Abstract
Hyperspectral images (HSIs) classification have aroused a great deal of attention recently due to their wide range of practical prospects in numerous fields. Spatial-spectral fusion feature is widely used in HSI classification to get better performance. These methods are mostly based on a simple linear addition with the combined hyper-parameter to fuse the spatial and spectral information. It is necessary to fuse the features in a more suitable method. To solve this problem, we propose a novel HSI classification approach based on Hybrid spatial-spectral feature in broad learning system (HSFBLS). First, we employ an adaptive weighted mean filter to obtain spatial feature. Computing the weights of spatial and spectral channels in hybrid module by two BLS and uniting them with a weighted linear function. Then, we fuse the spectral-spatial feature by sparse autoencoder to get weighted fusion feature as the feature nodes to classify HSI data in BLS. By a two-stage fusion of spatial and spectral information, it can increase the classification accuracy contrast to simple combination. Very satisfactory classification results on typical HSI datasets illustrate the availability of proposed HSFBLS. Moreover, HSFBLS also reduce training time greatly contrast to time-consuming network.
Similar content being viewed by others
References
Konstantinos M, Doulamis AD, Doulamis ND, Antonis N (2018) Tensor-based classification models for hyperspectral data analysis. IEEE Trans Geosci Remote Sens PP:1–15
Tjiong ASJ, Monteiro ST (2011) Feature selection with pso and kernel methods for hyperspectral classification. In: Evolutionary computation
Appice A, Guccione P, Acciaro E, Malerba D (2020) Detecting salient regions in a bi-temporal hyperspectral scene by iterating clustering and classification. Appl Intell 50(10):3179–3200
Li J, Bioucasdias J, Plaza A (2009) Semi-supervised hyperspectral classification using active label selection. In: Proceedings of SPIE - The international society for optical engineering, vol 7477, pp 74770F–74770F–8
Li Y, Tingjie X, Pin W, Liu J, Zhou S (2018) Joint spectral-spatial hyperspectral image classification based on hierarchical subspace switch ensemble learning algorithm. In: Applied intelligence the international journal of artificial intelligence neural networks & Complex problem solving technologies
Lin H, Li J, Liu C, Li S (2018) Recent advances on spectral-spatial hyperspectral image classification: An overview and new guidelines. IEEE Trans Geosci Remote Sens 56(99):1579–1597
Caporaso N, Whitworth MB, Fisk ID (2018) Protein content prediction in single wheat kernels using hyperspectral imaging. Food Chemistry
Bau TC, Healey G (2009) Rotation and scale invariant hyperspectral classification using 3d gabor filters. In: Proceedings of SPIE - The international society for optical engineering, p 7334
Zhang M, Li W, Du Q (2018) Diverse region-based cnn for hyperspectral image classification. IEEE Trans Image Process 27(6):2623–2634. https://doi.org/10.1109/TIP.2018.2809606
Jia S, Deng X, Wu K (2018) Multiscale superpixel-based fusion framework for hyperspectral image classification. In: 2018 Fifth international workshop on earth observation and remote sensing applications (EORSA)
Wang Z, Nasrabadi N, Huang T (2015) Semisupervised hyperspectral classification using task-driven dictionary learning with laplacian regularization. IEEE Trans Geosci Remote Sens 53(3):1161–1173
Pan ZK, Wang F, Xia LH, Zhou XZ (2012) An optimized method for hyperspectral imagery spectral feature fitting classification by using idl wavelet toolkit. Geomatics Spatial Information Technology
Du B, Zhang LP, Zhang LF, Chen T, Wu K (2012) A discriminative manifold learning based dimension reduction method for hyperspectral classification. Int J Fuzzy Syst 14(2):272–277
Velasco-Forero S, Manian V (2009) Improving hyperspectral image classification using spatial preprocessing. IEEE Geosci Remote Sens Lett 6(2):297–301
Mercier G, Lennon M (2003) Support vector machines for hyperspectral image classification with spectral-based kernels. In: IGARSS 2003. 2003 IEEE international geoscience and remote sensing symposium. Proceedings (IEEE Cat. No.03CH37477), vol. 1, pp. 288–290 vol.1. https://doi.org/10.1109/IGARSS.2003.1293752
Ramanath R, Qi H, Wang X, Du H, Snyder WE (2003) Band selection using independent component analysis for hyperspectral image processing. In: 2013 IEEE Applied imagery pattern recognition workshop (AIPR). IEEE Computer Society, USA, p 93. https://doi.org/10.1109/AIPR.2003.1284255
Du Q, Chang C (2004) Segmented pca-based compression for hyperspectral image analysis. In: Chemical biological standoff detection
Ren Y, Liao L, Maybank SJ, Zhang Y, Liu X (2017) Hyperspectral image spectral-spatial feature extraction via tensor principal component analysis. IEEE Geosci Remote Sens Lett 14(9):1431–1435
Chen Y, Lin Z, Xing Z, Gang W, Gu Y (2017) Deep learning-based classification of hyperspectral data. IEEE J Select Topics Appl Earth Observ Remote Sens 7(6):2094–2107
Venkatesan R, Prabu S (2019) Hyperspectral image features classification using deep learning recurrent neural networks. J Med Syst 43(7). https://doi.org/10.1007/s10916-019-1347-9
Zhang X, Luo L, Zhao W, Guo Z, Yue J (2015) On combining multiscale deep learning features for the classification ofn hyperspectral remote sensing imagery. Int J Remote Sens 36(13-14):3368–3379
Lee H, Kwon H (2017) Going deeper with contextual cnn for hyperspectral image classification. IEEE Trans Image Process 26(10):4843–4855
Li J, Xi B, Li Y, Du Q, Wang K (2018) Hyperspectral classification based on texture feature enhancement and deep belief networks. Remote Sens 10(3):396
Chen CLP, Liu Z (2018) Broad learning system: An effective and efficient incremental learning system without the need for deep architecture. IEEE Trans Neural Netw Learn Syst 29(99):10– 24
Feng S, Chen CLP (2018) Fuzzy broad learning system: A novel neuro-fuzzy model for regression and classification. IEEE Trans Cybern 50:414–424
Leanos S, Coons J, Rebok GW, Ozer DJ, Wu R (2019) Development of the broad learning adult questionnaire (blaq). Int J Aging Human Develop 88(3):286–311
Jin J, Liu Z, Chen CLP (2018) Discriminative graph regularized broad learning system for image recognition. Sci China Inform Sci 61(11):1–14
Jin JW, Chen CLP (2018) Regularized robust broad learning system for uncertain data modeling. Neurocomputing 322(DEC.17):58–69
Kong Y, Wang X, Cheng Y, Chen C (2018) Hyperspectral imagery classification based on semi-supervised broad learning system. Remote Sens 10(5):685
Wang H, Wang X, Chen CLP, Cheng Y (2020) Hyperspectral image classification based on domain adaptation broad learning. IEEE J Select Topics Appl Earth Observ Remote Sens 13:3006–3018. https://doi.org/10.1109/JSTARS.2020.3001198
Li W, Du Q (2015) Support vector machine with adaptive composite kernel for hyperspectral image classification. In: Proceedings of SPIE - The international society for optical engineering, vol 9501
Jiang M, Cao F, Lu Y (2018) Extreme learning machine with enhanced composite feature for spectral-spatial hyperspectral image classification. IEEE Access 6:22645–22654. https://doi.org/10.1109/ACCESS.2018.2825978
Luo F, Du B, Zhang L, Zhang L, Tao D (2019) Feature learning using spatial-spectral hypergraph discriminant analysis for hyperspectral image. IEEE Trans Cybern 49(7):2406– 2419
Kassani HP, Teoh JAB, Kim E (2018) Sparse pseudoinverse incremental extreme learning machine. Neurocomputing
Lin J, Liu Z, Chen CLP, Zhang Y (2019) A wavelet broad learning adaptive filter for forecasting and cancelling the physiological tremor in teleoperation. Neurocomputing 356(SEP.3):170–183
Hassan MI (2019) Ghassemian: Morphology-based structure-preserving projection for spectral-spatial feature extraction and classification of hyperspectral data. Iet Image Processing
Yu X, Wang R, Liu B, Yu A (2019) Salient feature extraction for hyperspectral image classification. Remote Sens Lett 10(6):553–562
He N, Paoletti ME, Mario HJ, Fang L, Li S, Antonio P, Javier P (2019) Feature extraction with multiscale covariance maps for hyperspectral image classification. IEEE Trans Geosci Remote Sens PP:1–15
Fang L, He N, Li S, Ghamisi P, Benediktsson JA (2018) Extinction profiles fusion for hyperspectral images classification. IEEE Trans Geosci Remote Sens 56(3):1803–1815
Song W, Li S, Fang L, Lu T (2018) Hyperspectral image classification with deep feature fusion network. IEEE Trans Geosci Remote Sens 56(6):3173–3184. https://doi.org/10.1109/TGRS.2018.2794326
Tao C, Pan H, Li Y, Zou Z (2015) Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification. IEEE Geosci Remote Sens Lett 12(12):2438–2442
Xiaoquan Y, Xing L, Chen (2016) Stacked denoise autoencoder based feature extraction and classification for hyperspectral images. J Sens
Jaime Z, Jiangbin Z, Stephen M, Chunmei Q, Peijun D (2016) Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging (vol 185, pg 1, 2016) Neurocomputing
Zhang C, Ahmad M, Wang Y (2018) Admm based privacy-preserving decentralized optimization. IEEE Trans Inform Forens Secur
Aswathy C, Haridas N, Sowmya V, Soman KP (2015) Effect of ab filter denoising on admm based hyperspectral image classification. Int J Appl Eng Res 10(73):127–131
Zhu F, Halimi A, Honeine P, Chen B, Zheng N (2017) Correntropy maximization via admm: Application to robust hyperspectral unmixing. IEEE Trans Geosci Remote Sens 55(9):4944–4955
Zhou Y, Wei Y (2017) Learning hierarchical spectral-spatial features for hyperspectral image classification. IEEE Trans Cybern 46(7):1667–1678
Chen L, Wei Z, Xu Y (2020) A lightweight spectral-spatial feature extraction and fusion network for hyperspectral image classification. Remote Sens 12(9):1395
Oktiana M, Saddami K, Arnia F, Away Y, Munadi K (2019) Advances in cross-spectral iris recognition using integrated gradientface-based normalization. IEEE Access PP(99):1–1
Yan L (2020) Spectral normalization for domain adaptation. Inf (Switzerland) 11(2):68
Rajadell O, Garcia-Sevilla P, Pla F (2013) Spectral-spatial pixel characterization using gabor filters for hyperspectral image classification. IEEE Geosci Remote Sens Lett
Hu J, Shen L, Albanie S, Sun G, Wu E (2017) Squeeze-and-excitation networks. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023. https://doi.org/10.1109/TPAMI.2019.2913372
Xu Y, Du B, Zhang F, Zhang L (2018) Hyperspectral image classification via a random patches network. ISPRS J Photogramm Remote Sens 142(AUG):344–357
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ma, Y., Liu, Z. & Chen Chen, C.L.P. Hybrid spatial-spectral feature in broad learning system for Hyperspectral image classification. Appl Intell 52, 2801–2812 (2022). https://doi.org/10.1007/s10489-021-02320-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02320-7