计算机科学 ›› 2014, Vol. 41 ›› Issue (10): 113-116.doi: 10.11896/j.issn.1002-137X.2014.10.026

• 2013’和谐人机环境联合学术会议 • 上一篇    下一篇

基于稀疏表示和词袋模型的高光谱图像分类

任越美,张艳宁,魏巍,张秀伟   

  1. 西北工业大学计算机学院 西安710072;河南工业职业技术学院计算机工程系 南阳473000;西北工业大学计算机学院 西安710072;西北工业大学计算机学院 西安710072;西北工业大学计算机学院 西安710072
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受中国自然科学基金重点项目(61231016),中国自然科学基金(61272288,61201291,61303123),河南省科技攻关计划(142102210557),西工大校基础研究基金(JCT20130108,JCT20130109)资助

Classification of Hyperspectral Image Based on Sparse Representation and Bag of Words

REN Yue-mei,ZHANG Yan-ning,WEI Wei and ZHANG Xiu-wei   

  • Online:2018-11-14 Published:2018-11-14

摘要: 为增强高光谱图像稀疏表示分类方法中稀疏字典的表征能力并充分利用高光谱图像的光谱信息和空间信息,提出了一种新的基于稀疏表示和词袋模型的高光谱遥感图像分类方法。首先利用词袋模型算法结合高光谱遥感图像数据集生成各类别专业码本,作为字典中对应的原子构造稀疏表示字典。在计算每个像元的对应稀疏表示字典中的稀疏表示特征时,利用空间连续性约束对像元的稀疏表示系数进行空间维的约束。最后根据最小重构误差实现高光谱图像分类。高光谱遥感数据实验结果表明:所提方法能有效提高分类效果,并且其分类精度和Kappa系数都优于其他稀疏表示方法以及单独使用光谱信息的方法。

关键词: 图像处理,高光谱图像,稀疏表示,词袋模型,空间连续性

Abstract: To enhance representation ability of the sparse dictionary for hyperspectral image classification using sparse representation and make full use of spectral information and spatial information of hyperspectral image,a novel hyperspectral image classification method based on sparse representation and bag of words was proposed.First,some professional dictionaries of each class are generated by bag of words algorithm based on the hyperspectral remote sensing image dataset,and the sparse representation dictionary is obtained by merging these professional dictionaries.Then,the sparse coefficient of each pixel is calculated according to the sparse representation dictionary,and the spatial continuity is used to constraint the coefficient by using the information of its neighborhoods.Finally,the classification of the objects is determined by computing the minimum reconstruction error of it on each professional dictionary.Experiments on hyperspectral remote sensing images indicate that the proposed method has better performance,a higher overall accuracy and Kappa coefficient than other sparse representation methods and the method based on spectral information respectively.

Key words: Image processing,Hyperspectral image,Sparse representation,Bag of words,Spatial continuity

[1] Plaza A,Benediktsson J A,Boardman J W,et al.Recentadvances in techniques for hyperspectral image processing [J].Remote Sensing of Environment,2009,113(1):110-122
[2] Geng Xiu-rui,Zhang Xia,Chen Zheng-chao,et al.Classification algorithm based on spatial continuity for hyperspectral image [J].Journal of Infrared Millimeter Waves,2004,23(4):209-302
[3] Mathieu F,Jón A B,Jocelyn C,et al.Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles [J].IEEE Transactions on Geoscience and Remote Sensing,2008,46( 11):3804-3814
[4] 高恒振,万建伟,粘永健,等.一种基于谱域-空域组合特征支持向量机的高光谱图像分类算法[J].宇航学报,2011,32(4):917-921
[5] Fauvel M,Chanussot J,et al.A spatial-spectral kernel-based approach for the classification of remote-sensing images [J].Pattern Recognition,2012,45(1):381-392
[6] Fu Z,Antonio R.Discriminant Absorption-Feature Learning for Material Classification [J].IEEE Transaction of Geoscience and Remote Sensing,2011,49(5):1536-1556
[7] Haq Q S,Shi Li-xin,Tao Lin-mi,et al.A L1-minimization based approach for hyperspectral data classification[C]∥Proceedings of 2010 International Conference on Remote Sensing(ICRS).2010,2:139-142
[8] Yi Chen,Nasrabadi N M,Tran T D.Hyperspectral image classification using dictionary-based sparse representation [J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(10):3973-3985
[9] 宋相法,焦李成.基于稀疏表示及光谱信息的高光谱遥感图像分类[J].电子与信息学报,2012,34(2):268-272
[10] Haq S,Tao Q L,et al.A Fast and Robust Sparse Approach for Hyperspectral Data Classification Using a Few Labeled Samples[J].IEEE Transactions on Geoscience and Remote Sensing,2012,99:1-16
[11] Iordache M D,Dias J M B,Plaza A.Sparse unmixing of hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(6):2014-2039
[12] Wright J,Yang A,Ganesh A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):201-227
[13] Elhamifar E,Vidal R.Robust classification using structuredsparse representation[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2011:1873-1879
[14] Weizman L,Goldberger J.Urban-Area Segmentation Using Vi-sual Words[J].IEEE Geoscience and Remote Sensing Letters,2009,6(3):388-392
[15] https://engineering.purdue.edu/~biehl/MultiSpec/hyperspec-tral.html

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!