Research on land use classification of hyperspectral images based on multiscale superpixels

Hua Wang; Weiwei Li; Wei Huang; Jiqiang Niu; Ke Nie; Hua Wang; Weiwei Li; Wei Huang; Jiqiang Niu; Ke Nie

doi:10.3934/mbe.2020275

Mathematical Biosciences and Engineering

2020, Volume 17, Issue 5: 5099-5119. doi: 10.3934/mbe.2020275

Previous Article Next Article

Research article Special Issues

Research on land use classification of hyperspectral images based on multiscale superpixels

1.
School of Computer and Communication Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China
2.
School of Geographical Sciences, Xinyang Normal University, Xinyang 464000, China
3.
Key Laboratory for Synergistic Prevention of Water and Soil Environmental Pollution, Xinyang Normal University, Xinyang 464000, China
4.
Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China

Received: 16 June 2020 Accepted: 17 July 2020 Published: 27 July 2020

With the rapid development of remote sensing technology, research on land use classification methods based on hyperspectral remote sensing images has attracted widespread attention. Existing land-use classification studies mostly use the average filtering method at a single scale for spectral image processing. These methods cannot accurately filter the window range, which leads to the neglect of image detail information, and the single kernel matrix cannot characterize multifeature information, resulting in reduced classification accuracy. Therefore, this study intended to use a superpixel segmentation method to perform multiscale superpixel segmentation on the first principal component of a hyperspectral image at multiple scales. By combining the weighted multiscale spatial-spectral kernel and the original spatial-spectral kernel to form a synthetic kernel for land use classification, the hyperspectral image of the National Mall in Washington DC was used as experimental data to test and analyze this method. The experimental results showed that the classification accuracy of this method on the experimental test set was 98.53%, which is compared with the classification results obtained by the single-scale spatial spectral synthetic nuclear method, the original spatial spectral synthetic nuclear method and the wavelength segmented synthetic nuclear method, the effective classification accuracy with this method was increased by 7.56%. The results prove that this method can effectively solve the problems of the lack of adaptability of the image spectrum and the lack of comprehensive spectral information and can significantly improve the accuracy of land use classification.
- multiscale,
- superpixel,
- land use classification,
- synthetic kernel SVM,
- hyperspectral
Citation: Hua Wang, Weiwei Li, Wei Huang, Jiqiang Niu, Ke Nie. Research on land use classification of hyperspectral images based on multiscale superpixels[J]. Mathematical Biosciences and Engineering, 2020, 17(5): 5099-5119. doi: 10.3934/mbe.2020275

Related Papers:

Abstract

With the rapid development of remote sensing technology, research on land use classification methods based on hyperspectral remote sensing images has attracted widespread attention. Existing land-use classification studies mostly use the average filtering method at a single scale for spectral image processing. These methods cannot accurately filter the window range, which leads to the neglect of image detail information, and the single kernel matrix cannot characterize multifeature information, resulting in reduced classification accuracy. Therefore, this study intended to use a superpixel segmentation method to perform multiscale superpixel segmentation on the first principal component of a hyperspectral image at multiple scales. By combining the weighted multiscale spatial-spectral kernel and the original spatial-spectral kernel to form a synthetic kernel for land use classification, the hyperspectral image of the National Mall in Washington DC was used as experimental data to test and analyze this method. The experimental results showed that the classification accuracy of this method on the experimental test set was 98.53%, which is compared with the classification results obtained by the single-scale spatial spectral synthetic nuclear method, the original spatial spectral synthetic nuclear method and the wavelength segmented synthetic nuclear method, the effective classification accuracy with this method was increased by 7.56%. The results prove that this method can effectively solve the problems of the lack of adaptability of the image spectrum and the lack of comprehensive spectral information and can significantly improve the accuracy of land use classification.

References

[1]	F. Yulianto, Suwarsono, U. C. Nugroho, N. P. Nugroho, W. Sunarmodo, M. R. Khomarudin, Spatial-Temporal Dynamics Land Use/Land Cover Change and Flood Hazard Mapping in the Upstream Citarum Watershed, West Java, Indonesia, Quaestiones Geographicae, 39 (2020), 125-146.
[2]	Y. Ye, Y. An, B. Chen, J. Wang, Y. Zhong, Land use classification from social media data and satellite imagery, J. Supercomput., 76 (2020), 777-792.
[3]	A. F. H. Goetz, Three decades of hyperspectral remote sensing of the Earth: A personal view, Remote Sens. Environ., 113 (2009), S5-S16.
[4]	L Sun, C Ma, Y Chen, Y. Zheng, H. J. Shim, Z. Wu, Low Rank Component Induced Spatial-spectral Kernel Method for Hyperspectral Image Classification, IEEE Trans. Circuits Syst. Video Technol., 2019 (2019), 3005-3008.
[5]	L Sun, F Wu, T Zhan, W. Liu, J. Wang, B. Jeon, Weighted Nonlocal Low-Rank Tensor Decomposition Method for Sparse Unmixing of Hyperspectral Images, IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 13 (2020), 1174-1188.
[6]	J. Peng, L. Li, Y. Y. Tang, Maximum Likelihood Estimation-Based Joint Sparse Representation for the Classification of Hyperspectral Remote Sensing Images, IEEE Trans. Neural Networks Learn. Syst., 30 (2018), 1790-1802.
[7]	J. C. W. Chan, D. Paelinckx, Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery, Remote Sens. Environ., 112 (2008), 2999-3011.
[8]	P. Rao, J. Wang, Y. Wang, Extraction of information on construction land based on multi-feature decision tree classification, Trans. Chin. Soc. Agric. Eng., 30 (2104), 233-240.
[9]	Y. Liu, L. Wang, B. Zhang, J. Men, Scene-level land use classification based on multi-features soft-probability cascading, Trans. Chin. Soc. Agric. Eng., 32 (2016), 266-272.
[10]	K. Rangzan, M. Kabolizadeh, D. Karimi, S. Zareie, Supervised cross-fusion method: A new triplet approach to fuse thermal, radar, and optical satellite data for land use classification, Environ. Monit. Assess., 191 (2019), 481.
[11]	S. A. Manaf, N. Mustapha, M. N. Sulaiman, N. A. Husin, M. R. A. Hamid, Artificial Neural Networks for Satellite Image Classification of Shoreline Extraction for Land and Water Classes of the North West Coast of Peninsular Malaysia, Adv. Sci. Lett., 24 (2018), 1382-1387.
[12]	J. Fan, T. Chen, S. Lu, Unsupervised Feature Learning for Land-Use Scene Recognition, IEEE Trans. Geosci. Remote Sens., 55 (2017), 2250-2261.
[13]	J. Men, L. Fang, Y. Liu, Y. Sun, Land Use Classification Based on Multi-structure Convolution Neural Network Features Cascading, Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci., 2019 (2019), 163-167.
[14]	K. Bhosle, V. Musande, Evaluation of Deep Learning CNN Model for Land Use Land Cover Classification and Crop Identification Using Hyperspectral Remote Sensing Images, J. Indian Soc. Remote Sens., 47 (2019), 1949-1958.
[15]	S. Bera, V. K. Shrivastava, Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification, Int. J. Remote Sens., 41 (2020), 2664-2683.
[16]	W. Huang, Y. Xu, X. Hu, Z. Wei, Compressive Hyperspectral Image Reconstruction Based on Spatial-Spectral Residual Dense Network, IEEE Geosci. Remote Sens. Lett., 17 (2020), 884-888.
[17]	P. J. Du, J. S. Xia, Z. H. Xue, K. Tan, H. J. Su, R. Bao, Review of hyperspectral remote sensing image classification, J. Remote Sens., 20 (2016), 236-256.
[18]	J. Fan, T. Chen, S. Lu, Superpixel Guided Deep-Sparse-Representation Learning for Hyperspectral Image Classification, IEEE Trans. Circuits Syst. Video Technol., 28 (2018), 3163-3173.
[19]	J. Li, J. M. Bioucas-Dias, A. Plaza, Semisupervised Hyperspectral Image Segmentation Using Multinomial Logistic Regression With Active Learning, IEEE Trans. Geosci. Remote Sens., 48 (2010), 4085-4098.
[20]	P. Ghamisi, M. S. Couceiro, F. M. Martins, J. A. Benediktsson, Multilevel Image Segmentation Based on Fractional-Order Darwinian Particle Swarm Optimization, IEEE Trans. Geosci. Remote Sens., 52 (2014), 2382-2394.
[21]	P. Y. Wang, H. Q. Zhu, N. CHEN, UMMS: Efficient Superpixel Segmentation Driven by a Mixture of Spatially Constrained Uniform Distribution, IEICE Trans. Inf. Syst., 103 (2020), 181-185.
[22]	D. Song, X. Tan, B. Wang, L. Zhang, X. Shan, J. Cui, Integration of super-pixel segmentation and deep-learning methods for evaluating earthquake-damaged buildings using single-phase remote sensing imagery, Int. J. Remote Sens., 41 (2020), 1040-1066.
[23]	B. Amin, M. M. Riaz, A. Ghafoor, Automatic Image Matting of Synthetic Aperture Radar Target Chips, Radioengineering, 29 (2020), 228-234.
[24]	X. Yuan, S. Guo, C. Li, B. Lu, S. Lou, Near Infrared Star Centroid Detection by Area Analysis of Multi-Scale Super Pixel Saliency Fusion Map, Tsinghua Sci. Technol., 24 (2019), 291-300.
[25]	K. Tang, Z. Su, W. Jiang, J. Zhang, Superpixels for large dataset subspace clustering, Neural Comput. Appl., 31 (2019), 8727-8736.
[26]	Y. J. Chen, C. Y. Ma, Edge-Modified Superpixel Based Spectral-Spatial Kernel Method for Hyperspectral Image Classification, Acta Electron. Sin., 47 (2019), 73-81.
[27]	Z. Liu, Y. Wu, Y. Zou, Multiscale infrared superpixel-image model for small-target detection, J. Image Graphics, 24 (2019), 2159-2173.
[28]	M. S. Chaibou, P. H. Conze, K. Kalti, M. A. Mahjoub, B. Solaiman, Learning contextual superpixel similarity for consistent image segmentation, Multimedia Tools Appl., 79 (2020), 2601-2627.
[29]	Y. Song, W. Liu, S. Zong, Y. Luo, Segmentation Algorithm for Unmanned Aerial Vehicle Imagery Based on Superpixel and Ultrametric Contour Map, J. Comput. Aided Des. Comput. Graphics, 31 (2019), 1294-1300.
[30]	X. Hou, H. Zhao, Y. Ma, Fast Image Segmentation Algorithm Based on Superpixel Multi-feature Fusion, Acta Electron. Sin., 47 (2019), 2126-2133.
[31]	H. Liang, B. X. Yao, P. D. Chen, Superpixel segmentation method of high resolution remote sensing images based on hierarchical clustering, J. Infrared Millimeter Waves, 39 (2020), 263-272.
[32]	Z. Yang, X. D. Mu, S. Y. Wang, C. H. Ma, Scene classification of remote sensing images based on multiscale features fusion, Opt. Precis. Eng., 26 (2018), 3099-3107.
[33]	D. Zhang, T. Yin, G. Yang, M. Xia, L. Li, X. Sun, Detecting image seam carving with low scaling ratio using multi-scale spatial and spectral entropies, J. Visual Commun. Image Representation, 48 (2017), 281-291.
[34]	Z. Chen, X. Wang, K. Yan, J. Zheng, Deep multi-scale feature fusion for pancreas segmentation from CT images, Int. J. Comput. Assisted Radiol. Surg., 15 (2020), 415-423.
[35]	Hyperspectral Image, the National Mall in Washington DC. Available from: https://engineering.purdue.edu/~biehl/MultiSpec/hyperspectral.html.
[36]	M Graña, M. A Veganzons, B Ayerdi, Hyperspectral Remote Sensing Scenes. Available from: http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes.
[37]	X. Jia, J. A. Richards, Segmented principal components transformation for efficient hyperspectral remote-sensing image display and classification, IEEE Trans. Geosci. Remote Sens., 37 (1999), 538-542.
[38]	X. Kang, P. Duan, S. Li, Hyperspectral image visualization with edge-preserving filtering and principal component analysis, Inf. Fusion, 57 (2020), 130-143.
[39]	B. Fatima, A. R. Shahid, S. Ziauddin, A. A. Safi, H. Ramzan, Driver Fatigue Detection Using Viola Jones and Principal Component Analysis, Appl. Artif. Intell., 34 (2020), 456-483.
[40]	Z. Zhang, J. Liu, Z. Xi, A disparity optimization algorithm using entropy rate super-pixel segmentation consistency check, Comput. Eng. Appl., 56 (2020), 1-8.
[41]	Liu Xia, Guo Yanan, Remote sensing image change detection algorithm based on random forest, Bull. Surv. Mapp., 5 (2020), 16-20.
[42]	C. Shi, C. M. Pun, Multiscale Superpixel-Based Hyperspectral Image Classification Using Recurrent Neural Networks With Stacked Autoencoders, IEEE Trans. Multimedia, 22 (2020), 487-501.
[43]	C. G. Karydas, Optimization of multi-scale segmentation of satellite imagery using fractal geometry, Int. J. Remote Sens., 41 (2020), 2905-2933.
[44]	L Sun, C Ma, Y Chen, H. J. Shim, Z. Wu, B. Jeon, Adjacent superpixel-based multiscale spatial-spectral kernel for hyperspectral classification, IEEE J. Selected Topics in Applied Earth Observations Remote Sens., 12 (2019), 1905-1919.
[45]	C. Liu, L. Hong, J. Chen, S. S. Chun, M. Deng, Fusion of pixel-based and multi-scale region-based features for the classification of high-resolution remote sensing image, J. Remote Sens., 19 (2015), 228-239.
[46]	G. Camps-Valls, L. Bruzzone, Kernel-based methods for hyperspectral image classification, IEEE Trans. Geosci. Remote Sens., 43 (2005), 1351-1362.
[47]	Y. Chen, J. Wang, R. Xia, Q. Zhang, Z. Cao, K. Yang, The Visual Object Tracking Algorithm Research Based on Adaptive Combination Kernel, J. Ambient Intell. Humanized Comput., 10 (2019), 4855-4867.
[48]	Y. Chen, J. Xiong, W. Xu, J. Zuo, A novel online incremental and decremental learning algorithm based on variable support vector machine, Cluster Comput., 22 (2019), 7435-7445.
[49]	Y. Chen, W. Xu, J. Zuo, K. Yang, The fire recognition algorithm using dynamic feature fusion and IV-SVM classifier, Cluster Comput., 22 (2019), 7665-7675.
[50]	K. Shankar, S. K. Lakshmanaprabu, D. Gupta, A. Maseleno, V. Hugo, C. de Albuquerque, Optimal feature-based multi-kernel SVM approach for thyroid disease classification, J. Supercomput., 76 (2020), 1128-1143.
[51]	M. Ramzan, A. Abid, H. U. Khan, S. M. Awan, A. Ismail, M. Ahmed, et al., A Review on State-of-the-Art Violence Detection Techniques, IEEE Access, 7 (2019), 107560-107575.
[52]	C. C. Chang, H. T. Huang, Automatic Tuning of the RBF Kernel Parameter for Batch-Mode Active Learning Algorithms: A Scalable Framework, IEEE Trans. Cybern., 49 (2019), 4460-4472.
[53]	K. Shang, P. Li, T. Cheng, Land Cover Classification of Hyperspectral Data Using Composite Kernel Support Vector Machines, Acta Sci. Nat. Univ. Pekin., 7 (2019), 107560-107575.

Reader Comments

Your name:*

Email:*
© 2020 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)