In this paper we present a change detection approach for exposure-different images. This approach is based on a significance test on the joint comparametric probability distribution, that is, the joint noise and intensity image pair distribution. The approach involves determining a binary comparametric change detection mask for which homologous pixel pairs in our images are compared. In addition, joint spatial and tonal image registration is performed prior to carrying out the change detection. Two examples of real imagery are presented and receiver operating characteristic curves from three other change detection approaches are provided as comparison. The results demonstrate the increasing importance of properly accounting for exposure in change detection approaches as the exposure difference between images increases.

A mesh-based approach to optimally and densely matching two epipolar row-rectified stereo images with small (even subpixel) maximal disparity is presented. It is a global matching approach that only requires specifying the size of the mesh to work with-no search windows, regions or other such typical heuristics are needed. We show how the parameters of the ordering constrained mesh are determined in an unconstrained manner via auxiliary parameterization. We illustrate algorithm performance on a real stereo pair.

In this article, an enhanced wavelet domain communication system (EWDCS) is presented. The basic idea for this system is to synthesize an intelligent adaptive waveform in the wavelet domain at both the transmitter and receiver to avoid spectral crowded regions. This approach offers better bit error performance in contrast to other conventional interference mitigation techniques that process the signal at the receiver only. Moreover, since this smart waveform is able to search "spectrum hole" and adapt to electromagnetic environment, it could be a potential candidate in cognitive radio technology. The EWDCS exploits both transform domain processing and the evolutionary wavelet spectrum (EWS) estimation technique to extend interference avoidance capability from stationary interference to nonstationary interference. Compared to similar systems such as the transform domain communication system (TDCS) or the wavelet domain communication system (WDCS), the EWDCS significantly improves the bit error performance under nonstationary interference such as with swept-tone and also offers comparable bit error performance under stationary interference such as with single-tone, multiple-tone and partial-band interference. Our results indicate the proposed EWDCS is a viable approach to highly reliable communication or cognitive radio technology.

This correspondence details enhancements to previous work on piecewise linear comparametric image registration. The enhancements come in the form of slope constraints and knots' location selection in the comparametric modeling. An analysis of the properties of comparametric functions leads to two general slope constraints that, along with a knot location selection based on the reference image's pixel value distribution, serves to reduce error and sensitivity to the number of segments considered as well as allow for the solution to cases in which there are gaps in the comparagram. Results on real images are presented.

A fundamentally new approach that accurately estimates the camera response function from comparametric data, i.e., pixel data from two differently exposed images over a common field of view, is presented. It does so by solving for the camera response function from its associated comparametric relation. The approach offers several advantageous features, including having a complexity that is independent of the number of pixel data considered, allowing for the modeling of saturated pixels, enabling an inherently constrained optimization problem to be solved in an unconstrained manner, and the easy incorporation into an existing framework for joint image registration. This is accomplished by approximating the camera response function with a constrained piecewise linear model so that its solution, within the comparametric camera relation, can be obtained. This results in a semiparametric comparametric model, optimally determined from pixel data, which is directly parameterized in terms of the exposure parameter. Subsequently, it is shown how this semiparametric model is used for exposure estimation from captured images. Finally, we incorporate the semiparametric model within an existing and previously published framework for simultaneous and joint spatial and tonal image registration in order to illustrate the developed model's performance.

This paper describes an approach whereby comparametric analysis is used in jointly registering image pairs in their domain and range, i.e., in their spatial coordinates and pixel values, respectively. This is accomplished by approximating a camera's nonlinear comparametric function with a constrained piecewise linear one. The optimal fitting of this approximation to comparagram data is then used in a re-parameterized version of the camera's comparametric function to estimate the exposure difference between images. Doing this allows the inherently nonlinear problem of joint domain and range registration to be performed using a computationally attractive least squares formalism. The paper first presents the range registration process and then describes the strategy for performing the joint registration. The models used allow for the pair-wise registration of images taken from a camera that can automatically adjust its exposure as well as tilt, pan, rotate and zoom about its optical center. Results concerning the joint registration as well as range-only registration are provided to demonstrate the method's effectiveness.

An approach is presented that can simultaneously align multiple exposure-adjusted pictures of the same scene both in their spatial coordinates as well as in their pixel values. The approach is featureless and produces an image mosaic at a common spatial and exposure reference and also addresses the misalignment problem common to methods that compose mosaics from only pair-wise registered image pairs. The objective function considered minimizes the sum of the collective variance over pixels of a global coordinate grid on which to create the final image. The models employed relate images spatially by homographic transformations and tonally by comparametric functions. The importance of performing joint spatial and tonal registration on exposure-adjusted images is emphasized by providing two examples in which spatial-only registration fails. A discussion describing the performance between pair-wise and simultaneous registration under both spatial-only and joint registration procedures is provided.

A formulation is presented for the registration of two images in range. This is in contrast to the typical registration of images that occurs over their domain and ignores any exposure differences that might exist between the images. The registration is accomplished by approximating the camera's nonlinear comparametric function with a constrained piecewise linear model so that the nonlinear optimization needed to estimate the exposure difference can be simply performed using linear least squares. Results are shown illustrating the effectiveness of the approach.

An approach for jointly registering images in domain and range using a least squares formalism is presented. This joint approach is in contrast to almost all current registration methods that only register images with respect to their domains and neglect accounting for exposure differences between images. The inclusion of range into the registration process is accomplished by approximating the camera's nonlinear comparametric function with a piecewise linear one. This results in a computationally attractive least squares approach to an otherwise inherently nonlinear optimization problem. The effectiveness of this approach is illustrated.

An adaptive two-step paradigm for the superresolution of optical images is developed in this paper. The procedure locally projects image samples onto a family of kernels that are learned from image data. First, an unsupervised feature extraction is performed on local neighborhood information from a training image. These features are then used to cluster the neighborhoods into disjoint sets for which an optimal mapping relating homologous neighborhoods across scales can be learned in a supervised manner. A super-resolved image is obtained through the convolution of a low-resolution test image with the established family of kernels. Results demonstrate the effectiveness of the approach.

An approach to stereo feature matching is presented with the introduction of a similarity measure for evaluating and confirming a stereo match. The contributions of this study are reflected in (1) the development of a similarity measure which evaluates a stereo match based on feature locality and gray-level gradient associated with the feature; and (2) the use of a matching procedure that integrates local and global matching strategies based on matching first those features with the highest similarity measure among the set of all highest similarities found locally under confined search spaces, ensuring that each feature is matched with a high degree of certainty. A left-to-right and right-to-left consistency check is used for each feature to comply with the uniqueness constraint and to confirm if a potential match can be declared a correct match.

Describes a new feature-based stereo matching technique which exploits the Walsh transformation. The established matching strategy adopts and integrates the fundamental steps of the stereo vision problem: (a) detecting and locating feature points, (b) searching for potential matches, (c) validating a match through a global consistency check, and (d) determining the disparity of the matched feature points. The unique representation of stereo images into Walsh-based attributes unites the aforementioned steps into an integrated process which yields accurate disparity extraction. It is shown that the first and second Walsh attributes are used as operators approximating the first and second derivatives for the extraction and localization of feature points. The complete set of these attributes are then used as matching primitives contributing equally to the decision-making process and providing relevant information on both the characterization of a potential match and its validation through a consistency check. Computer results using images of varying complexities prove the soundness and the relatively fast processing time of this stereo matching technique.>