基于SSLPP算法对高光谱遥感影像分类

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z11): 333-336.

基于SSLPP算法对高光谱遥感影像分类

潘银松,王攀峰,黄鸿,刘艳

重庆大学光电技术及系统教育部重点实验室重庆400044;重庆大学光电技术及系统教育部重点实验室重庆400044;重庆大学光电技术及系统教育部重点实验室重庆400044;重庆大学光电技术及系统教育部重点实验室重庆400044

出版日期:2018-11-16 发布日期:2018-11-16
基金资助:
本文受国家自然科学基金(61101168),中国博士后科学基金项目(2012M511906)资助

Hyperspectral Remote Sensing Image Classification Based on SSLPP

PAN Yin-song,WANG Pan-feng,HUANG Hong and LIU Yan

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 局部保持投影算法为非监督维数约简算法,没有有效利用样本数据的类别信息,不能有效提取鉴别特征。针对此问题,提出一种半监督局部保持投影(SSLPP)算法。该算法以少量有标记数据和无标记数据作为训练样本集构造出本征图G_i,并有区别地对待标记样本与无标记样本,增大同类样本点之间的权重,更有利于鉴别特征提取。在AVIRIS KSC和Botswana高光谱遥感影像数据集上的实验结果表明,SSLPP算法能够较为有效地发现高维空间中数据的内蕴结构,使得总体分类精度得到较为明显的改善。

关键词: 高光谱影像,维数约简,半监督学习,半监督局部保持投影

Abstract: Without using the data category information,Locality Preserving Projection algorithm is an unsupervised algorithm in the dimension reduction of hyperspectral images,so it has not a very good performance in the aspect of feature extraction．To resolve this problem,an algorithm based on semi-supervised locality preserving projection (SSLPP) is proposed in this paper．A graph G_i is constructed by SSLPP combined with the information of unlabeled samples and labeled samples whose are treated in different ways,therefore increasing the weights of congener samples and being beneficial to feature extraction．Experiments on the AVIRIS KSC set and Botswana data set show that the algorithm proposed in the paper can find the high dimensional space data intrinsic structure,effectively improving the overall accuracy of the classification.

Key words: Hyperspectral images,Dimension reduction,Semi-supervised learning,Semi-supervised locality preserving projection

潘银松,王攀峰,黄鸿,刘艳. 基于SSLPP算法对高光谱遥感影像分类[J]. 计算机科学, 2013, 40(Z11): 333-336. https://doi.org/

PAN Yin-song,WANG Pan-feng,HUANG Hong and LIU Yan. Hyperspectral Remote Sensing Image Classification Based on SSLPP[J]. Computer Science, 2013, 40(Z11): 333-336. https://doi.org/

参考文献

[1] 王立志,黄鸿,冯海亮.基于MFA与kNNS算法的高光谱遥感影像分类[J].计算机科学,2012,39(6):261-265
[2] Yang Guo-peng,Zhou xin,Yu Xu-chu,et al．Relevance vector machine for hyperspectral imagery unmixing [J]．Acta Electro-nica Sinica,2010,38(12):2751-2756
[3] Yin Ji-hao,Wang Yan,Wang Yi-song．A revised multi-target detection approach in hyperspectral image [J]．Acta Electronica Sinica,2010,8(9):1975-1978
[4] Luo Si-wei,Zhao Lian-wei.Manifold learning algorithms based on spectral graph theory [J]．Journal of Computer Research and Development,2006,3(7):1173-1179
[5] He Lin,Pan Quan,et al．Re search Advance on Target Detection for Hyperspectral Imagery [J]．Acta Electronica Sinica,2009,37(9):2016-2024
[6] Wang Li-zhi,Huang Hong,Feng Hai-liang．HyperspectralRemote Sensing Image Classification Based on SSMFA and kNNS [J]．Acta Electronica Sinica,2012,40(4):780-787
[7] Ma Li,Crawford M M,Tian Jin-wen．Local manifold learning-based k-nearest-neighbor for hyperspectral image classification [J]．IEEE Transactions on Geoscience and Remote Sensing,2010,48(11):4099-4109
[8] Huang H,Li J W,Feng H L．Subspaces versus Submanifolds:A comparative study in small sample size problem [J]．International Journal of Pattern Recognition And Artificial Intelligence,2009,23(3):463-490
[9] Turk M,Pentland A．Eigenfaces for recognition [J]．Journal of Cognitive Neuroscience,1991,3(1):71-86
[10] Belhumeur P,Hespanha J,Kriegman D．Eigenfaces vs．Fisher-faces:Recognition using class specific linear projection [J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,20(7):711-720
[11] He Xiao-fei,Cai Deng,Yan Shui-cheng,et al．Neighborhood preserving embedding [A]∥Proceedings of the 10^thIEEE International Conference Computer Vision (ICCV’05)[C]．Beijing,2005:1208-1213
[12] He Xiao-fei,Yan Shui-cheng,Hu Yu-xiao,et al.Face recognitionusing Laplacianfaces [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,7(3):328-340
[13] Yan Shui-cheng,Xu Dong,Zhang Ben-yu,et al．Graph embed-ding and extensions:A general framework for dimensionality reduction [J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,9(1):40-51
[14] Fu Yun,Yan Shui-cheng,Huang T S．Classification and feature extraction by simplexization [J]．IEEE Transactions on Information Forensics and Security,2008,3(1):91-100
[15] Fu Yun,Yan Shui-cheng,Huang T S.Discriminant simplex analysis [A]∥Proceedings of the IEEE Conference ICASSP[C]．Las Vegas,NV,2008:3333-3336
[16] Bau T C,Sarkar S,Healey G．Hyperspectral region classification using a three-dimensional gabor filterbank [J]．IEEE Transactions on Geoseience and Remote Sensing,2010,48(9):3457-3464
[17] Acito N,Diani M,Corsini G．Hyperspectral signal subspaceidentification in the presence of rare signal components [J]．IEEE Transactions on Gescience and Remote Sensing,2010,48(4):1940-1954
[18] Yang J M,Kuo B C,Yu P T,et al．Adynamic sbuspace method for hypersoectral image classification [J]．IEEE Transactions on Geoscience and Remote Sensing,2010,48(7):2840-2853

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed