱分析的高光谱影像分类[J]. 中国图象图形学报, 2021, 26(8):1978-1993.
[11]	Fu H, Sun G Y, Zhao Y H, et al. Combining multiscale superpixel segmentation and singular spectral analysis for hyperspectral image classification[J]. Journal of Image and Graphics, 2021, 26(8):1978-1993.
[12]	Liao J, Wang L, Zhao G, et al. Hyperspectral image classification based on bilateral filter with linear spatial correlation information[J]. International Journal of Remote Sensing, 2019, 40(17):6861-6883. doi: 10.1080/01431161.2019.1597301 url: https://www.tandfonline.com/doi/full/10.1080/01431161.2019.1597301
[13]	Feng J, Zhang J, Zhang Y. A multiview spectral-spatial feature extraction and fusion framework for hyperspectral image classification[J]. IEEE Geoscience and Remote Sensing Letters, 2021, 19:5504805.
[14]	Ren L, Zhao L, Wang Y. A superpixel-based dual window RX for hyperspectral anomaly detection[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(7):1233-1237. doi: 10.1109/LGRS.8859 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=8859
[15]	Sellars P, Aviles-Rivero A, Schonlieb C B. Superpixel contracted graph-based learning for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(6):4180-4193. doi: 10.1109/TGRS.36 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36
[16]	Jiang J, Ma J, Chen C, et al. SuperPCA:A superpixelwise PCA approach for unsupervised feature extraction of hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(8):4581-4593. doi: 10.1109/TGRS.2018.2828029 url: https://ieeexplore.ieee.org/document/8390924/
[17]	Zhang X, Jiang X, Jiang J, et al. Spectral-spatial and superpixelwise PCA for unsupervised feature extraction of hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60:552210.
[18]	Beirami A B, Mokhtarzade M. Band grouping SuperPCA for feature extraction and extended morphological profile production from hyperspectral images[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(11):1953-1957. doi: 10.1109/LGRS.8859 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=8859
[19]	Jia S, Deng X, Xu M, et al. Superpixel-level weighted label propagation for hyperspectral image classification[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(7):5077-5091. doi: 10.1109/TGRS.36 url: https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=36
[20]	王扣准, 黄睿. 利用多属性剖面与双边滤波的高光谱影像分类[J]. 遥感信息, 2016, 31(6):104-109.
[20]	Wang K Z, Huang R. Hyperspectral image classification using extended multi-attribute profiles and guide bilateral filter[J]. Remote Sensing Information, 2016, 31(6):104-109.
[21]	罗建华, 李明奇, 郑泽忠, 等. 基于深度卷积神经网络的高光谱遥感图像分类[J]. 西华大学学报(自然科学版), 2017, 36(4):13-20.
[21]	Luo J H, Li M Q, Zheng Z Z, et al. Hyperspectral remote sensing images classification using a deep convolutional neural network model[J]. Journal of Xihua University (Natural Science Edition), 2017, 36(4):13-20.
[22]	付光远, 辜弘炀, 汪洪桥. 基于加权K近邻和卷积神经网络的高光谱图像分类[J]. 计算机应用研究, 2018, 35(8):2540-2543.
[22]	Fu G Y, Gu H Y, Wang H Q. Hyperspectral image classification based on weighted KNN and CNN[J]. Application Research of Computers. 2018, 35(8):2540-2543.

[1]	ZHANG Pengqiang, GAO Kuiliang, LIU Bing, TAN Xiong. Classification of hyperspectral images based on deep Transformer network combined with spatial-spectral information[J]. Remote Sensing for Natural Resources, 2022, 34(3): 27-32.
[2]	QU Haicheng, WAND Yaxuan, SHEN Lei. Hyperspectral super-resolution combining multi-receptive field features with spectral-spatial attention[J]. Remote Sensing for Natural Resources, 2022, 34(1): 43-52.
[3]	HAN Yanling, CUI Pengxia, YANG Shuhu, LIU Yekun, WANG Jing, ZHANG Yun. Classification of hyperspectral image based on feature fusion of residual network[J]. Remote Sensing for Land & Resources, 2021, 33(2): 11-19.
[4]	XIA Yan, HUANG Liang, CHEN Pengdi. Tobacco fine extraction from UAV image based on fuzzy-superpixel segmentation algorithm[J]. Remote Sensing for Land & Resources, 2021, 33(1): 115-122.
[5]	CAI Xiang, LI Qi, LUO Yan, QI Jiandong. Surface features extraction of mining area image based on object-oriented and deep-learning method[J]. Remote Sensing for Land & Resources, 2021, 33(1): 63-71.
[6]	LI Xusheng, LIU Yufeng, CHEN Donghua, LIU Saisai, LI Hu. Cloud detection based on support vector machine with image features for GF-1 data[J]. Remote Sensing for Land & Resources, 2020, 32(3): 55-62.
[7]	Benzuo YAO, Fang HE. Spatial and spectral feature hierarchical fusion for hyperspectral image feature extraction[J]. Remote Sensing for Land & Resources, 2019, 31(3): 59-64.
[8]	Xinghang ZHANG, Lin ZHU, Wei WANG, Lishan MENG, Xiaojuan LI, Yingchao REN. Study and application of sequential extraction method of ground fissures based on object[J]. Remote Sensing for Land & Resources, 2019, 31(1): 87-94.
[9]	Wanjun LIU, Tianhui LI, Haicheng QU. Hyperspectral similar sample classification algorithm based on Fisher criterion and TrAdaboost[J]. Remote Sensing for Land & Resources, 2018, 30(4): 41-48.
[10]	WEI Yingjuan, ZHENG Xiongwei, LEI Bing, GAN Yuhang. Realization of clouds automatic extraction of GF-1 remote sensing image based on sample model[J]. REMOTE SENSING FOR LAND & RESOURCES, 2017, 29(s1): 39-45.
[11]	ZHANG Yongmei, YANG Fei, XU Jing. An improved length variable angle chain code algorithm and its application to dock identification[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(4): 164-169.
[12]	LI Fuyu, YE Famao. Summarization of SIFT-based remote sensing image registration techniques[J]. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 14-20.
[13]	LIU Pengcheng. Feature extraction of coastline contour based on level set theory[J]. REMOTE SENSING FOR LAND & RESOURCES, 2015, 27(2): 75-79.
[14]	CHANG Ruichun, WANG Lu, WANG Maozhi. Application of FastICA in mineral information extraction from hyperspectral remote sensing data[J]. REMOTE SENSING FOR LAND & RESOURCES, 2013, 25(4): 129-132.
[15]	LI Ting, ZHAN Qing-ming, YU Liang. A Classification Method for Mobile Laser Scanning Data Based on Object Feature Extraction[J]. REMOTE SENSING FOR LAND & RESOURCES, 2012, 24(1): 17-21.

Viewed

Full text

Abstract

Cited

Shared

Discussed