A robust multi-stage information-theoretic approach for registration of partially overlapped hyperspectral aerial imagery and evaluation in the presence of system noise
作者：
Highlights：
• A method to enhance aerial image registration with no well-defined feature structures.
• Information theoretic and correlation methodology for image low spatial resolution.
• A derived multi-stage approach resulting in search space and computational reduction.
• Analysis and modeling of the effect of sensor, quantization and impulsive noise.
• The method is also applied to heterogeneous hyper spectral bands registration.
摘要
•A method to enhance aerial image registration with no well-defined feature structures.•Information theoretic and correlation methodology for image low spatial resolution.•A derived multi-stage approach resulting in search space and computational reduction.•Analysis and modeling of the effect of sensor, quantization and impulsive noise.•The method is also applied to heterogeneous hyper spectral bands registration.
论文关键词：Image registration,Normalized cross-correlation,Variation of information,System noise
论文评审过程：Received 26 May 2016, Revised 26 December 2016, Accepted 26 December 2016, Available online 27 December 2016, Version of Record 12 January 2017.
论文官网地址：https://doi.org/10.1016/j.image.2016.12.009
