Scale Conversion of Multi Sensor Remote Sensing Image Using Single Frame Super Resolution Technology
Despite its high spatial resolution (15m), the 60kmswath width of Advanced Spaceborne Thermal Emission andReflection Radiometer (ASTER) can limit the effectiveness ofaccurately large-scale study. One possible solution is to downscale low spatial resolution but width swath satellite image data(e.g. Landsat TM/ETM+with spatial resolution 30m and swathwidth 185km). This paper proposed a method related with superresolution named support vector regression (SVR) to convert thelow resolution ETM+image to a high resolution ASTER image.The experiments are conducted on the subset of the ETM+sceneand ASTER UV/NIR scene. The predicted results show that theproposed method is better than the interpolation methodcommon adopted in down scale, both visually and objectively.Thus it can be used to make multi sensor and multi resolutionanalysis, even has the potential to extend the ASTER scenesswath width to the same with the ETM+s.
Hankui Zhang Bo Huang
Department of Geography and Recourse Management The Chinese University of Hong Kong Hong Kong, China
国际会议
The 19th International Conference on Geoinformatics(第19届国际地理信息科学与技术大会 19 Geoinformatics)
上海
英文
1-6
2011-06-01（万方平台首次上网日期，不代表论文的发表时间）