Abstract In joint sparse representation of hyperspectral image classification, once the local window of each pixel includes samples from different categories, the dictionary atoms and testing samples are easily affected by samples from different categories with same spectrum and the classification performance is seriously decreased. According to the characteristics of hyperspectral image , an algorithm of joint sparse representation fusing hierarchical deep network is proposed. Discriminative spectral information and spatial information are extracted by alternating spectral and spatial feature learning operations, and then a dictionary with spatial spectral features is constructed for joint sparse representation. In the classification process, the correlation coefficient between the dictionary and the testing samples is combined with classification error to make decisions. Experiments on two hyperspectral remote sensing datasets verify the effectiveness of the proposed algorithm.
Fund:Supported by National Natural Science Foundation of China(No.61772250), Natural Science Foundation of Liaoning Province(No.20170540574), Scientific Research Project of Educational Department of Liaoning Province(No.LJ2019014)
Corresponding Authors:
LIU Deshan, master, professor. His research interests include machine learning, intelligent information processing and pattern recognition.
About author:: WANG Junhao, master student. His research interests include machine learning, dictionary learning and remote sensing image classification.YAN Deqin, Ph.D., professor. His resear-ch interests include machine learning, dictionary learning, deep learning and remote sensing image classification.YAN Huicong, master student. Her research interests include machine learning, intelligent information processing and pattern recognition.
[1] PLAZA A, BENEDIKTSSON J A, BOARDMAN J W, et al. Recent Advances in Techniques for Hyperspectral Image Processing. Remote Sensing of Environment, 2009, 113(S1): S110-S122. [2] RESHMA S, VENI S. Comparative Analysis of Classification Techniques for Crop Classification Using Airborne Hyperspectral Data // Proc of the International Conference on Wireless Communications, Signal Processing and Networking. Washington, USA: IEEE, 2017: 2272-2276. [3] WEI L F, YU M, LIANG Y J, et al. Precise Crop Classification Using Spectral-Spatial-Location Fusion Based on Conditional Random Fields for UAV-Borne Hyperspectral Remote Sensing Imagery. Remote Sensing, 2019, 11(17). DOI: 10.3390/rs11070780. [4] GAIKWAD S V, VIBHUTE A D, KALE K V, et al. Identification and Classification of Water Stressed Crops Using Hyperspectral Data: A Case Study of Paithan Tehsil // Proc of the 2nd International Conference on Communication, Computing and Networking. Berlin, Germany: Springer, 2019: 911-919. [5] CABALLERO D, CALVINI R, AMIGO J M. Chapter 3.3-Hyperspectral Imaging in Crop Fields: Precision Agriculture. Data Handling in Science and Technology, 2020, 32: 453-473. [6] ZHANG Y X, DU B, ZHANG L P, et al. Joint Sparse Representation and Multitask Learning for Hyperspectral Target Detection. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(2): 894-906. [7] KANG X D, ZHANG X P, LI S T, et al. Hyperspectral Anomaly Detection with Attribute and Edge-Preserving Filters. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(10): 5600-5611. [8] WU K, XU G, ZHANG Y X, et al. Hyperspectral Image Target Detection via Integrated Background Suppression with Adaptive Weight Selection. Neurocomputing, 2018, 315: 59-67. [9] DONG Y N, DU B, ZHANG L P, et al. Hyperspectral Target Detection via Adaptive Information-Theoretic Metric Learning with Local Constraints. Remote Sensing, 2018, 10(9). DOI: 10.3390/rs10091415. [10] ZHU D H, DU B, ZHANG L P. Binary-Class Collaborative Representation for Target Detection in Hyperspectral Images. IEEE Geoscience and Remote Sensing Letters, 2019, 16(7): 1100-1104. [11] LEI J, WU L Y, LI Y S, et al. A Novel FPGA-Based Architecture for Fast Automatic Target Detection in Hyperspectral Images. Remote Sensing, 2019, 11(2). DOI: 10.3390/rs11020146. [12] ZHANG X R, HU B L, PAN Z B, et al. Dictionary Learning Based Target Detection for Hyperspectral Image // Proc of the 5th Symposium on Novel Optoelectronic Detection Technology and Application. Bellingham, USA: SPIE, 2019. DOI: 10.1117/12.2519943. [13] ZHU D H, DU B, ZHANG L P. Target Dictionary Construction-Based Sparse Representation Hyperspectral Target Detection Me-thods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(4): 1254-1264. [14] GUO T, LUO F L, ZHANG L, et al. Target Detection in Hyperspectral Imagery via Sparse and Dense Hybrid Representation. IEEE Geoscience and Remote Sensing Letters, 2020, 17(4): 716-720. [15] AYHAN B, KWAN C. Application of Deep Belief Network to Land Cover Classification Using Hyperspectral Images // Proc of the 14th International Symposium on Neural Networks. Berlin, Germany: Springer, 2017: 269-276. [16] GARCIA-SALGADO B P, PONOMARYOV V I, SADOVNYCHIY S, et al. Parallel Supervised Land-Cover Classification System for Hyperspectral and Multispectral Images. Journal of Real-Time Image Processing, 2018, 15(3): 687-704. [17] CHEN F, JIANG H J, VAN DE VOORDE T, et al. Land Cover Mapping in Urban Environments Using Hyperspectral APEX Data: A Study Case in Baden, Switzerland. International Journal of Applied Earth Observation and Geoinformation, 2018, 71: 70-82. [18] THYAGHARAJAN K K, VIGNESH T. Soft Computing Techniques for Land Use and Land Cover Monitoring with Multispectral Remote Sensing Images: A Review. Archives of Computational Methods in Engineering, 2019, 26(2): 275-301. [19] CARRANZA-GARCIA M, GARCIA-GUTIÉRREZ J, RIQUELME J C. A Framework for Evaluating Land Use and Land Cover Classification Using Convolutional Neural Networks. Remote Sensing, 2019, 11(3). DOI: 10.3390/rs11030274. [20] SZABÓ L, BURAI P, DEÁK B, et al. Assessing the Efficiency of Multispectral Satellite and Airborne Hyperspectral Images for Land Cover Mapping in an Aquatic Environment with Emphasis on the Water Caltrop(Trapa Natans). International Journal of Remote Sensing, 2019, 40(13): 5192-5215. [21] CHRISTOVAM L E, PESSOA G G, SHIMABUKURO M H, et al. Land Use and Land Cover Classification Using Hyperspectral Imagery: Evaluating the Performance of Spectral Angle Mapper, Support Vector Machine and Random Forest. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2019, XLII-2/W13: 1841-1847. [22] KANG X D, HUANG Y F, LI S T, et al. Extended Random Walker for Shadow Detection in Very High Resolution Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 2017, 56(2): 867-876. [23] MORALES G, ARTEAGA D, HUAMÁN S G, et al. Shadow Detection in High-Resolution Multispectral Satellite Imagery Using Generative Adversarial Networks // Proc of the XXV IEEE International Conference on Electronics, Electrical Engineering and Computing. Washington, USA: IEEE, 2018. DOI: 10.1109/INTERCON.2018.8526416. [24] BRABANT C, ALVAREZ-VANHARD E, HOUET T. Improving the Classification of Urban Tree Diversity from Very High Spatial Resolution Hyperspectral Images: Comparison of Multiples Techniques[C/OL]. [2019-11-10]. https://halshs.archives-ouvertes.fr/halshs-02191097/document. [25] KAROUI M S, BENHALOUCHE F Z, DEVILLLE Y, et al. Partial Linear NMF-Based Unmixing Methods for Detection and Area Estimation of Photovoltaic Panels in Urban Hyperspectral Remote Sensing Data. Remote Sensing, 2019, 11(18). DOI : 10.3390/rs11182164. [26] ZHANG H X, LI J Y, HUANG Y C, et al. A Nonlocal Weighted Joint Sparse Representation Classification Method for Hyperspectral Imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2056-2065. [27] WENG X H, LEI W H, REN X D. Kernel Sparse Representation for Hyperspectral Unmixing Based on High Mutual Coherence Spectral Library. International Journal of Remote Sensing, 2020, 41(4): 1286-1301. [28] SUN H, REN J C, ZHAO H M, et al. Superpixel Based Feature Specific Sparse Representation for Spectral-Spatial Classification of Hyperspectral Images. Remote Sensing, 2019, 11(5). DOI: 10.3390/rs11050536. [29] WRIGHT J, YANG A Y, GANESH A, et al. Robust Face Reco-gnition via Sparse Representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 31(2): 210-227. [30] CHEN Y, NASRABADI N M, TRAN T D. Hyperspectral Image Classification Using Dictionary-Based Sparse Representation. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(10): 3973-3985. [31] CHEN Y, NASRABADI N M, TRAN T D. Hyperspectral Image Classification via Kernel Sparse Representation. IEEE Transactions on Geoscience and Remote Sensing, 2012, 51(1): 217-231. [32] TU B, ZHANG X F, KANG X D, et al. Hyperspectral Image Classification via Fusing Correlation Coefficient and Joint Sparse Representation. IEEE Geoscience and Remote Sensing Letters, 2018, 15(3): 340-344. [33] TU B, KUANG W L, ZHAO G Z, et al. Hyperspectral Image Classification by Combining Local Binary Pattern and Joint Sparse Representation. International Journal of Remote Sensing, 2019, 40(24): 9484-9500. [34] ZHANG L, YANG M, FENG X C. Sparse Representation or Co-llaborative Representation: Which Helps Face Recognition? // Proc of the International Conference on Computer Vision. Washington, USA: IEEE, 2011: 471-478. [35] JIANG J J, CHEN C, YU Y, et al. Spatial-Aware Collaborative Representation for Hyperspectral Remote Sensing Image Classification. IEEE Geoscience and Remote Sensing Letters, 2017, 14(3): 404-408. [36] CAO X H, GE Y M, LI R J, et al. Hyperspectral Imagery Classification with Deep Metric Learning. Neurocomputing, 2019, 356: 217-227. [37] WASKE B, VAN DER LINDEN S, BENEDIKTSSON J A, et al. Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(7): 2880-2889. [38] LI W, CHEN C, SU H J, et al. Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(7): 3681-3693. [39] YU S Q, JIA S, XU C Y. Convolutional Neural Networks for Hyperspectral Image Classification. Neurocomputing, 2017, 219: 88-98. [40] HE N J, PAOLETTI M E, HAUT J M, et al. Feature Extraction with Multiscale Covariance Maps for Hyperspectral Image Classification. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(2): 755-769. [41] SINGHAL V, AGGARWAL H K, TARIYAL S, et al. Discriminative Robust Deep Dictionary Learning for Hyperspectral Image Cla-ssification. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(9): 5274-5283. [42] TARIYAL S, MAJUMDAR A, SINGH R, et al. Greedy Deep Dictionary Learning[C/OL]. [2019-11-10]. https://arxiv.org/ftp/arxiv/papers/1602/1602.00203.pdf. [43] WEI Y T, ZHOU Y C. Stacked Tensor Subspace Learning for Hyperspectral Image Classification // Proc of the International Joint Conference on Neural Networks. Washington, USA: IEEE, 2016: 1985-1992. [44] HE M Y, LI X H, ZHANG Y F, et al. Hyperspectral Image Cla-ssification Based on Deep Stacking Network // Proc of the IEEE International Geoscience and Remote Sensing Symposium. Washington, USA: IEEE, 2016: 3286-3289. [45] MAGGU J. Deep Transform Learning. Ph.D. Dissertation. Delhi, India: Indraprastha Institute of Information Technology, 2019. [46] GAO H M, YANG Y, YAO D, et al. Hyperspectral Image Classification with Pre-activation Residual Attention Network. IEEE Access, 2019, 31(12): 176587-176599. [47] SUTSKEVER I, HINTON G E. Deep, Narrow Sigmoid Belief Networks Are Universal Approximators. Neural Computation, 2008, 20(11): 2629-2636. [48] LE ROUX N, BENGIO Y. Deep Belief Networks Are Compact Universal Approximators. Neural Computation, 2010, 22(8): 2192-2207. [49] YU S, ZHANG T, MA C, et al. Learning a Discriminative Dictionary with CNN for Image Classification // Proc of the International Conference on Neural Information Processing. Berlin, Germany: Springer, 2016: 185-194. [50] CHEN J B, WANG C Y, MA Z, et al. Remote Sensing Scene Classification Based on Convolutional Neural Networks Pre-trained Using Attention-Guided Sparse Filters. Remote Sensing, 2018, 10(2). DOI: 10.3390/rs10020290. [51] RANGARAJAN A K, PURUSHOTHAMAN R, RAMESH A. Tomato Crop Disease Classification Using Pre-trained Deep Learning Algorithm. Procedia Computer Science, 2018, 133: 1040-1047. [52] ZHOU Y C, WEI Y T. Learning Hierarchical Spectral-Spatial Features for Hyperspectral Image Classification. IEEE Transactions on Cybernetics, 2015, 46(7): 1667-1678. [53] WANG Z Y, LIU J X, XUE J H. Joint Sparse Model-Based Discriminative K-SVD for Hyperspectral Image Classification. Signal Processing, 2017, 133: 144-155. [54] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfa-ces vs. Fisherfaces: Recognition Using Class Specific Linear Projection // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 1996: 43-58. [55] RICHARDS J A, JIA X P. Remote Sensing Digital Image Analysis. Berlin, Germany: Springer, 1999. [56] GUALTIERI J A, CROMP R F. Support Vector Machines for Hyperspectral Remote Sensing Classification. Proceeding of SPIE, 1999, 3584: 221-232.
2020, Vol. 33 
