Aim to the difficulty of automatic and robust registration of optical imagery with point cloud data, this paper propose a new method based on SIFT and Mutual Information (MI). The SIFT features are firstly extracted and matched, whose result is used to derive the coarse geometric relationship between the optical imagery and the point cloud data. Secondly, the MI-based similarity measure is used to derive the conjugate points. And then the RANSAC algorithm is adopted to eliminate the erroneous matching points. Repeating the procedure of MI matching and mismatching points deletion until the finest pyramid image level. Using the matching results, the transform model is determined. The experiments have been made and they demonstrate the potential of the MI-based measure for the registration of optical imagery with the point cloud data, and this highlight the feasibility and robustness of the method proposed in this paper to automated registration of multi-modal, multi-temporal remote sensing data for a wide range of applications.
This paper proposes a robust matching method for the multi-sensor imagery. Firstly, the SIFT feature matching and relaxation matching method are integrated in the highest pyramid to derive the approximate relationship between the reference and slave image. Then, the normalized Mutual Information and multi-grid multi-level RANSAC algorithm are adopted to find the correct conjugate points. Iteratively perform above steps until the original image level, the facet- based transformation model is used to carry out the image registration. Experiments have been made, and the results show that the method in this paper can deliver large number of evenly distributed conjugate points and realize the accurate registration of optical and SAR multi-sensor imagery.
Registration of two or more complex images of the same scene is an important procedure in InSAR (Interferometric
Synthetic Aperture Radar) image processing. Meanwhile, the accuracy of this step is crucial to the reliability of
subsequent image processing and final results of the data processing chain. This paper presents a robust method which
introduces the coarse-to-fine strategy, relaxation optimization technology and Maximum Spectrum Method to obtain the
dense, reliable and accurate conjugate points for the registration of two single looking complex (SLC) SAR images. In
each pyramid image, we extract the feature points using the Moravec interest operator, and then perform matching for
feature points to find their candidate conjugate points whose correlation coefficient is above certain threshold, and
through relaxation technology to find the best matcher. The matching result at higher pyramid level is then used to guide
and limit the search space for the matching in the lower level. Perform above procedure iteratively until to the original
image, the Maximum Spectrum Method is carried out to refine the matching accuracy to the sub-pixel. After determining
dozens of thousands conjugate points on master and slave image, we can form the transformation model between them
and perform image correction. We have made experiments to validate our method, and it comes to the conclusion that
with coarse-to-fine strategy, global relaxation and Maximum Spectrum Method, it efficiently reduces the matching error
and improves matching precision.
In this paper, we propose an automatic and accurate image registration method for the high resolution. Due to the strong
distortion caused by the terrain relief in this kind of images, it cannot be resolved by one set of transformation
coefficients for the whole image. So the method mainly consists of two parts: one part is the dense feature point
matching, and the other is the faced based differential registration. The matching algorithm integrates the feature point
matching, relaxation optimization technique, the Least Square Matching, the coarse-to-fine strategy, and it can provide
hundreds of thousands of reliable and accurate control points. With the TIN, these points divide the image into a lot of
small triangles. For each triangle, we can assume the local distortion is simple and can be depicted by the affine
transformation function. Finally, faced based differential registration is performed to resample the slave image.
Experiments have been carried out and satisfactory results have been obtained.
In this paper, we present a matching method for DSM generation from multiple images based on feature points, which
introduce the coarse-to-fine strategy, geometrically constrained matching and relaxation technology, the matching is
guided by the information in the object and make full use of the information in both image and object space. A match
appearing in any pair has the chance to survive, and very dense disparity maps are obtained. Experiments have been
performed and the height accuracy of the derived DSM is about 3 pixels.