A new automatic image registration algorithm based on corner detector for remote sensing applications
Résumé
In this paper, we propose a new automatic satellite image registration approach capable of handling remotely sensed images geometrically distorted by various transformations such as translation, rotation, and shear. This technique exploits the invariant relations between regions of a reference image and those of a sensed image. It involves an edge-based selection of the most distinctive control points in the reference image. The search for the corresponding control points in the sensed image is based on local similarity detection by means of correlation coefficient according to a combined invariants-based similarity measure. Feature matches are refined using RANSAC matching algorithm. The final warping of the images according to the selected control points is performed by using affine transformations. The procedure is fully automatic and computationally efficient. The proposed algorithm for this technique has been successfully applied to register multitemporal Spot, Landsat, Ikonos, Quick bird, ERS-1, SAR, and aerial images from urban and agricultural areas. The experimental results demonstrate the robustness, efficiency and accuracy of the algorithm.