首页 > 论文 > 激光与光电子学进展 > 55卷 > 10期(pp:103004--1)

基于自动子空间划分的高光谱本征图像分解

Hyperspectral Intrinsic Image Decomposition Based on Automatic Subspace Partitioning

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

摘要

受传感器状态、成像机理、气候、光照等条件的影响, 高光谱遥感图像存在严重的畸变和失真。本征图像分解是计算机视觉及图形学领域广泛应用的图像处理技术, 采用该技术能够获得图像的本质特征。本研究将本征图像分解引入到高光谱图像处理中对原始图像进行本征图像分解。提出了一种基于自动子空间划分的高光谱本征图像分解方法。首先对高光谱图像进行子空间划分, 再对每个子空间应用基于最优化的本征图像分解方法进行分解, 然后对分解得到的反射率本征图像进行高光谱图像分类处理。实验结果表明:基于自动子空间划分的高光谱本征图像分解能够在较大程度上提高高光谱图像的分类精度。

Abstract

Because of the influence of certain operational parameters, such as sensor status, imaging mechanism, climate, and illumination, hyperspectral remote sensing images suffers from serious distortion. Intrinsic image decomposition (IID) is an extensively used image processing technology in the field of computer vision and graphics because it can acquire the essential features of the images that are being processed. IID is introduced to hyperspectral image procesing to decoposite the original images. Accordingly, we propose a hyperspectral IID method based on automatic subspace partitioning. Firstly, the hyperspectral image is divided into subspaces, and the optimal decomposition-based IID method is applied to each subspace. The reflectance intrinsic image that is obtained from the decomposition is further subjected to hyperspectral image classification processing. The experimental results obtained from this study indicate that the proposed method can considerably improve the accuracy of hyperspectral image classification.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:O433.4

DOI:10.3788/lop55.103004

所属栏目:光谱学

基金项目:国家自然科学基金(61801513)

收稿日期:2018-03-14

修改稿日期:2018-05-04

网络出版日期:2018-05-10

作者单位    点击查看

任智伟:航天工程大学航天信息学院, 北京 101416
吴玲达:航天工程大学航天信息学院, 北京 101416

联系人作者:任智伟(juimer@foxmail.com)

【1】Ma P F, Chen L F, Li Q, et al. Simulation of atmospheric nitrous oxide profiles retrieval from AIRS observations[J]. Spectroscopy and Spectral Analysis, 2015, 35(6): 1690-1694.
马鹏飞, 陈良富, 厉青, 等. 红外高光谱资料AIRS反演晴空条件下大气氧化亚氮廓线[J]. 光谱学与光谱分析, 2015, 35(6): 1690-1694.

【2】Rinker J N. Hyperspectral imagery: a new technique for targeting and intelligence[R]. Washington: Directorate for Information Operations and Reports, 1990: 2-7.

【3】Muller-Karger F, Roffer M, Walker N, et al. Satellite remote sensing in support of an integrated ocean observing system[J]. IEEE Geoscience and Remote Sensing Magazine, 2013, 1(4): 8-18.

【4】Zhang C Y, Cheng H F, Chen Z H, et al. The development of hyperspectral remote sensing and its threatening to military equipments[J]. Electro-Optic Technology Application, 2008, 23(1): 10-12
张朝阳, 程海峰, 陈朝辉, 等. 高光谱遥感的发展及其对军事装备的威胁[J]. 光电技术应用, 2008, 23(1): 10-12.

【5】Liu K L, Sun X J, Zhao Z Y, et al. Spectrum imaging test method for camouflage characteristic of ground target[J]. Journal of PLA University of Science and Technology (Natural Science Edition), 2005, 6(2): 166-169.
刘凯龙, 孙向军, 赵志勇, 等. 地面目标伪装特征的高光谱成像检测方法[J]. 解放军理工大学学报(自然科学版), 2005, 6(2): 166-169.

【6】Barrow H G, Tenenbaum J M. Recovering intrinsic scene characteristics from images[M]. New York: Academic Press, 1978: 3-26.

【7】Guo Y B. Research and application of intrinsic image decomposition algorithm[D]. Xiamen: Xiamen University, 2014: 14-16.
郭银斌. 本征图像分解算法研究及其应用[D]. 厦门: 厦门大学, 2014: 14-16

【8】Dai H P. Decomposition method and application of intrinsic image[D]. Tianjin: Tianjin University, 2014: 12-13.
戴海鹏. 本征图像分解方法与应用研究[D]. 天津: 天津大学, 2014: 12-13.

【9】Yang B J. Geometric feature extraction and shape restoration algorithm based on RGB-D image[D]. Zhengzhou: Zhengzhou University, 2015: 9-11.
杨秉杰. 基于RGB-D图像的几何特征提取及形状恢复算法研究[D]. 郑州: 郑州大学, 2015: 9-11.

【10】Land E H, McCann J J. Lightness and retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1): 1-11.

【11】Funt B V, Drew M S, Brockington M. Recovering shading from color images[J]. Lecture Notes in Computer Science, 1992, 588(12): 124-132.

【12】Tappen M F, Freeman W T, Adelson E H. Recovering intrinsic images from a single image[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(9): 1459-1472.

【13】Garces E, Munoz A, Lopez-Moreno J, et al. Intrinsic images by clustering[J]. Computer Graphics Forum, 2012, 31(4): 1415-1424.

【14】Bell S, Bala K, Snavely N. Intrinsic images in the wild[J]. ACM Transactions on Graphics, 2014, 33(4): 1-12.

【15】Bi S, Han X G, Yu Y Z. An L1 image transform for edge-preserving smoothing and scene-level intrinsic decomposition[J]. ACM Transactions on Graphics, 2015, 34(4): 1-12

【16】Yang X C. Research on solving method of intrinsic image based on learning and interaction[D]. Beijing: Beijing Institute of Technology, 2011: 7-10.
杨小灿. 基于学习与交互的本征图像求解方法研究[D]. 北京: 北京理工大学, 2011: 7-10.

【17】Shen J B, Yang X S, Li X L, et al. Intrinsic image decomposition using optimization and user scribbles[J]. IEEE Transactions on Cybernetics, 2013, 43(2): 425-436.

【18】Zheng Y Q, Sato I, Sato Y. Illumination and reflectance spectra separation of a hyperspectral image meets low-rank matrix factorization[C]. IEEE Conference on Computer Vision and pattern Recognition, 2015: 1779-1787.

【19】Chen X. Intrinsic image decomposition of spectral images[D]. Nanjing: Nanjing University, 2017: 4-9.
陈希. 光谱图像本质分解[D]. 南京: 南京大学, 2017: 4-9.

【20】Dai Q H, Lin X , Xu C X, et al. Decomposition method and device for hyperspectral intrinsic image: CN104700109A[P]. 2015-06-10.
戴琼海, 林星, 许晨雪, 等. 高光谱本征图像的分解方法及装置: CN104700109A[P]. 2015-06-10.

【21】Gu Y F, Zhang Y. Feature extraction based on automatic subspace partition for hyperspectral images[J]. Remote Sensing Technology and Application, 2003, 18(6): 384-387.
谷延锋, 张晔. 基于自动子空间划分的高光谱数据特征提取[J]. 遥感技术与应用, 2003, 18(6): 384-387.

【22】Su H J, Sheng Y H, Du P J. Study on auto-subspace partition for band selection of hyperspectral image[J]. Geo-Information Science, 2007, 9(4): 123-128.
苏红军, 盛业华, 杜培军. 自动子空间划分在高光谱影像波段选择中的应用[J]. 地球信息科学, 2007, 9(4): 123-128.

引用该论文

Ren Zhiwei,Wu Lingda. Hyperspectral Intrinsic Image Decomposition Based on Automatic Subspace Partitioning[J]. Laser & Optoelectronics Progress, 2018, 55(10): 103004

任智伟,吴玲达. 基于自动子空间划分的高光谱本征图像分解[J]. 激光与光电子学进展, 2018, 55(10): 103004

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