Multi-Spectral Remote Sensing Image Registration Based on SURF

摘要：

As remote sensing breaking into all fields of professions, the needs of it are increasing, which give power to its development. However, before using the images, we must process them first. And image registration plays an significant role in remote sensing image processing. Now more and more sensors appeard, multi-spectral remote sensing images are used in widely application all the way. At the same time, for its characteristics of mass data and illumination variation, it is extremely urgent to find a way to register multi-spectral remote sensing images automatically and accurately. SURF is a kind of feature extraction algorithm with scale-invariation, rotation-invariation, iliumination-invariation and speediness. This paper applied SURF on multi-spectral image registration in different platforms, and got satisfied results, which verifies the feasibility of SURF in multi-spectral image registration.

关键词： image registration Remote Sensing multi-spectral SURF(Speeded-Up Robust Features)

作者: Yunfei Lu Haimeng Zhao Bo Li Lei Yan

作者单位: Institute of Remote Sensing & Geographic Information System,Beijing Key Lab of Spatial Information Integration & Its Applications, Peking University,Beijing, China

会议类型: 国际会议

会议名称: 2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)

会议地点: 上海

会议语种:英文

页码: 632-635

在线出版日期: 2010-12-25（万方平台首次上网日期，不代表论文的发表时间）