Quality Assessment for Pansharpening Based on Component Analysis
The quality assessment for pansharpening is important. Since most existing indexes evaluate the performance of entire fused image either from the spatial aspect or the spectral aspect individually, we introduce an pansharpening metric which separate the fused image into two components to evaluate spectral and spatial quality simultaneously. This can be achieved by pure pixels containing one material and mixed pixels with more than one materials in the multispectral (MS) image. The MS pure pixels can be utilized to evaluate the spectral quality, which are projected to the low-frequency regions in the panchromatic (PAN) image. In contrast, the MS mixed pixels corresponding to the PAN high-frequency regions can be utilized to evaluate the spatial quality. Finally, the pansharpening quality assessment is made by a weighted sum of common existing criteria on pure and mixed components, which generates a pure and mixed index (PM index). Experimental results, carried out on high-resolution GeoEye-1 and WV-2 datasets, demonstrate that the proposed quality assessment is made on fused images in a more comprehensive and objective manner.
KeywordsPansharpening Remote sensing Quality assessment Superpixels
- 6.Aiazzi, B., Alparone, L., Baronti, S., Garzelli, A., Selva, M.: Twenty-five years of pansharpening: a critical review and new developments. In: Chen, C.-H. (ed.) Signal and Image Processing for Remote Sensing, 2nd edn., pp. 533–548. CRC Press, Boca Raton, FL, USA (2012)Google Scholar
- 8.Wald, L.: Data Fusion. Definitions and Architectures-Fusion of Images of Different Spatial Resolutions. Presses des MINES, Paris (2002)Google Scholar
- 13.Liu, M.-Y., Tuzel, O., Ramalingam, S., Chellappa, R.: Entropy rate superpixel segmentation. In: Proceedings IEEE Conference Vision and Pattern Recognition, pp. 2097–2104 (2011)Google Scholar
- 14.Chavez Jr., P.S., Sides, S.C., Anderson, J.A.: Comparison of three different methods to merge multiresolution and multispectral data: landsat TM and SPOT PANchromatic. Photogramm. Eng. Remote Sens. 57(3), 295–303 (1991)Google Scholar