|
- 2018
一种切空间协同表示的高光谱遥感影像分类方法
|
Abstract:
协同表示分类(collaborative representation classification,CRC)算法近年来成为高光谱遥感分类的研究热点。地物类别间区分性不高会严重影响现有CRC算法的性能。流形结构可有效地解决非线性问题,并解决高光谱遥感影像因数据冗余导致的类别间区分性低的问题。提出了一种基于切空间的高光谱遥感影像协同表示分类算法(tangent space collaborative representation classification,TCRC)和一种基于欧氏距离的自适应加权的切空间协同表示分类算法(weighted tangent space collaborative representation classification,WTCRC)。TCRC算法利用测试样本的切平面来估计区域流形,在测试样本的切空间中使用协同表示算法,寻找测试样本在各类训练样本中的最优线性表示估计,并用其最小误差来对测试样本进行分类。在此基础上,利用测试样本邻域像元、训练样本与测试样本的欧氏距离作为权矩阵来自适应调整各样本对测试样本的影响。实验采用ROSIS(reflective optics system image spectro-meter)和AVIRIS(airbone visible infrared imaging spectrometer)高光谱遥感影像对所提出算法的性能进行了评价,结果表明TCRC和WTCRC在分类效果上比CRC有明显的提升,WTCRC相较于TCRC具有更好的分类效果,具有更强鲁棒性
[1] | Melgani F, Bruzzone L. Classification of Hyperspectral Remote Sensing Images with Support Vector Machines[J]. <em>IEEE Transactions on Geoscience and Remote Sensing</em>, 2004,42(8):1778-1790 |
[2] | Li W, Tramel E W, Prasad S, et al. Nearest Regularized Subspace for Hyperspectral Classification[J], <em>IEEE Transactions on Geoscience and Remote Sensing</em>,2014,52(1):477-489 |
[3] | Li W, Du Q, Zhang F, et al. Collaborative Representation Based Nearest Neighbor Classifier for Hyperspectral Imagery[J]. <em>IEEE Geoscience and Remote Sensing Letters</em>,2015,12(2):389-393 |
[4] | Zhang L, Yang M, Feng X. Sparse Representation or Collaborative Representation:Which Helps Face Recognition?[C]. IEEE International Conference on Computer Vision,Barcelona, Spain, 2011 |
[5] | Li W, Du Q. Joint Within-Class Collaborative Representation for Hyper Spectral Image Classification[J]. <em>IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,</em>2014, 7(6):2200-2208 |
[6] | Li J, Zhang H, Zhang L. Column-Generation Kernel Nonlocal Joint Collaborative Representation for Hyperspectral Image Classification[J]. <em>ISPRS Journal of Photogrammetry and Remote Sensing,</em>2014, 94:25-36 |
[7] | Li J, Zhang H, Huang Y, et al. Hyperspectral Image Classification by Nonlocal Joint Collaborative Representation with a Locally Adaptive Dictionary[J]. <em>IEEE Transactions on Geoscience and Remote Sensing</em>, 2014,52(6):3707-3719 |
[8] | Ni D, Ma H. Classification of Hyperspectral Image Based on Sparse Representation in Tangent Space[J]. <em>IEEE Geoscience and Remote Sensing Letters</em>,2015,12(4):786-790 |
[9] | Tong Qingxi, Zhang Bing, Zheng Lanfen. Hyperspectral Remote Sensing[M]. Beijing:Higher Education Press, 2006(童庆禧,张兵, 郑兰芬.高光谱遥感[M].北京:高等教育出版社,2006) |
[10] | Wright J, Yang A Y, Ganesh A, et al. Robust Face Recognition via Sparse Representation[J]. <em>IEEE Transactions on Pattern Analysis and Machine Intelligence,</em>2009, 31(2):210-227 |
[11] | Chen Y, Nasrabadi N M, Tran T D. Hyper-spectral Image Classification Using Dictionary-Based Sparse Representation[J]. <em>IEEE Transactions on Geoscience and Remote Sensing</em>, 2011,49(10):3973-3985 |