基于卷积核哈希学习的高光谱图像分类

薛朝辉; 张瑜娟

doi:10.11834/jrs.20220359

智能遥感处理与分析 | 浏览量 : 0 下载量: 306 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

基于卷积核哈希学习的高光谱图像分类
Supervised Hashing with RBF Kernel and Convolution for Hyperspectral image classification
2022年26卷第4期页码：722-738
纸质出版日期： 2022-04-07 ，
DOI： 10.11834/jrs.20220359

扫描看全文

薛朝辉，张瑜娟.2022.基于卷积核哈希学习的高光谱图像分类.遥感学报，26（4）： 722-738

Xue Z H and Zhang Y J. 2022. Hyperspectral image classification method based on Supervised Hashing with RBF Kernel and Convolution. National Remote Sensing Bulletin， 26（4）：722-738
薛朝辉，张瑜娟.2022.基于卷积核哈希学习的高光谱图像分类.遥感学报，26（4）： 722-738 DOI： 10.11834/jrs.20220359.

Xue Z H and Zhang Y J. 2022. Hyperspectral image classification method based on Supervised Hashing with RBF Kernel and Convolution. National Remote Sensing Bulletin， 26（4）：722-738 DOI： 10.11834/jrs.20220359.

摘要

高光谱遥感可同步获取地表覆盖空间影像和连续且精细的光谱数据，能够实现对地物的精细分类与识别。然而，高光谱图像的高维特性对分类带来巨大挑战。为此，本文探讨了一种基于卷积核哈希学习的高光谱图像分类方法。哈希学习可以将高维信息表达为低维哈希编码，通过计算哈希编码内积并借助最小汉明距离实现分类。为了有效表达非线性数据，又发展了核哈希学习方法。然而，直接应用核哈希学习进行高光谱图像分类存在运行速度慢和未考虑空间邻域信息的不足。为此，本文在核哈希学习中引入径向基函数RBF（Radial Basis Function）作为损失函数以提高运行效率；同时，借助四维卷积操作充分表达空间邻域信息，提出了基于卷积核哈希学习的高光谱图像分类方法CKSH（Supervised Hashing with RBF Kernel and Convolution），同时探讨了该方法在仅利用光谱特征和光谱—空间联合特征上的分类效果。在国际通用测试数据Indian Pines和University of Pavia上进行了实验，结果表明：本文提出的CKSH方法优于传统分类方法（支持向量机、随机子空间）和其他哈希学习方法（如谱哈希、球哈希、监督离散哈希、潜在因子哈希等），同时在不同训练样本数量条件下均取得了较高的分类精度，达到96.12%（Indian Pines，10%的训练样本）和98.00%（University of Pavia，5%的训练样本），从而验证了该方法的有效性。

Abstract

Hyperspectral remote sensing can obtain both spatial images and continuous spectral data of land cover

thus realizing the classification and identification of ground objects. However

the high-dimensional characteristics of hyperspectral images pose great challenges to classification. Therefore

this paper discusses a hyperspectral image classification method based on Hash learning. Hash learning can switch high-dimensional information to low-dimensional binary encoding

and achieve classification by calculating encoding internal product and using hamming distance.

To effectively express nonlinear data

one supervised hashing method is proposed. However

the disadvantage of Hash learning are that they run slowly and lack consideration for spatial neighborhood information. Therefore

this paper introduces RBF kernel to improve efficiency. In addition

it uses four-dimensional convolution to fully express spatial information

namely Supervised Hashing with RBF Kernel and Convolution (CKSH).

Experiments were carried out on the international general test data. Experimental results show that the proposed method is superior to traditional classification methods and other hash learning. Under different percentage conditions of training samples

it has achieved high classification accuracy and reached 96.12% (Indian Pine

10%) and 98.00% (University of Pavia

5%)

which verified the effectiveness of proposed method.

In view of the two problems that loss function of KSH using the L2 norm causes low efficiency

and it does not consider spatial information. This paper uses four-dimensional convolution to introduce spatial information

and applies the RBF kernel instead of the L2 norm. Experiments on general test data sets have confirmed the advantages of CKSH in classification accuracy and runtime. The reason for high accuracy and efficiency has two hands. On the one hand

CKSH uses four-dimensional convolution to mine underlying structural information. Therefore

the obtained binary encoding conducive to improving the classification performance. On the other hand

using the RBF kernel as loss function can significantly reduce the arithmetic series.

关键词

遥感高光谱图像哈希学习RBF四维卷积特征提取光谱—空间分类

Keywords

remote sensinghyperspectral imageHash learningRBFfour-Dimensional convolutionfeature extractionspectral-spatial classification

references

Belgiu M and Drăguţ L. 2016. Random forest in remote sensing: a review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114: 24-31 [DOI: 10.1016/j.isprsjprs.2016.01.011http://dx.doi.org/10.1016/j.isprsjprs.2016.01.011]

Chen Y, Nasrabadi N M and Tran T D. 2011. Hyperspectral image classification using dictionary-based sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3973-3985 [DOI: 10.1109/TGRS.2011.2129595http://dx.doi.org/10.1109/TGRS.2011.2129595]

Dalla Mura M, Benediktsson J A, Waske B and Bruzzone L. 2010a. Morphological attribute profiles for the analysis of very high resolution images. IEEE Transactions on Geoscience and Remote Sensing, 48(10): 3747-3762 [DOI: 10.1109/TGRS.2010.2048116http://dx.doi.org/10.1109/TGRS.2010.2048116]

Dalla Mura M, Benediktsson J A, Waske B and Bruzzone L. 2010b. Extended profiles with morphological attribute filters for the analysis of hyperspectral data. International Journal of Remote Sensing, 31(22): 5975-5991 [DOI: 10.1080/01431161.2010.512425http://dx.doi.org/10.1080/01431161.2010.512425]

Du P J, Xia J S, Xue Z H, Tan K, Su H J and Bao R. 2016. Review of hyperspectral remote sensing image classification. Journal of Remote Sensing, 20(2): 236-256

杜培军, 夏俊士, 薛朝辉, 谭琨, 苏红军, 鲍蕊. 2016. 高光谱遥感影像分类研究进展. 遥感学报, 20(2): 236-256 [DOI: 10.11834/jrs.20165022http://dx.doi.org/10.11834/jrs.20165022]

Fang L Y, Liu Z L and Song W W. 2019. Deep hashing neural networks for hyperspectral image feature extraction. IEEE Geoscience and Remote Sensing Letters, 16(9): 1412-1416 [DOI: 10.1109/LGRS.2019.2899823http://dx.doi.org/10.1109/LGRS.2019.2899823]

Fauvel M, Tarabalka Y, Benediktsson J A, Chanussot J and Tilton J C. 2012. Advances in spectral-spatial classification of hyperspectral images. Proceedings of the IEEE, 2012, 101(3): 652-675 [DOI: 10.1109/JPROC.2012.2197589http://dx.doi.org/10.1109/JPROC.2012.2197589]

Gong Y and Lazebnik S. 2011. Iterative quantization: a procrustean approach to learning binary codes//Proceedings of CVPR 2011. Colorado Springs: IEEE: 817-824 [DOI: 10.1109/CVPR.2011.5995432http://dx.doi.org/10.1109/CVPR.2011.5995432]

Gurram P and Kwon H. 2013. Contextual SVM using Hilbert space embedding for hyperspectral classification. IEEE Geoscience and Remote Sensing Letters, 10(5): 1031-1035 [DOI: 10.1109/LGRS.2012.2227934http://dx.doi.org/10.1109/LGRS.2012.2227934]

Heo J P, Lee Y, He J F, Chang S F and Yoon S E. 2012. Spherical hashing//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE: 2957-2964 [DOI: 10.1109/CVPR.2012.6248024http://dx.doi.org/10.1109/CVPR.2012.6248024]

Ho T K. 1998. The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8): 832-844 [DOI: 10.1109/34.709601http://dx.doi.org/10.1109/34.709601]

Jiang K, Que Q C and Kulis B. 2015. Revisiting kernelized locality-sensitive hashing for improved large-scale image retrieval//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE: 4933-4941 [DOI: 10.1109/CVPR.2015.7299127http://dx.doi.org/10.1109/CVPR.2015.7299127]

Li J, Bioucas-Dias J M and Plaza A. 2012. Spectral-spatial hyperspectral image segmentation using subspace multinomial logistic regression and Markov random ﬁelds. IEEE Transactions on Geoscience and Remote Sensing, 50(3): 809-823 [DOI: 10.1109/TGRS.2011.2162649http://dx.doi.org/10.1109/TGRS.2011.2162649]

Li S T, Song W W, Fang L Y, Chen Y S, Ghamisi P and Benediktsson J A. 2019. Deep learning for hyperspectral image classification: an overview. IEEE Transactions on Geoscience and Remote Sensing, 57(9): 6690-6709 [DOI: 10.1109/TGRS.2019.2907932http://dx.doi.org/10.1109/TGRS.2019.2907932]

Lin G S, Shen C H, Shi Q F, van den Hengel A and Suter D. 2014. Fast supervised hashing with decision trees for high-dimensional data//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE: 1971-1978 [DOI: 10.1109/CVPR.2014.253http://dx.doi.org/10.1109/CVPR.2014.253]

Lin G S, Shen C H, Suter D and van den Hengel A. 2013. A general two-step approach to learning-based hashing. Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney: IEEE: 2552-2559 [DOI: 10.1109/ICCV.2013.317http://dx.doi.org/10.1109/ICCV.2013.317]

Liu W, Wang J, Ji R R, Jiang Y G and Chang S F. 2012. Supervised hashing with kernels//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE: 2074-2081 [DOI: 10.1109/CVPR.2012.6247912http://dx.doi.org/10.1109/CVPR.2012.6247912]

Shen F M, Shen C H, Liu W and Shen H T. 2015. Supervised discrete hashing//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE: 37-45 [DOI: 10.1109/CVPR.2015.7298598http://dx.doi.org/10.1109/CVPR.2015.7298598]

Tarabalka Y, Fauvel M, Chanussot J and Benediktsson J A. 2010. SVM-and MRF-based method for accurate classiﬁcation of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 7(4): 736-740 [DOI: 10.1109/LGRS.2010.2047711http://dx.doi.org/10.1109/LGRS.2010.2047711]

Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707

童庆禧, 张兵, 张立福. 2016. 中国高光谱遥感的前沿进展. 遥感学报, 20(5): 689-707 [DOI: 10.11834/jrs.20166264http://dx.doi.org/10.11834/jrs.20166264]

Tuia D, Camps-Valls G, Matasci G and Kanevski M. 2010. Learning relevant image features with multiple-kernel classiﬁcation. IEEE Transactions on Geoscience and Remote Sensing, 48(10): 3780-3791 [DOI: 10.1109/TGRS.2010.2049496http://dx.doi.org/10.1109/TGRS.2010.2049496]

Weiss Y, Torralba A and Fergus R. 2009. Spectral hashing//Proceedings of the 21st International Conference on Neural Information Processing Systems. Vancouver: ACM: 1753-1760

Yu C Y, Zhao M, Song M P, Wang Y L, Li F, Han R and Chang C I. 2019. Hyperspectral image Classiﬁcation method based on CNN architecture embedding with hashing semantic feature. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(6): 1866-1881 [DOI: 10.1109/JSTARS.2019.2911987http://dx.doi.org/10.1109/JSTARS.2019.2911987]

Yuan H L, Lu Y, Yang L N, Luo H W and Tang Y Y. 2013. Sparse representation using contextual information for hyperspectral image classification//Proceedings of 2013 IEEE International Conference on Cybernetics. Lausanne: IEEE: 138-143 [DOI: 10.1109/CYBConf.2013.6617422http://dx.doi.org/10.1109/CYBConf.2013.6617422]

Zhang B. 2016. Advancement of hyperspectral image processing and information extraction. Journal of Remote Sensing, 20(5): 1062-1090

张兵. 2016. 高光谱图像处理与信息提取前沿. 遥感学报, 20(5): 1062-1090 [DOI: 10.11834/jrs.20166179http://dx.doi.org/10.11834/jrs.20166179]

Zhang L P and Li J Y. 2016. Development and prospect of sparse representation-based hyperspectral image processing and analysis. Journal of Remote Sensing, 20(5): 1091-1101

张良培, 李家艺. 2016. 高光谱图像稀疏信息处理综述与展望. 遥感学报, 20(5): 1091-1101 [DOI: 10.11834/jrs.20166050http://dx.doi.org/10.11834/jrs.20166050]

Zhang L P and Shen H F. 2016. Progress and future of remote sensing data fusion. Journal of Remote Sensing, 20(5): 1050-1061

张良培, 沈焕锋. 2016. 遥感数据融合的进展与前瞻. 遥感学报, 20(5): 1050-1061 [DOI: 10.11834/jrs.20166243http://dx.doi.org/10.11834/jrs.20166243]

Zhang P C, Zhang W, Li W J and Guo M Y. 2014. Supervised hashing with latent factor model//Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. Gold Coast: ACM: 173-182 [DOI: 10.1145/2600428.2609600http://dx.doi.org/10.1145/2600428.2609600]

Zhong Z H, Fan B, Ding K, Li H C, Xiang S M and Pan C H. 2016. Efﬁcient multiple feature fusion with hashing for hyperspectral imagery Classiﬁcation: a comparative study. IEEE Transactions on Geoscience and Remote Sensing, 54(8): 4461-4478 [DOI: 10.1109/TGRS.2016.2542342http://dx.doi.org/10.1109/TGRS.2016.2542342]

Zikiou N, Lahdir M and Helbert D. 2020. Hyperspectral image classification using graph-based wavelet transform. International Journal of Remote Sensing, 41(7): 2624-2643 [DOI: 10.1080/01431161.2019.1694194http://dx.doi.org/10.1080/01431161.2019.1694194]

文章被引用时，请邮件提醒。

提交

5米光学02星多光谱影像农田防护林信息提取

高光谱图像类别独立的域适应分类

光谱—频域属性模式融合的高光谱遥感图像变化检测

基于多方向自适应感知网络的高光谱遥感图像分类