A new method of automatic region registration method based on spatially assistant planes is introduced in this paper.The method integrates both algorithm features of the global-region registration method’s high precision and the local-region registration method’s low complexity.Spatially assistant features with the same angle and resolution are calculated from
and the gray similarity is defined by normalized cross-correlation coefficient.By introducing the spatially assistant planes
spatially assistant features and gray similarity are combined together to register images.Two groups of images SPOT and ASTER
ASAR and ASTER
were tested.A mosaic was formed from the reference and re-sampled sensed images.In the mosaic
lineal features are well-aligned
which effectively proves that the automatic registration has a high accuracy.
关键词
空间辅助面特征主被动遥感影像区域自动配准正、反函数变换变换模型
Keywords
spatially assistant planeactive and passive remote sensing imagesautomatic region registrationpositive and negative function transformstransform model