基于稀疏表示及光谱信息的高光谱遥感图像分类

宋相法; 焦李成

doi:10.3724/SP.J.1146.2011.00540

基于稀疏表示及光谱信息的高光谱遥感图像分类

doi: 10.3724/SP.J.1146.2011.00540

宋相法^1,,
焦李成¹

基金项目:

国家自然科学基金(60803097, 60971112, 60971128, 60970067, 61072108, 61072106)，高等学校学科创新引智计划(111计划) (B07048)和中央高校基本科研业务费专项资金(JY10000902001, K50510020001, JY10000902045)资助课题

计量
- 文章访问数: 4791
- HTML全文浏览量: 168
- PDF下载量: 3335
- 被引次数: 0
出版历程
- 收稿日期: 2011-06-02
- 修回日期: 2011-10-31
- 刊出日期: 2012-02-19

Classification of Hyperspectral Remote Sensing Image Based on Sparse Representation and Spectral Information

Song Xiang-Fa^1
,,
Jiao Li-Cheng¹

摘要

摘要: 该文结合稀疏表示及光谱信息提出了一种新的高光谱遥感图像分类算法。首先提出利用高光谱遥感图像数据集构造学习字典，然后根据学习字典计算每个像元的稀疏系数，从而获得像元的稀疏表示特征，最后根据稀疏表示特征和光谱信息分别构造随机森林，通过投票机制得到最终的分类结果。在AVIRIS高光谱遥感图像上的实验结果表明：该文所提方法能够提高分类效果，且其分类总精度和Kappa系数要高于光谱信息和稀疏表示特征方法。
- 图像处理 /
- 高光谱遥感图像 /
- 稀疏表示 /
- 分类 /
- 随机森林
Abstract: This paper presents a novel classification algorithm of hyperspectral remote sensing image based on sparse representation and spectral information. First, a learning dictionary is obtained based on hyperspectral remote sensing image data set, and then the sparse coefficient of each pixel is calculated according to the learning dictionary. As a result, sparse representation feature is obtained. Finally, random forests are respectively constructed based on sparse representation feature and spectral information, and the classification result is decided by voting strategy. Experiments on AVIRIS hyperspectral remote sensing image justify the effectiveness of the algorithm. The experimental results indicate that the proposed method has better performance than methods based on spectral and sparse representation respectively, and has a higher overall accuracy and Kappa coefficient.
- Image processing /
- Hyperspectral remote sensing image /
- Sparse representation /
- Classification /
- Random forests

HTML全文

参考文献(1)

Plaza A, Benediktsson J A, Boardman J, et al.. Recent advances in techniques for hyperspectral image processing [J]. Remote Sensing of Environment, 2009, 113(9): 110-122.[2] 邸韡, 潘泉, 赵永强, 等. 高光谱图像波段子集模糊积分融合异常检测[J]. 电子与信息学报, 2008, 30(2): 267-271.Di Wei, Pan Quan, Zhao Yong-qiang, et al.. Anomaly target detection in hyperspectral imagery based on band subset fusion by fuzzy integral[J]. Journal of Electronics Information Technology, 2008, 30(2): 267-271.[3] 宋娟, 吴成柯, 张静, 等. 基于分类和陪集码的高光谱图像无损压缩[J]. 电子与信息学报, 2011, 33(1): 231-234.Song Juan, Wu Cheng-ke, Zhang Jing, et al.. Lossless compression of hyperspectral images based on classification and coset coding [J]. Journal of Electronics Information Technology, 2011, 33(1): 231-234.[4] Chan J C W and Paelinckx D. Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery[J]. Remote Sensing of Environment, 2008, 112(6): 2999-3011.[5] Ham J, Chen Y, Crawford M, et al.. Investigation of the random forest framework for classification of hyperspectral data [J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(3): 492-501.[6] Shahshahani B M and Landgrebe D A. The effect of unlabeled samples in reducing the small sample size problem and mitigating the hughes phenomenon[J]. IEEE Transactions on Geoscience and Remote Sensing, 1994, 32(5): 1087-1095.[7] Breiman L. Random forests [J]. Machine Learning, 2001, 45(1): 5-32.[8] Olshausen B A and Field D J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images [J]. Nature, 1996, 381(6583): 607-609.[9] Iordache M D, Dias J M B, and Plaza A. Sparse unmixing of hyperspectral data. [J]. IEEE Transactions on Geoscience and Remote Sensing, 2011, 49(6): 2014-2039.[10] Wright J, Ma Y, Mairal J, et al.. Sparse representations for computer vision and pattern recognition [J]. Proceedings of the IEEE, 2010, 98(6): 1031-1044.[11] 余慧敏, 方广有. 压缩感知理论在探地雷达三维成像中的应用[J]. 电子与信息学报, 2010, 32(1): 12-16.Yu Hui-min and Fang Guang-you. Research on compressive sensing based 3D imaging method applied to ground penetrating radar [J]. Journal of Electronics Information Technology, 2010, 32(1): 12-16.[12] 屈乐乐, 方广有, 杨天虹. 压缩感知理论在频率步进探地雷达偏移成像中的应用[J]. 电子与信息学报, 2011, 33(1): 21-26.Qu Le-le, Fang Guang-you, and Yang Tian-hong. The application of compressed sensing to stepped-frequency ground penetrating radar migration imaging [J]. Journal of Electronics Information Technology, 2011, 33(1): 21-26.[13] 孙玉宝, 韦志辉, 吴敏, 等. 稀疏性正则化的图像泊松去噪算法[J]. 电子学报, 2011, 39(2): 285-290.Sun Yu-bao, Wei Zhi-hui, Wu Min, et al.. Image poisson denoising using sparse representations [J]. Acta Elcetronica Sinica, 2011, 39(2): 285-290.[14] Raina R, Battle A, Lee H, et al.. Self-taught learning: transfer learning from unlabeled data[C]. International Conference on Machine Learning, Corvallis, 2007: 759-766. [15] Qiao Li-shan, Chen Song-can, and Tan Xiao-yang. Sparsity preserving projection with applications to face recognition [J]. Pattern Recognition, 2010, 43(1): 331-341.[16] Han Ya-hong, Wu Fei, Zhuang Yue-ting, et al.. Multi-label transfer learning with sparse representation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2010, 20(8): 1110-1121.[17] Aharon M, Elad M, and Bruckstein A. K-SVD: an algorithm for designing over-complete dictionaries for sparse representation [J]. IEEE Transactions on Signal Processing, 2006, 54(11): 4311-4322.[18] Mairal J, Bach F, Ponce J, et al.. Online learning for matrix factorization and sparse coding [J]. Journal of Machine Learning Research, 2010, 11(1): 19-60.[19] 童庆禧, 张兵, 郑兰芬. 高光谱遙感: 原理、技术与应用[M]. 北京: 高等教育出版社, 2006: 262-272.Tong Qing-xi, Zhang Bing, and Zheng Lan-fen. Hyperspectral Remote Sensing Theory, Technology and Applications [M]. Beijing: Higer Education Press, 2006: 262-272.[20] Breiman L. Bagging predictors [J]. Machine Learning, 1996, 24(2): 123-140.

施引文献

资源附件(0)

访问统计