Recent research in image sensors has produced cameras with very large fields of view. An area of computer vision research which will benefit from this technology is the computation of camera motion (ego-motion) from a sequence of images. Traditional cameras suffer from the problem that the direction of translation may lie outside of the field of view, making the computation of camera motion sensitive to noise. In this paper, we present a method for the recovery of ego-motion using omnidirectional cameras. Noting the relationship between spherical projection and wide-angle imaging devices, we propose mapping the image velocity vectors to a sphere, using the Jacobian of the transformation between the projection model of the camera and spherical projection. Once the velocity vectors are mapped to a sphere, we show how existing ego-motion algorithms can be applied and present some experimental results. These results demonstrate the ability to compute egomotion with omnidirectional cameras....

AbstractÐNearly all super-resolution algorithms are based on the fundamental constraints that the super-resolution image should generate the low resolution input images when appropriately warped and down-sampled to model the image formation process. �These reconstruction constraints are normally combined with some form of smoothness prior to regularize their solution.) In the first part of this paper, we derive a sequence of analytical results which show that the reconstruction constraints provide less and less useful information as the magnification factor increases. We also validate these results empirically and show that, for large enough magnification factors, any smoothness prior leads to overly smooth results with very little high-frequency content �however, many low resolution input images are used). In the second part of this paper, we propose a super-resolution algorithm that uses a different kind of constraint, in addition to the reconstruction constraints. The algorithm attempts to recognize local features in the low-resolution images and then enhances their resolution in an appropriate manner. We call such a super-resolution algorithm a hallucination or recogstruction algorithm. We tried our hallucination algorithm on two different data sets, frontal images of faces and printed Roman text. We obtained significantly better results than existing reconstruction-based algorithms, both qualitatively and in terms of RMS pixel error. Index TermsÐSuper-resolution, analysis of reconstruction constraints, learning, faces, text, hallucination, recogstruction. 1

Slanted surfaces pose a problem for correspondence algorithms utilizing search because of the greatly increased number of possibilities, when compared with frontoparallel surfaces. In this paper we propose an algorithm to compute correspondence between stereo images or between frames of a motionsequence by minimizingan energy functional that accounts for slanted surfaces. The energy is minimized in a greedy strategy that alternates between segmenting the image into a number of non-overlapping regions (using the multiway-cut algorithm of Boykov, Veksler, and Zabih) and finding the affine parameters describing the displacement function of each region. A follow-up step enables the algorithm to escape local minima due to oversegmentation. Experiments on real images show the algorithm’s ability to find an accurate segmentation and displacement map, as well as discontinuities and creases, from a wide variety of stereo and motion imagery. 1

Most visual features are parametric in nature, including, edges, lines, corners, and junctions. We propose an algorithm to automatically construct detectors for arbitrary parametric features. To maximize robustness we use realistic multi-parameter feature models and incorporate optical and sensing effects. Each feature is represented as a densely sampled parametric manifold in a low dimensional subspace of a Hilbert space. During detection, the vector of intensity values in a window about each pixel in the image is projected into the subspace. If the projection lies sufficiently close to the feature manifold, the feature is detected and the location of the closest manifold point yields the feature parameters. The concepts of parameter reduction by normalization, dimension reduction, pattern rejection, and heuristic search are all employed to achieve the required efficiency. Detectors have been constructed for five features, namely, step edge (five parameters), roof edge (five parameters), line (six parameters), corner (five parameters), and circular disc (six parameters). The results of detailed experiments are presented which demonstrate the robustness of feature detection and the accuracy of parameter estimation.

A real-time vision system is described that can recognize 100 complex three-dimensional objects. In contrast to traditional strategies that rely on object geometry and local image features, the present system is founded on the concept of appearance matching. Appearance manifolds of the 100 objects were automatically learned using a computer-controlled turntable. The entire learning process was completed in 1 day. A recognition loop has been implemented that performs scene change detection, image segmentation, region normalizations, and appearance matching, in less than 1 second. The hardware used by the recognition system includes no more than a CCD color camera and a workstation. The real-time capability and interactive nature of the system have allowed numerous observers to test its performance. To quantify performance, we have conducted controlled experiments on recognition and pose estimation. The recognition rate was found to be 100 % and object pose was estimated with a mean abso...

Abstract—A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottomup) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented. Index Terms — Image segmentation, nearest neighbor region merging, noise reduction, watershed transform. I.

Automatic on-line signature verification is an intriguing intellectual challenge with many practical applications. I review the context of this problem and then describe my own approach to it, which breaks with tradition by relying primarily on the detailed shape of a signature for its automatic verification, rather than relying primarily on the pen dynamics during the production of the signature. I propose a robust, reliable, and elastic localshape-based model for handwritten on-line curves; this model is generated by first parameterizing each on-line curve over its normalized arc-length and then representing along the length of the curve, in a moving coordinate frame, measures of the curve within a sliding window that are analogous to the position of the center of mass, the torque exerted by a force, and the moments of inertia of a mass distribution about its center of mass. Further, I suggest the weighted and biased harmonic mean as a graceful mechanism of combining errors from multiple models of which at least one model is applicable but not necessarily more than one model is applicable, recommending that each signature be represented by multiple models, these models, perhaps, local and global, shape based and dynamics based. Finally, I outline a signature-verification algorithm that I have implemented and tested successfully both on databases and in live experiments. I.

In computer vision and image processing, edge detection concerns the localization of significant variations of the grey level image and the identification of the physical phenomena that originated them. This information is very useful for applications in 3D reconstruction, motion, recognition, image enhancement and restoration, image registration, image compression, and so on. Usually, edge detection requires smoothing and differentiation of the image. Differentiation is an ill-conditioned problem and smoothing results in a loss of information. It is difficult to design a general edge detection algorithm which performs well in many contexts and captures the requirements of subsequent processing stages. Consequently, over the history of digital image processing a variety of edge detectors have been devised which differ in their mathematical and algorithmic properties. This paper is an account of the current state of our understanding of edge detection. We propose an overview of research...

ion and Mapping with Spatial Constraints # Rama Bindiganavale and Norman I. Badler Computer and Information Science Department University of Pennsylvania# PA 19104#6389# USA Abstract. A new technique is introduced to abstract and edit motion capture data with spatial constraints. Spatial proximities of end#e#ectors with tagged objects during zero#crossings in acceleration space are used to isolate signi#cant events and abstract constraints from an agent#s ac# tion. The abstracted data is edited and applied to another agent of a di#erent anthropometric size and a similar action is executed while main# taining the constraints. This technique is speci#cally useful for actions involving interactions of a human agent with itself and other objects. 1 Introduction When one person mimics the actions of another# the two actions may be similar but not exact. The dissimilarities are mainly due to the di#erences in sizes be# tween the two people# as well as individual performance o...

Theories of visual object recognition must solve the problem of recognizing 3D objects given that perceivers only receive 2D patterns of light on their retinae. Recent findings from human psychophysics, neurophysiology and machine vision provide converging evidence for `image-based' models in which objects are represented as collections of viewpoint-specific local features. This approach is contrasted with `structural-description' models in which objects are represented as configurations of 3D volumes or parts. We then review recent behavioral results that address the biological plausibility of both approaches, as well as some of their computational advantages and limitations. We conclude that, although the image-based approach holds great promise, it has potential pitfalls that may be best overcome by including structural information. Thus, the most viable model of object recognition may be one that incorporates the most appealing aspects of both image-based and structural-description theories. 1998 Elsevier Science B.V. All rights reserved Keywords: Object recognition; Image-based model; Structural description 1.