Phase Correlation based Local Illumination-invariant Method for Multi-Tempro Remote Sensing Image Matching

Abstract. This paper aims at image matching under significantly different illumination conditions, especially illumination angle changes, without prior knowledge of lighting conditions. We investigated the illumination impact on Phase Correlation (PC) matrix by mathematical derivation and from which, we decomposed PC matrix as the multiplication product of the illumination impact matrix and the translation matrix. Thus the robustness to illumination variation of the widely used Absolute Dirichlet Curve-fitting (AD-CF) algorithm for pixel-wise disparity estimation is proved. Further, an improved PC matching algorithm is proposed: Absolute Dirichlet SVD (AD-SVD), to achieve illumination invariant image alignment. Experiments of matching DEM simulated terrain shading images under very different illumination angles demonstrated that AD-SVD achieved 1/20 pixels accuracy for image alignment and it is nearly entirely invariant to daily and seasonal solar position variation. The AD-CF algorithm was tested for generating disparity map from multi-illumination angle stereo pairs and the results demonstrated high fidelity to the original DEM and the Normalised Correlation Coefficient (NCC) between the two is 0.96.