首页 > 论文 > 激光与光电子学进展 > 57卷 > 12期(pp:121102--1)

结合地物类别和低秩特性的高光谱图像降噪

Hyperspectral Image Denoising By Combining Ground Object Features with Low-Rank Characteristics

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对现有方法不易确定划分高光谱图像子块的大小和个数,仅考虑子块内低秩性等不足,提出一种结合地物类别和低秩特性的高光谱图像降噪方法。根据地物数据先验知识的类别数,简单划分子块的个数,指定最优参数明确分块大小,再通过相同地物中像素空间和光谱的相关性定义同物空谱低秩特性,最后结合整幅高光谱图像的光谱低秩特性,并根据低秩矩阵恢复模型求解降噪图像。在Washington DC Mall和Indian Pines数据集上进行实验,结果表明:所提方法不仅对每一类地物噪声的降噪效果有所提高,而且针对更为严重的随机噪声和稀疏噪声的混合噪声,也能够达到更好的降噪效果。

Abstract

It is difficult to determine the size and number of sub-blocks in a hyperspectral image using the existing methods because of the low rank of the sub-blocks and other associated disadvantages. Therefore, we propose a hyperspectral image denoising method, which combines the features of the ground objects with the low-rank characteristics. Further, the number of sub-blocks are divided with respect to the number of categories of prior knowledge of ground object data, and optimal parameters are specified for determining the size of the blocks. Then, the low-rank characteristics of the same object space spectrum are obtained based on the correlation of the pixel space and spectrum with respect to the same feature. Finally, the spectral low-rank characteristics of the entire hyperspectral image are combined, and the noise-reduced image is obtained according to the low-rank matrix recovery model. Experiments conducted on the Washington DC Mall and Indian Pines datasets demonstrate that the proposed method not only improves the noise reduction effect with respect to each type of ground noise but also targets mixed noise containing more severe random noise and sparse noise.

广告组1 - 空间光调制器+DMD
补充资料

中图分类号:TP751

DOI:10.3788/LOP57.121102

所属栏目:成像系统

基金项目:国家重点研发计划、国家自然科学基金、上海市自然科学基金、上海市科委部分地方院校能力建设项目;

收稿日期:2019-08-23

修改稿日期:2019-11-08

网络出版日期:2020-06-01

作者单位    点击查看

黄冬梅:上海海洋大学信息学院, 上海 201306上海电力大学, 上海 200090
李永兰:上海海洋大学信息学院, 上海 201306
张明华:上海海洋大学信息学院, 上海 201306
宋巍:上海海洋大学信息学院, 上海 201306

联系人作者:张明华(mhzhang@shou.edu.cn)

备注:国家重点研发计划、国家自然科学基金、上海市自然科学基金、上海市科委部分地方院校能力建设项目;

【1】Tong Q X, Zhang B, Zhang L F. Current progress of hyperspectral remote sensing in China [J]. Journal of Remote Sensing. 2016, 20(5): 689-707.
童庆禧, 张兵, 张立福. 中国高光谱遥感的前沿进展 [J]. 遥感学报. 2016, 20(5): 689-707.
Tong Q X, Zhang B, Zhang L F. Current progress of hyperspectral remote sensing in China [J]. Journal of Remote Sensing. 2016, 20(5): 689-707.
童庆禧, 张兵, 张立福. 中国高光谱遥感的前沿进展 [J]. 遥感学报. 2016, 20(5): 689-707.

【2】Cui R M. Hyperspectral image denoising and classification Xi''an: [D]. Xidian University. 2018, 17-19.
崔荣梅. 高光谱图像去噪及分类技术研究 [D]. 西安: 西安电子科技大学. 2018, 17-19.

【3】Liu L X, Li M Z, Zhao Z G, et al. Recent advances of hyperspectral imaging application in biomedicine [J]. Chinese Journal of Lasers. 2018, 45(2): 0207017.
刘立新, 李梦珠, 赵志刚, 等. 高光谱成像技术在生物医学中的应用进展 [J]. 中国激光. 2018, 45(2): 0207017.

【4】Skauli T. Sensor noise informed representation of hyperspectral data, with benefits for image storage and processing [J]. Optics Express. 2011, 19(14): 13031-13046.

【5】Sun L. Signal-dependent noise parameter estimation of hyperspectral remote sensing images [J]. Spectroscopy Letters. 2015, 48(10): 717-725.

【6】Zhang B. Advancement of hyperspectral image processing and information extraction [J]. Journal of Remote Sensing. 2016, 20(5): 1062-1090.
张兵. 高光谱图像处理与信息提取前沿 [J]. 遥感学报. 2016, 20(5): 1062-1090.

【7】Dabov K, Foi A, Katkovnik V, et al. Image denoising by sparse 3-D transform-domain collaborative filtering [J]. IEEE Transactions on Image Processing. 2007, 16(8): 2080-2095.

【8】Zhang H Y, He W, Zhang L P, et al. Hyperspectral image restoration using low-rank matrix recovery [J]. IEEE Transactions on Geoscience and Remote Sensing. 2014, 52(8): 4729-4743.

【9】Wang M D, Yu J, Xue J H, et al. Denoising of hyperspectral images using group low-rank representation [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2016, 9(9): 4420-4427.

【10】Fan H X, Li J, Yuan Q Q, et al. Hyperspectral image denoising with bilinear low rank matrix factorization [J]. Signal Processing. 2019, 163: 132-152.

【11】Chen G Y, Qian S E. Denoising of hyperspectral imagery using principal component analysis and wavelet shrinkage [J]. IEEE Transactions on Geoscience and Remote Sensing. 2011, 49(3): 973-980.

【12】Xue J Z, Zhao Y Q, Liao W Z, et al. Joint spatial and spectral low-rank regularization for hyperspectral image denoising [J]. IEEE Transactions on Geoscience and Remote Sensing. 2018, 56(4): 1940-1958.

【13】Fan H Y, Chen Y J, Guo Y L, et al. Hyperspectral image restoration using low-rank tensor recovery [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2017, 10(10): 4589-4604.

【14】Zhang X H, Hao R F, Li T Y. Hyperspectral abnormal target detection based on low rank and sparse matrix decomposition-sparse representation [J]. Laser & Optoelectronics Progress. 2019, 56(4): 042801.
张晓慧, 郝润芳, 李廷鱼. 基于低秩稀疏矩阵分解和稀疏字典表达的高光谱异常目标检测 [J]. 激光与光电子学进展. 2019, 56(4): 042801.

【15】Wang L G, Zhao C H. Hyperspectral image processing [M]. Heidelberg: Springer. 2016.

【16】Rasti B, Scheunders P, Ghamisi P, et al. Noise reduction in hyperspectral imagery: overview and application [J]. Remote Sensing. 2018, 10(3): 482.

【17】He W, Zhang H Y, Zhang L P, et al. Hyperspectral image denoising via noise-adjusted iterative low-rank matrix approximation [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2015, 8(6): 3050-3061.

【18】He W, Zhang H Y, Zhang L P, et al. Total-variation-regularized low-rank matrix factorization for hyperspectral image restoration [J]. IEEE Transactions on Geoscience and Remote Sensing. 2016, 54(1): 178-188.

【19】Fan F, Ma Y, Li C, low-rank representation[J]. Information Sciences, et al. 2017, 397/398: 48-68.

【20】Yin X, Ma J. Image fusion method based on entropy rate segmentation and multi-scale decomposition [J]. Laser & Optoelectronics Progress. 2018, 55(1): 011011.
殷向, 马骏. 基于熵率分割和多尺度分解的图像融合方法 [J]. 激光与光电子学进展. 2018, 55(1): 011011.

【21】Yao D. Hyperspectral image denoising and inpainting based on low-rank representation [D]. Beijing: University of Chinese Academy of Sciences. 2018.
姚丹. 基于低秩表示的高光谱图像降噪和修复算法研究 [D]. 北京: 中国科学院大学. 2018.

【22】Lin Z C, Liu R S. -10-18)[2019-03-01] . https:∥arxiv. 2013, org/abs/1009: 5055.

【23】Wright J, Ganesh A, Rao S, et al. Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization . [C]∥Proceedings of the 23rd Annual Conference on Neural Information Processing Systems, December 7-10, 2009, Vancouver, British Columbia, Canada. New York: Curran Associates, Inc. 2009, 1-9.

【24】Zhou T, Tao D. GoDec: randomized lowrank & sparse matrix decomposition in noisy case . [C]∥International Conference on Machine Learning, ICML 2011, June 28 - July 2, 2011, Bellevue, Washington, USA. [S.l.: s.n.]. 2011, 33-40.

【25】Zhao Y Q, Yang J X, Zhang Q Y, et al. Hyperspectral imagery super-resolution by sparse representation and spectral regularization [J]. EURASIP Journal on Advances in Signal Processing. 2011, 2011: 87.

【26】MultiSpec. HYDICE data[2019-03-01]. https:∥engineering.purdue.edu/~biehl/MultiSpec/hyperspectral.html.[2019-03-01]. 0.

【27】Remote sensing laboratory. Hyperspectral datasets: AVIRIS Indian Pines[2019-03-01]. https:∥rslab.ut.ac.ir/data.[2019-03-01]. 0.

引用该论文

Huang Dongmei,Li Yonglan,Zhang Minghua,Song Wei. Hyperspectral Image Denoising By Combining Ground Object Features with Low-Rank Characteristics[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121102

黄冬梅,李永兰,张明华,宋巍. 结合地物类别和低秩特性的高光谱图像降噪[J]. 激光与光电子学进展, 2020, 57(12): 121102

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF