多核融合多尺度特征的高光谱影像地物分类

王庆超; 付光远; 汪洪桥; 王超

doi:doi:10.3788/ope.20182604.0980

光学精密工程, 2018, 26 (4): 980, 网络出版: 2018-08-28

多核融合多尺度特征的高光谱影像地物分类

Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification

论文大纲

王庆超付光远 ^*汪洪桥王超

作者单位

火箭军工程大学信息工程系, 陕西西安 710025

高光谱影像稀疏表示多尺度多核学习地物分类 hyperspectral image SRC multi-scale multiple kernel learning land cover classification

摘要

对于高光谱影像地物分类问题, 为更加有效地利用像元空间信息和光谱信息, 提高地物分类精度, 提出了多核融合多尺度特征的分类方法。首先, 通过多尺度空间滤波和PCA白化, 提取出多尺度特征;接着在核稀疏表示分类器内使用多核方式对分别表示每项特征, 在分类器内实现特征自动融合, 根据子核与理想核、子核之间距离求取核组合的权重, 使用训练集所构成的字典在特征空间内对待测样本进行线性表示, 根据每类地物的重构误差确定待测像元所属地物类别。实验结果表明: 对于Indian Pines影像和Pavia University影像总体分类精度分别达到99.51%和97.96%, 较传统方法明显提高, 并且对于小样本地物识别精度也都能达到90%以上。本文算法对于高光谱影像地物具有更强的识别能力, 并且具有较强的稳定性和鲁棒性。

Abstract

In order to make full use of the spatial information and spectral information and improve the classification accuracy of hyperspectral imager, a fusion multi-scale feature with multiple kernel learning method was proposed in this paper. Firstly, multi-scale features were extracted by multi-scale spatial filtering and PCA whitening. Then multiple kernels were used to represent the multi-scale feature in the framework of kernel sparse representation classifier. The kernel weight was computed according to the CKTA between the sub-kernels and ideal kernel and the CKTA between sub-kernels. The unlabeled pixels were linearly represented by the training samples in the feature space. According to the reconstruction error of each kind of land cover, the category of unlabeled pixels was determined. The experiment results showed that the overall classification accuracy in Indian Pines images and Pavia University images reached 99.51% and 97.96%, which significantly surpassed the traditional method. The accuracy of object recognition of small sample could also reach more than 90%. It can be seen that algorithm proposed has stronger recognition ability for hyperspectral images land cover.

参考文献

[1] 何芳, 王榕, 于强, 等. 加权空谱局部保持投影的高光谱图像特征提取［J］. 光学精密工程, 2017, 25(1): 263-273.

HE F, WANG R, YU Q, et al.. Feature extraction of hyperspectral images of weighted spatial and spectral locality preserving projection (WSSLPP)［J］. Opt. Precision Eng., 2017, 25(1): 263-273. (in Chinese)

[2] DELLACQUA F, GAMBA P, FERRARI A, et al.. Exploiting spectral and spatial information in hyperspectral urban data with high resolution［J］. IEEE Geoscience and Remote Sensing Letters, 2004, 1(4): 322-326.

[3] YUAN H L, TANG Y Y, LU Y, et al.. Spectral-spatial classification of hyperspectral image based on discriminant analysis［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(6): 2035-2043.

[4] 黄鸿, 郑新磊. 加权空-谱与最近邻分类器相结合的高光谱图像分类［J］. 光学精密工程, 2016, 24(4): 873-881.

HUANG H, ZHENG X L. Hyperspectral image classification with combination of weighted spatial-spectral and KNN［J］. Opt. Precision Eng., 2016, 24(4): 873-881. (in Chinese)

[5] FU W, LI SH T, FANG L Y, et al.. Hyperspectral image classification via shape-adaptive joint sparse representation［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(2): 556-567.

[6] FAUVEL M, TARABALKA Y, BENEDIKTSSON J A, et al.. Advances in spectral-spatial classification of hyperspectral images［J］. Proceedings of the IEEE, 2013, 101(3): 652-675.

[7] CHEN Y, NASRABADI N M, TRAN T D. Hyperspectral image classification via kernel sparse representation［J］. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 217-231.

[8] LI SH SH, NI L, JIA X P, et al.. Multi-scale superpixel spectral-spatial classification of hyperspectral images［J］. International Journal of Remote Sensing, 2016, 37(20): 4905-4922.

[9] REININGHAUS J, HUBER S, BAUER U, et al.. A stable multi-scale kernel for topological machine learning［C］. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2015: 4741-4748.

[10] 唐中奇, 付光远, 陈进, 等. 基于多尺度分割的高光谱图像稀疏表示与分类［J］. 光学精密工程, 2015, 23(9): 2708-2714.

TANG ZH Q, FU G Y, CHEN J, et al.. Multiscale segmentation-based sparse coding for hyperspectral image classification［J］. Opt. Precision Eng., 2015, 23(9): 2708-2714. (in Chinese)

[11] YIN J, LIU ZH H, JIN ZH, et al.. Kernel sparse representation based classification［J］. Neurocomputing, 2012, 77(1): 120-128.

[12] CORTES C, MOHRI M, ROSTAMIZADEH A. Algorithms for learning kernels based on centered alignment［J］. The Journal of Machine Learning Research, 2012, 13(1): 795-828.

[13] HE ZH, LI J B. Multiple data-dependent kernel for classification of hyperspectral images［J］. Expert Systems with Applications, 2015, 42(3): 1118-1135.

王庆超, 付光远, 汪洪桥, 王超. 多核融合多尺度特征的高光谱影像地物分类[J]. 光学精密工程, 2018, 26(4): 980. WANG Qing-chao, FU Guang-yuan, WANG Hong-qiao, WANG Chao. Fusion of multi-scale feature using multiple kernel learning for hyperspectral image land cover classification[J]. Optics and Precision Engineering, 2018, 26(4): 980.

多核融合多尺度特征的高光谱影像地物分类

关于本站 Cookie 的使用提示

全站搜索

多核融合多尺度特征的高光谱影像地物分类

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索