Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representat...
详细信息
ISBN:
(纸本)0818621486
Gradient methods are widely used in the computation of optical flow. The authors discuss extensions of these methods which compute probability distributions of optical flow. The use of distributions allows representation of the uncertainties inherent in the optical flow computation, facilitating the combination with information from other sources. Distributed optical flow for a synthetic image sequence is computed, and it is demonstrated that the probabilistic model accounts for the errors in the flow estimates. The distributed optical flow for a real image sequence is computed.
It is shown that the hitherto heuristic hysteresis linking idea of J. F. Canny (1986) can be formulated as a Bayesian contextual decision process. This approach draws on an explicit image model which accounts both for...
详细信息
ISBN:
(纸本)0818621486
It is shown that the hitherto heuristic hysteresis linking idea of J. F. Canny (1986) can be formulated as a Bayesian contextual decision process. This approach draws on an explicit image model which accounts both for the way in which noisy raw-edge information is characterized via filtering operations and how the required edge-connectivity information is quantified. The main advantage is that the previously ad hoc hysteresis thresholds can be related to the parameters of an image model. One feature is the requirement of a third hysteresis threshold based on the consistency of non-edge configurations;this results in an increased capability to reject inconsistent edge candidates. The parameters of the image model can be robustly estimated from image-statistics. The approach endows the hysteresis linking algorithm with adaptive capabilities.
A model-based recognition method that runs in time proportional to the actual number of instances of a model that are found in an image is presented. The key idea is to filter out many of the possible matches without ...
详细信息
ISBN:
(纸本)0818621486
A model-based recognition method that runs in time proportional to the actual number of instances of a model that are found in an image is presented. The key idea is to filter out many of the possible matches without having to explicity consider each one. This contrasts with the hypothesize-and-test paradigm, commonly used in model-based recognition, where each possible match is tested and either accepted or rejected. For most recognition problems the number of possible matches is very large, whereas the number of actual matches is quite small, making output-sensitive methods such as this one very attractive. The method is based on an affine invariant representation of an object that uses distance ratios defined by quadruples of feature points. A central property of this representation is that it can be recovered from an image using only pairs of feature points.
Ellipses seen in an image may be the 2-D projection of 3-D circles from the scene. Given this assumption, ellipses can be grouped into perceptual groups from which inferences about the 3-D structure of objects can be ...
详细信息
ISBN:
(纸本)0818621486
Ellipses seen in an image may be the 2-D projection of 3-D circles from the scene. Given this assumption, ellipses can be grouped into perceptual groups from which inferences about the 3-D structure of objects can be made. Methods are proposed for extracting groupings corresponding to surfaces of revolution. A Hough transform approach is used for grouping, after which the confidence in the plausibility of the perceptual group is improved by detecting symmetry groupings.
A novel approach to computing egomotion and detecting points not moving rigidly with the scene when an observer moves with unrestricted motion is presented. The approach, using collinear image points, is based on an e...
详细信息
ISBN:
(纸本)0818621486
A novel approach to computing egomotion and detecting points not moving rigidly with the scene when an observer moves with unrestricted motion is presented. The approach, using collinear image points, is based on an exact method for cancelling effects of the observer's rotation from optic flow. For each point only the component of velocity normal to the direction of the line joining the collinear points is needed. The algorithm is simple, appears robust, and is ideal for parallel implementation.
A method for identifying groups of intensity edges in an image that are likely to result from the same convex object in a scene is described. A key property of the method is that its output is no more complex than the...
详细信息
ISBN:
(纸本)0818621486
A method for identifying groups of intensity edges in an image that are likely to result from the same convex object in a scene is described. A key property of the method is that its output is no more complex than the original image. The method uses a triangulation of linear edge segments to define a local neighborhood that is scale invariant. From this local neighborhood a local convexity graph that encodes which neighboring image edges could be part of a convex group of image edges is constructed. A path in the graph corresponds to a convex polygonal chain in the image, such as a convex polygon or a spiral. Examples are presented to illustrate that the technique finds intuitively salient groups.
An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the i...
详细信息
ISBN:
(纸本)0818621486
An early-processing algorithm to extract motion information from closely sampled image sequences is presented. This method outputs dense displacement field, based on the extraction of strips in slices taken from the image volume along the temporal dimension. The extracted strips provide estimates of the velocity component along the slice orientation. Because of the high sampling rate, the motion is assumed to be piecewisely translational. A voting scheme to estimate the position of FOE while extracting strips is proposed. The true velocity can then be calculated. Results on several real image sequences and a promising speedup from the parallel implementation on the connection machine are presented.
A polynomial time algorithm is presented (pruned correspondence search, PCS) with good average case complexity for solving a wide class of geometric maximal matching problems, including the problem of recognizing 3-D ...
详细信息
ISBN:
(纸本)0818621486
A polynomial time algorithm is presented (pruned correspondence search, PCS) with good average case complexity for solving a wide class of geometric maximal matching problems, including the problem of recognizing 3-D objects from a single 2-D image. The PCS algorithm is connected with the geometry of the underlying recognition problem only through calls to a verification algorithm. Efficient verification algorithms are given for the case of affine transformations among vector spaces and for the case of rigid 2-D and 3-D transformations with scale. Among the known algorithms that solve the bounded error recognition problem exactly and completely, the PCS algorithm currently has the lowest complexity. Some preliminary experiments suggest that PCS is a practical algorithm.
A description is given of the construction of a symmetry analyzer. Examples using SYMAN on both real and synthetic images are shown. SYMAN's combination of both global and local methods is discussed. The derivatio...
详细信息
ISBN:
(纸本)0818621486
A description is given of the construction of a symmetry analyzer. Examples using SYMAN on both real and synthetic images are shown. SYMAN's combination of both global and local methods is discussed. The derivation of a global analytic solution for the skew axes when the degree of skew symmetry is known is described. A local tangent-based algorithm which has advantages over previous methods is presented.
An edge detection algorithm based on the regularization theory in which the smoothness is controlled spatially over the image space is presented. The algorithm starts with an oversmoothed regularized solution and iter...
详细信息
ISBN:
(纸本)0818621486
An edge detection algorithm based on the regularization theory in which the smoothness is controlled spatially over the image space is presented. The algorithm starts with an oversmoothed regularized solution and iteratively refines the surface around discontinuities using the knowledge on the structure of discontinuities exhibited in the error signal between the image data and the previous regularized solution. The spatial control of smoothness is shown to resolve the conflict between detection and localization criteria. The adaptive nature of the algorithm eliminates the need to select image-dependent parameters and enables the extraction of multiscale features from the image. The computational aspects of the algorithm as well as its performance on real and synthetic images are considered.
暂无评论