Intrinsic Image Recovery From Remote Sensing Hyperspectral Images

被引:26
作者
Jin, Xudong [1 ]
Gu, Yanfeng [1 ]
Liu, Tianzhu [1 ]
机构
[1] Harbin Inst Technol, Sch Elect & Informat Engn, Harbin 150001, Heilongjiang, Peoples R China
来源
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 2019年 / 57卷 / 01期
关键词
Classification; feature extraction; hyperspectral images (HSIs); intrinsic image decomposition (IID); reflectance; FEATURE-EXTRACTION; CLASSIFICATION; DECOMPOSITION; PROFILES; FUSION;
D O I
10.1109/TGRS.2018.2853178
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
In this paper, a novel reflectance model is proposed to recover intrinsic images from remote sensing hyperspectral images (HSIs). Intrinsic image recovery is a well-known challenging and underconstrained problem in computer vision, and it becomes even more severely illposed for HSIs. To reduce the uncertainties and improve the recovery accuracy, two kinds of priors are introduced: 1) shading prior which describes the geometric relation between illuminate and object surface and 2) reflectance prior based on L1-graph coding, which describes the relation between pigment density with reflectance. These priors can effectively eliminate the reflectance inhomogeneity caused by surface normal changes or pigment density variations other than material changes. Then, a noniterative optimization method is proposed to combine the shading prior and reflectance prior, with which closed-form solutions can be derived and thus avoided falling into local optimums. The experimental results demonstrate that the proposed method can efficiently improve the spectral reflectance homogeneity within a class while preserving the image boundaries; it also produces a competitive performance with the state of the art when utilizing the extracted intrinsic hyperspectral reflectance feature in the task of HSI classification.
引用
收藏
页码:224 / 238
页数:15
相关论文
共 48 条
[1]  
[Anonymous], 2004, EROSION DILATION
[2]   Intrinsic Scene Properties from a Single RGB-D Image [J].
Barron, Jonathan T. ;
Malik, Jitendra .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (04) :690-703
[3]   Shape, Illumination, and Reflectance from Shading [J].
Barron, Jonathan T. ;
Malik, Jitendra .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2015, 37 (08) :1670-1687
[4]  
Barron JT, 2012, PROC CVPR IEEE, P334, DOI 10.1109/CVPR.2012.6247693
[5]  
Barron JT, 2012, LECT NOTES COMPUT SC, V7575, P57, DOI 10.1007/978-3-642-33765-9_5
[6]   Lambertian reflectance and linear subspaces [J].
Basri, R ;
Jacobs, DW .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2003, 25 (02) :218-233
[7]   Photometric stereo with general, unknown lighting [J].
Basri, Ronen ;
Jacobs, David ;
Kemelmacher, Ira .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2007, 72 (03) :239-257
[8]   Classification of hyperspectral data from urban areas based on extended morphological profiles [J].
Benediktsson, JA ;
Palmason, JA ;
Sveinsson, JR .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2005, 43 (03) :480-491
[9]   Classification and feature extraction for remote sensing images from urban areas based on morphological transformations [J].
Benediktsson, JA ;
Pesaresi, M ;
Arnason, K .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (09) :1940-1949
[10]   Composite kernels for hyperspectral image classification [J].
Camps-Valls, G ;
Gomez-Chova, L ;
Muñoz-Marí, J ;
Vila-Francés, J ;
Calpe-Maravilla, J .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2006, 3 (01) :93-97