An Automated Parallel Image Registration Technique Based on the Correlation of Wavelet Features

Appl. Inf. Sci. Branch, NASA Goddard Space Flight Center, Greenbelt, MD
IEEE Transactions on Geoscience and Remote Sensing (Impact Factor: 3.51). 09/2002; 40(8):1849 - 1864. DOI: 10.1109/TGRS.2002.802501
Source: IEEE Xplore


With the increasing importance of multiple multiplatform remote sensing missions, fast and automatic integration of digital data from disparate sources has become critical to the success of these endeavors. Our work utilizes maxima of wavelet coefficients to form the basic features of a correlation-based automatic registration algorithm. Our wavelet-based registration algorithm is tested successfully with data from the National Oceanic and Atmospheric Administration (NOAA) Advanced Very High Resolution Radiometer (AVHRR) and the Landsat Thematic Mapper (TM), which differ by translation and/or rotation. By the choice of high-frequency wavelet features, this method is similar to an edge-based correlation method, but by exploiting the multiresolution nature of a wavelet decomposition, our method achieves higher computational speeds for comparable accuracies. This algorithm has been implemented on a single-instruction multiple-data (SIMD) massively parallel computer, the MasPar MP-2, as well as on the CrayT3D, the Cray T3E, and a Beowulf cluster of Pentium workstations.

1 Follower
21 Reads
  • Source
    • "In[14], a robust corner detector that is based on the firstorder derivatives was developed. L. Moigne[1]detected feature using the maxima of LH and HL wavelet coefficients for remote sensed image registration. Image gradients are used in[15]to present 'Harris detector'. "

    Full-text · Article · Dec 2015
  • Source
    • "The second approach is applied by comparing brightness values (intensity) of base and slave images using image correlation metrics [15] [16] [17] [18]. Several studies employed wavelet coefficient maxima to perform automatic registration [5], and others applied similarity of mutual information to register multi-sensor images [19]. Previous studies have also applied windows matching to find corresponding key points between a reference and sensed images [9]. "

    Full-text · Dataset · Sep 2015
  • Source
    • "The main idea of these methods is to compute the similarities of window pairs in two images, and consider the one with the largest similarity as a correspondence. In remote sensing applications, a correlation-like method utilizing maxima of wavelet coefficients has been developed for automatic registration [27]. The correlation-like methods suffer from some drawbacks such as the flatness of the similarity measure in textureless regions and high computational complexity. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature matching, which refers to establishing reliable correspondence between two sets of features (particularly point features), is a critical prerequisite in feature-based registration. In this paper, we propose a flexible and general algorithm, which is called locally linear transforming (LLT), for both rigid and nonrigid feature matching of remote sensing images. We start by creating a set of putative correspondences based on the feature similarity and then focus on removing outliers from the putative set and estimating the transformation as well. We formulate this as a maximum-likelihood estimation of a Bayesian model with hidden/latent variables indicating whether matches in the putative set are outliers or inliers. To ensure the well-posedness of the problem, we develop a local geometrical constraint that can preserve local structures among neighboring feature points, and it is also robust to a large number of outliers. The problem is solved by using the expectation–maximization algorithm (EM), and the closed-form solutions of both rigid and nonrigid transformations are derived in the maximization step. In the nonrigid case, we model the transformation between images in a reproducing kernel Hilbert space (RKHS), and a sparse approximation is applied to the transformation that reduces the method computation complexity to linearithmic. Extensive experiments on real remote sensing images demonstrate accurate results of LLT, which outperforms current state-of-the-art methods, particularly in the case of severe outliers (even up to 80%).
    Full-text · Article · Jun 2015 · IEEE Transactions on Geoscience and Remote Sensing
Show more