多分辨率低秩导向滤波的热红外图像空间融合
Spatial fusion enhancement of thermal infrared images based on multi-resolution analysis and low-rank guided filter
- 2021年25卷第11期 页码:2255-2269
纸质出版日期: 2021-11-07
DOI: 10.11834/jrs.20219358
扫 描 看 全 文
浏览全部资源
扫码关注微信
纸质出版日期: 2021-11-07 ,
扫 描 看 全 文
苗馨远,张晔,张钧萍.2021.多分辨率低秩导向滤波的热红外图像空间融合.遥感学报,25(11): 2255-2269
Miao X Y, Zhang Y and Zhang J P. 2021. Spatial fusion enhancement of thermal infrared images based on multi-resolution analysis and low-rank guided filter. National Remote Sensing Bulletin, 25(11):2255-2269
热红外遥感图像由于其特定的成像方式,包含目标特有的发射率及温度等特征。然而,热红外遥感图像较低的空间分辨率却限制了其广泛应用。随着遥感技术的发展,同一区域获得的多源遥感图像可以提供更为完备的目标信息,使得利用多源融合技术实现热红外图像空间分辨率增强与亚像素级特征提取成为可能。为此,本文提出了一种基于多分辨率自适应低秩表达与残差信息迁移的热红外图像空间超分辨算法,该算法通过可见光与热红外图像融合的方式实现热红外图像空间特性的自适应融合增强。本文算法优势主要体现在以下几个方面:(1)基于多分辨率的超像素分割,使用超像素块代替传统的方块作为低秩恢复单元,自适应地调整单元内空间特性以保持单元内地物类型的稳定并抑制结构性噪声;(2)通过构建导向线性滤波器,在保护热红外图像光谱信息的前提下,实现可见光图像精细空间特征向热红外图像的迁移;(3)在低分辨层建立增强热红外图像残差与可见光图像残差之间关联并迁移至高分辨层,在保证超分辨图像细节信息的前提下,实现热红外图像空间超分辨。为了验证算法的有效性,本文采用2014年IGARSS数据融合竞赛提供的可见光与热红外实验数据进行实验,并与融合竞赛中表现最为优异的监督图特征融合方法进行比较,并从温度反演精度以及分类精度两个方面评价超分辨效果。实验结果表明,本文提出的方法其噪声抑制效果、空间平滑效果、边缘锐化效果更为优异,超分辨热红外图像有着更为精细的空间信息,并且对于不同区域类型均能较好的保护热红外图像光谱信息。对于不同地物类型,融合超分辨图像有较高的亚像素温度反演精度以及更高的分类精度,其温度反演误差小于1 K,总体分类精度较原热红外图像提升20%以上。
Owing to the special imaging principle in the long-wave infrared region
thermal infrared remote sensing images contain the temperature and emissivity features of targets. However
the low spatial resolution of thermal infrared images limits its wide application. With the development of remote sensing technology
multisource remote sensing images in the same region can provide complete information of a target for researchers. On the basis of the high spatial resolution of visible band images
thermal infrared image fusion enhancement and subpixel feature extraction have a high application value.
Therefore
a new method named subpixel temperature retrieval of thermal infrared images based on multiresolution superpixel low-rank representation and residual correlation is proposed in this paper. The method achieves two goals by fusing visible and thermal infrared images in a super-resolution way: (1) enhancement of spatial characteristics for thermal infrared images based on adaptive fusion and (2) estimation of subpixel temperature and super resolution for thermal infrared images.
The main processing and advantages of the algorithm are listed as follows: (1) For superpixel segmentation and low-rank restoration at multiresolution
superpixel blocks
instead of traditional blocks
are used as low-rank restoration units to enhance the stability of species in each unit and suppress structural noise. (2) Through constructing a guided linear filter
the high-spatial-resolution feature of the visible image can be transferred to the thermal infrared image while keeping the spectral information of the thermal infrared image unchanged. (3) For the estimation of subpixel temperature and super resolution of thermal infrared images
the correlation between the residuals of VIS and fusion images is established at the low-resolution layer and applied to the high-resolution layer to preserve image details.
To validate the effectiveness of the proposed method
the visible and thermal infrared data in the 2014 IGARSS data fusion contest are used for experiments. The algorithm is evaluated in three aspects: (1) the improvement of spatial characteristics for thermal infrared images through adaptive low-rank representation
such as noise suppression
intraclass smoothing
and edge enhancement; (2) the spectral information protection of thermal infrared images in homogeneous and heterogenous regions; (3) the super-resolution effect and the accuracy of subpixel temperature retrieval. Compared with the traditional supervised graph-based feature fusion method
the proposed method has the best edge-sharpening
noise suppression
and spatial smoothing effects. It can protect the spectral information of thermal infrared images for different region types. The super-resolution image obtained by the proposed algorithm achieves high-temperature retrieval accuracy
and the overall root-mean-square error is less than 1 K. The average classification accuracy is improved by more than 20%.
亚像素温度反演可见光、热红外图像融合导向滤波器多分辨率空间自适应低秩表达超像素分割
subpixel temperature retrievalvisible and thermal infrared image fusionguided filtermulti-resolution self-adaption low-rank representationsuper-pixel segmentation
Cai R R and Wang B. 2017. Hyperspectral imagery restoration based on low-rank representation. Journal of Fudan University (Natural Science), 56(3): 346-358
蔡荣荣, 王斌. 2017. 一种基于低秩表示的高光谱图像恢复方法. 复旦学报(自然科学版), 56(3): 346-358 [DOI: 10.15943/j.cnki.fdxb-jns.2017.03.011http://dx.doi.org/10.15943/j.cnki.fdxb-jns.2017.03.011]
Candes E J and Donoho D L. 2000. Curvelets, multiresolution representation, and scaling laws//Proceedings SPIE 4119, Wavelet Applications in Signal and Image Processing VIII. San Diego: SPIE: 4119 [DOI: 10.1117/12.408568]
Chen J S, Li Z Q and Huang B. 2017. Linear spectral clustering superpixel. IEEE Transactions on Image Processing, 26(7): 3317-3330 [DOI: 10.1109/TIP.2017.2651389http://dx.doi.org/10.1109/TIP.2017.2651389]
Da Cunha A L, Zhou J and Do M N. 2006. The nonsubsampled contourlet transform: theory, design, and applications. IEEE Transactions on Image Processing, 15(10): 3089-3101 [DOI: 10.1109/TIP.2006.877507http://dx.doi.org/10.1109/TIP.2006.877507]
Ding M, Wei L and Wang B F. 2013. Research on fusion method for infrared and visible images via compressive sensing. Infrared Physics and Technology, 57: 56-67 [DOI: 10.1016/j.infrared.2012.12.014http://dx.doi.org/10.1016/j.infrared.2012.12.014]
Do M N and Vetterli M. 2005. The contourlet transform: an efficient directional multiresolution image representation. IEEE Transactions on Image Processing, 14(12): 2091-2106 [DOI: 10.1109/TIP.2005.859376http://dx.doi.org/10.1109/TIP.2005.859376]
Fasbender D, Radoux J and Bogaert P. 2008. Bayesian data fusion for adaptable image pansharpening. IEEE Transactions on Geoscience and Remote Sensing, 46(6): 1847-1857 [DOI: 10.1109/TGRS.2008.917131http://dx.doi.org/10.1109/TGRS.2008.917131]
Foster L A, Brock B W, Cutler M E J and Diotri F. 2012. A physically based method for estimating supraglacial debris thickness from thermal band remote-sensing data. Journal of Glaciology, 58(210): 677-691 [DOI: 10.3189/2012JoG11J194http://dx.doi.org/10.3189/2012JoG11J194]
Garcia F, Mirbach B, Ottersten B, Grandidier F and Cuesta Á. 2010. Pixel weighted average strategy for depth sensor data fusion//2010 IEEE International Conference on Image Processing. Hong Kong, China: IEEE: 2805-2808 [
DOI 10.1109/ICIP.2010.5651112]
Gillespie A, Rokugawa S, Matsunaga T, Cothern J S, Hook S and Kahle A B. 1998. A temperature and emissivity separation algorithm for Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images. IEEE Transactions on Geoscience and Remote Sensing, 36(4): 1113-1126 [DOI: 10.1109/36.700995http://dx.doi.org/10.1109/36.700995]
He K M, Sun J and Tang X O. 2010. Guided image filtering//Proceeding of 11th European Conference on Computer Vision. Heraklion: Springer: 1-14 [DOI: 10.1007/978-3-642-15549-9_1http://dx.doi.org/10.1007/978-3-642-15549-9_1]
Jiao L C and Tan S. 2003. Development and prospect of image multiscale geometric analysis. Acta Electronica Sinica, 31(12A): 1975-1981 (焦李成, 谭山. 2003. 图像的多尺度几何分析: 回顾和展望. 电子学报, 31(12A): 1975-1981) [DOI: 10.3321/j.issn:0372-2112.2003.z1.007]
Kang X D, Li S T and Benediktsson J A. 2014. Spectral–spatial hyperspectral image classification with edge-preserving filtering. IEEE Transactions on Geoscience and Remote Sensing, 52(5): 2666-2677 [DOI: 10.1109/TGRS.2013.2264508http://dx.doi.org/10.1109/TGRS.2013.2264508]
Kustas W P, Norman J M, Anderson M C and French A N. 2003. Estimating subpixel surface temperatures and energy fluxes from the vegetation index-radiometric temperature relationship. Remote Sensing of Environment, 85(4): 429-440 [DOI: 10.1016/s0034-4257(03)00036-1http://dx.doi.org/10.1016/s0034-4257(03)00036-1]
Li H, Manjunath B S and Mitra S K. 1995. Multisensor image fusion using the wavelet transform. Graphical Models and Image Processing, 57(3): 235-245
Li X and Qin S Y. 2011. Efficient fusion for infrared and visible images based on compressive sensing principle. IET Image Processing, 5(2): 141-147 [DOI: 10.1049/iet-ipr.2010.0084http://dx.doi.org/10.1049/iet-ipr.2010.0084]
Liao W Z, Huang X, Van Coillie F, Gautama S, Pižurica A, Philips W, Liu H, Zhu T T, Shimoni M, Moser G and Tuia D. 2015a. Processing of multiresolution thermal hyperspectral and digital color data: outcome of the 2014 IEEE GRSS data fusion contest. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2984-2996 [DOI: 10.1109/JSTARS.2015.2420582http://dx.doi.org/10.1109/JSTARS.2015.2420582]
Liao W Z, Huang X, Van Coillie F, Thoonen G, Pižurica A, Scheunders P and Philips W. 2015b. Two-stage fusion of thermal hyperspectral and visible RGB image by PCA and Guided filter//2015 7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS). Tokyo: IEEE: 1-4 [DOI: 10.1109/WHISPERS.2015.8075405http://dx.doi.org/10.1109/WHISPERS.2015.8075405]
Li Z L, Duan S B, Tang B H, Wu Y, Ren H Z and Yan G j. 2016. Review of methods for land surface temperature derived from thermal infrared remotely sensed data. National Remote Sensing Bulletin, 20(005):899-920
李召良, 段四波, 唐伯惠, 吴骅, 任华忠, 阎广建. 2016. 热红外地表温度遥感反演方法研究进展. 遥感学报,20(005):899-920
Manolakis D, Golowich S and DiPietro R S. 2014. Long-wave infrared hyperspectral remote sensing of chemical clouds: a focus on signal processing approaches. IEEE Signal Processing Magazine, 31(4): 120-141 [DOI: 10.1109/MSP.2013.2294804http://dx.doi.org/10.1109/MSP.2013.2294804]
Manolakis D, Pieper M, Truslow E, Lockwood R, Weisner A, Jacobson J and Cooley T. 2019. Longwave infrared hyperspectral imaging: principles, progress, and challenges. IEEE Geoscience and Remote Sensing Magazine, 7(2): 72-100 [DOI: 10.1109/MGRS.2018.2889610http://dx.doi.org/10.1109/MGRS.2018.2889610]
Mao K B, Qin Z H and Xu B. 2005. Method for land surface temperature retrieval from ASTER data. Journal of Institute of Surveying and Mapping, 22(1): 40-42
毛克彪, 覃志豪, 徐斌. 2005. 针对ASTER数据的单窗算法. 测绘学院学报, 22(1): 40-42 [DOI: 10.3969/j.issn.1673-6338.2005.01.013http://dx.doi.org/10.3969/j.issn.1673-6338.2005.01.013]
Pieri D and Abrams M. 2004. ASTER watches the world's volcanoes: a new paradigm for volcanological observations from orbit. Journal of Volcanology and Geothermal Research, 135(1/2): 13-28 [DOI: 10.1016/j.jvolgeores.2003.12.018http://dx.doi.org/10.1016/j.jvolgeores.2003.12.018]
Qin Z H, Zhang M H, Karnieli A and Berliner P. 2001. Mono-window algorithm for retrieving land surface temperature from landsat TM6 data. Acta Geographica Sinica, 56(4): 456-466
覃志豪, Zhang M H, Karnieli A, Berliner P. 2001. 用陆地卫星TM6数据演算地表温度的单窗算法. 地理学报, 56(4): 456-466 [DOI: 10.11821/xb200104009http://dx.doi.org/10.11821/xb200104009]
Sun L, Jeon B, Zheng Y H, Xu Y and Wu Z B. 2017. Homogeneous region based low rank representation in hidden field for hyperspectral classification//2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). Fort Worth: IEEE: 4758-4761 [DOI: 10.1109/IGARSS.2017.8128065http://dx.doi.org/10.1109/IGARSS.2017.8128065]
Van Der Meer F D, Van Der Werff H M A, Van Ruitenbeek F J A, Hecker C A, Bakker W H, Noomen M F, Van Der meijde M, Carranza E J M, De Smeth J B and Woldai T. 2012. Multi- and hyperspectral geologic remote sensing: a review. International Journal of Applied Earth Observation and Geoinformation, 14(1): 112-128 [DOI: 10.1016/j.jag.2011.08.002http://dx.doi.org/10.1016/j.jag.2011.08.002]
Wang C C, Yang G J, Ma Z and Xing Z R. 2009. Fusion of VNIR and thermal infrared remote sensing data based on GA-SOFM neural network. Geo-Spatial Information Science, 12(4): 271-280 [DOI: 10.1007/s11806-009-0093-4http://dx.doi.org/10.1007/s11806-009-0093-4]
Wang J D, Li X W, Sun X M and Liu Q. 2000. Inversion of temperature of non-isothermal pixel components using thermal radiation directional model. Chinese Science E Series, 30(S1): 54-60
王锦地, 李小文, 孙晓敏, 刘强. 2000. 用热辐射方向性模型反演非同温像元组分温度. 中国科学(E辑), 30(S1): 54-60 [DOI: 10.3321/j.issn:1006-9275.2000.z1.008http://dx.doi.org/10.3321/j.issn:1006-9275.2000.z1.008]
Wang J N, Jiao L C, Liu H Y, Yang S Y and Liu F. 2015. Hyperspectral image classification by spatial–spectral derivative-aided kernel joint sparse representation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2485-2500 [DOI: 10.1109/JSTARS.2015.2394330http://dx.doi.org/10.1109/JSTARS.2015.2394330]
Wang Z, Bovik A C, Sheikh H R and Simoncelli E P. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4): 600-612 [DOI: 10.1109/TIP.2003.819861http://dx.doi.org/10.1109/TIP.2003.819861]
Weng Q H, Rajasekar U and Hu X F. 2011. Modeling urban heat islands and their relationship with impervious surface and vegetation abundance by using ASTER images. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 4080-4089 [DOI: 10.1109/tgrs.2011.2128874http://dx.doi.org/10.1109/tgrs.2011.2128874]
Wright J, Ganesh A, Rao S, Peng Y and Ma Y. 2009. Robust principal component analysis: exact recovery of corrupted low-rank matrices via convex optimization. Neuro Computing, 87(4): 3-56 [DOI: 10.1109/CVPR.2016.567http://dx.doi.org/10.1109/CVPR.2016.567]
Wu Y Y, Jin C, Pang L W, Zhao J L, Song Y, Hu T G, Zhao D R and Xu J F. 2019. Distribution characteristics of surface thermal environment in Zhejiang province based on thermal infrared remote sensing. National Remote Sensing Bulletin, 234
) (吴文渊, 金城, 庞毓雯, 赵丽佳, 宋瑜, 胡潭高, 赵登荣,徐俊峰. 2019. 热红外遥感浙江地表热环境分布研究. 遥感学报, 23(4))
Xu Y, Wu Z B, Wei Z H, Mura M D, Chanussot J and Bertozzi A. 2016. GAS plume detection in hyperspectral video sequence using low rank representation//2016 IEEE International Conference on Image Processing (ICIP). Phoenix: IEEE: 2221-2225 [DOI: 10.1109/ICIP.2016.7532753http://dx.doi.org/10.1109/ICIP.2016.7532753]
Zhou T Y and Tao D C. 2011. Godec: Randomized low-rank and sparse matrix decomposition in noisy case//Proceedings of the 28th International Conference on International Conference on Machine Learning. Washington: Omnipress: 33-40
相关文章
相关作者
相关机构