This paper aims to present a review of recent as well as classic image registration methods. Image registration is the process of overlaying images (two or more) of the same scene taken at different times, from different viewpoints, and/or by different sensors. The registration geometrically align two images (the reference and sensed images). The reviewed approaches are classified according to their nature (areabased and feature-based) and according to four basic steps of image registration procedure: feature detection, feature matching, mapping function design, and image transformation and resampling. Main contributions, advantages, and drawbacks of the methods are mentioned in the paper. Problematic issues of image registration and outlook for the future research are discussed too. The major goal of the paper is to provide a comprehensive reference source for the researchers involved in image registration, regardless of particular application areas. q 2003 Elsevier B.V. All rights reserved.

Super-resolution algorithms reconstruct a high-resolution image from a set of low-resolution images of a scene. Precise alignment of the input images is an essential part of such algorithms. If the low-resolution images are undersampled and have aliasing artifacts, the performance of standard registration algorithms decreases. We propose a frequency domain technique to precisely register a set of aliased images, based on their low-frequency, aliasing-free part. A high-resolution image is then reconstructed using cubic interpolation. Our algorithm is compared to other algorithms in simulations and practical experiments using real aliased images. Both show very good visual results and prove the attractivity of our approach in the case of aliased input images. A possible application is to digital cameras where a set of rapidly acquired images can be used to recover a higher-resolution final image. Copyright © 2006 Patrick Vandewalle et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

The phase correlation method is known to provide straightforward estimation of rigid translational motion between two images. It is often claimed that the original method is best suited to identify integer pixel displacements, which has prompted the development of numerous subpixel displacement identification methods. However, the fact that the phase correlation matrix is rank one for a noisefree rigid translation model is often overlooked. This property leads to the low complexity subspace identification technique presented here. The combination of non-integer pixel displacement identification without interpolation, robustness to noise, and limited computational complexity make this approach a very attractive extension of the phase correlation method. In addition, this approach is shown to be complementary with other subpixel phase correlation based techniques.

Abstract—The estimation of large motions without prior knowledge is an important problem in image registration. In this paper, we present the angular difference function (ADF) and demonstrate its applicability to rotation estimation. The ADF of two functions is defined as the integral of their spectral difference along the radial direction. It is efficiently computed using the pseudopolar Fourier transform, which computes the discrete Fourier transform of an image on a near spherical grid. Unlike other Fourier-based registration schemes, the suggested approach does not require any interpolation. Thus, it is more accurate and significantly faster. Index Terms—Global motion estimation, Fourier domain, pseudopolar FFT, image alignment. æ 1

Sea-ice motion consists of complex non-rigid motions involving continuous, piece-wise continuous and discrete particle motion. Techniques for estimating non-rigid motion of sea ice from pairs of satellite images (generally spaced three days apart) are still in the developmental stages. For interior Arctic and Antarctic pack ice, the continuum assumption begins to fail below the 5 km scale with evidence of discontinuities already revealed in models and remote sensing products in the form of abrupt changes in magnitude and direction of the differential velocity. Using a hierarchical multi-scale phase-correlation method and profiting from known limitations of cross correlation methods, we incorporate the identification of discontinuities into our motion estimation algorithm, thereby descending below the continuum threshold to examine the phenomenon of discontinuous non-rigid sea-ice motion. 1.

The accurate registration of multiview images is of central importance in many advanced image processing applications. Image super-resolution, for example, is a typical application where the quality of the super-resolved image is degrading as registration errors increase. Popular registration methods are often based on features extracted from the acquired images. The accuracy of the registration is in this case directly related to the number of extracted features and to the precision at which the features are located: images are best registered when many features are found with a good precision. However, in low-resolution images, only a few features can be extracted and often with a poor precision. By taking a sampling perspective, we propose in this paper new methods for extracting features in low resolution images in order to develop efficient registration techniques. We consider in particular the sampling theory of signals with finite rate of innovation [10] and show that some features of interest for registration can be retrieved perfectly in this framework, thus allowing an exact registration. We also demonstrate through simulations that the sampling model which enables the use of finite rate of innovation principles is well-suited for modeling the acquisition of images by a camera. Simulations of image registration and image super-resolution of artificially sampled images are first presented, analyzed and compared to traditional techniques. We finally present favorable experimental results of super-resolution of real images acquired by a digital camera available on the market.

In many practical situations, we do not know the relative orientation of the two images. In such situations, it is desirable to register these images, i.e., to find the rotation and the shift after which the images match as much as possible. A similar problem occurs when we have the images of two different objects whose shapes should match. For example, we may have images of two bioactive molecules. We know that in vivo, these molecules interact because one of these molecules "docks " to the other one, i.e., gets into a position where their surfaces match. In such situations, it is also important to find orientation and shift corresponding to this match. Comment. Sometimes, the images also differ in lighting conditions, as a result of which we may have I2(~x) ss C \Delta I1( * \Delta R~x + ~a) for some unknown factor C.

One of the major challenges related to image registration is the estimation of large motions without prior knowledge. This paper presents a Fourier based approach that estimates large translation, scale and rotation motions. The algorithm uses the pseudo-polartransform to achieve substantial improved approximations of the polarandlog-polar Fourier transforms of an image. Thus, rotation and scale changes are reduced to translations which are estimated using phasecorrelation. By utilizing the pseudo-polar grid we increase the performance (accuracy, speed, robustness) of the registration algorithms. Scales up to 4 and arbitrary rotationangles can be robustly recovered, compared to a maximum scaling of 2 recovered by the currrnt state of-the-artalgorithms. The algorithm utilizes only 1D-FFT calculations whose overall complexity is signifficantly lower than prior works. Experimental results demonstrate the applicability of these algorithms.

Using Synthetic Aperture Radar (SAR) images from ERS-1, we render high resolution motion fields of sea ice using a multi- resolution processing system. The results are provided at a 400 m resolution, which is an order of magnitude greater than the standard SAR motion products (5–10 km). An error propagation experiment shows a standard deviation of 1.3% day − 1 for the noise in invariant shear resulting from position uncertainties and processing techniques. We use this noise level to determine a significant lower threshold when identifying shear zone discontinuities. As example, a 24-day sequence of images is processed using this system to examine the development and evolution of a shear zone. This evolution is in response to the topographic steering caused by ocean circulation and wind forcing along a continental shelf break. In addition, we adapt the Line Integral Convolution (LIC) to depict flow patterns present in the motion field. Collectively, these motion products provide valuable descriptions of the non-rigid dynamics taking place within the sea ice. Our goal is to complement the existing RADARSAT Geophysical Processing System (RGPS) motion products and aid in the validation and further development of the most progressive “lead-resolving” sea ice models currently available. This form of sea ice visualization is important for understanding air–ice–sea momentum transfer processes that transcend through small-scale to large-scale fracture events with application to ship navigation.

The contribution of this paper is twofold. First, a new spatial domain image registration technique with subpixel accuracy is presented. This technique is based on a double maximization of the correlation coefficient and provides a closed-form solution to the subpixel translation estimation problem. Second, an efficient iterative scheme for integer registration is proposed, which reduces significantly the number of searches, as compared to the exhaustive search. This scheme can be used as a pre-processing step in the sub-pixel accuracy technique, leading to lower computational complexity. Extensive simulation results have shown that the performance of the proposed technique compares very favorably with respect to existing ones. 1.