针对不同融合算法的质量评价指标性能评估

被引:20
作者
余先川
裴文静
机构
[1] 北京师范大学信息科学与技术学院
基金
北京市自然科学基金;
关键词
评价指标; 参考图像; 性能评价; 影像融合; 影像质量;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
融合质量评价指标的性能对图像融合方法的提出和改进十分重要。讨论了目前常用的三种参考图像的构建方法,并对常用融合质量评价指标(相关系数CC、偏差指数RB、结构相似度SSIM、均方根误差RMSE、光谱角SAM和ERGAS)从三方面进行性能评价分析:(1)功能相似指标间评价结果的一致性;(2)对同一融合算法、不同图像的评价结果的鲁棒性;(3)与目视评价结果的一致性。中、高空间分辨率遥感影像融合实验结果表明:CC、SSIM和SAM选择原始低分辨率多光谱图像作为参考图像性能最好,仅适合做融合图像光谱质量评价;RMSE和ERGAS选择原始低分辨率多光谱图像或高分辨率图像作为参考图像性能最好,因此这两个指标既可以做融合图像光谱质量评价,也可以做空间质量评价。
引用
收藏
页码:3416 / 3422
页数:7
相关论文
共 19 条
[1]  
Smoothing filter-based intensity modulation: a spectral preserve image fusion technique for improving spatial details. Liu J G. International Journal of Remote Sensing . 2000
[2]  
Assessment of the quality of fusedproducts. Thomas C,Wald L. New Strategies Eur . 2004
[3]  
Comparison of different methods to merge SPOTP and XS data:Evaluation in an urban area. Terretaz P. FutureTrends in Remote Sensing . 1998
[4]  
A simple spatial filtering routine for thecosmetic removal of scan-line noise from LANDSAT TMP-Tape imagery. Crippen R E. Photogrammetric Engineering&Remote Sensing . 1987
[5]  
A wavelet transform method to merge Landsat TM and SPOT panchromatic data. Zhou J, Civco DL, Silander JA. International Journal of Remote Sensing . 1998
[6]  
Fusion of multispectral and panchromatic satellite sensor imagery based on tailored filtering in the Fourier domain. Lillo-Saavedra, M,C Gonzalo,A. Arquero et al. International Journal of Remote Sensing . 2005
[7]  
Multi-Spectral Image Resolution Refinement Using Stationary Wavelet Transform. Beaulieu, M,Foucher, S,Gagnon, L. IEEE International Conference on Geoscience and Remote Sensing Symposium . 2003
[8]  
Assessmentand Evaluation of Different Data Fusion Techniques. Helmy,A K,Nasr,A.H,El-Taweel,Gh.S. International Journal of Computers . 2010
[9]  
The remote-sensing image fusion based on GPU, The International Archives of the Photogrammetry. Jun Lu,Baoming Zhang,Zhihui Gong, et al. Remote Sensing and Spatial Information Sciences . 2008
[10]  
Fusion of Multispectral and Panchromatic Images by Local Mean and Variance Matching Filtering Techniques. Bethune S,Muller F,Donnay J.P. Fusion of Earth Data . 1998