A heuristic method has been developed for registering two sets of 3-D curves obtained by using an edge-based stereo system, or two dense 3-D maps obtained by using a correlation-based stereo system. Geometric matching in general is a difficult unsolved problem in computer vision. Fortunately, in many practical applications, some a priori knowledge exists which considerably simplifies the problem. In visual navigation, for example, the motion between successive positions is usually approximately known. From this initial estimate, our algorithm computes observer motion with very good precision, which is required for environment modeling (e.g., building a Digital Elevation Map). Objects are represented by a set of 3-D points, which are considered as the samples of a surface. No constraint is imposed on the form of the objects. The proposed algorithm is based on iteratively matching points in one set to the closest points in the other. A statistical method based on the distance distribution is used to deal with outliers, occlusion, appearance and disappearance, which allows us to do subset-subset matching. A least-squares technique is used to estimate 3-D motion from the point correspondences, which reduces the average distance between points in the two sets. Both synthetic and real data have been used to test the algorithm, and the results show that it is efficient and robust, and yields an accurate motion estimate.

Using known camera motion to estimate depth from image sequences is an important problem in robot vision. Many applications of depth-from-motion, including navigation and manipulation, require algorithms that can estimate depth in an on-line, incremental fashion. This requires a representation that records the uncertainty in depth estimates and a mechanism that integrates new measurements with existing depth estimates to reduce the uncertainty over time. Kalman filtering provides this mechanism. Previous applications of Kalman filtering to depth-from-motion have been limited to estimating depth at the location of a sparse set of features. In this paper, we introduce a new, pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. We describe the algorithm and contrast its formulation and performance to that of a feature-based Kalman filtering algorithm. We compare the performance of the two approaches by analyzing their theoretical convergence rates, by conducting quantitative experiments with images of a flat poster, and by conducting qualitative experiments with images of a realistic outdoor-scene model. The results show that the new method is an effective way to extract depth from lateral camera translations. This approach can be extended to incorporate general motion and to integrate other sources of information, such as stereo. The algorithms we have developed, which combine Kalman filtering with iconic descriptions of depth, therefore can serve as a useful and general framework for low-level dynamic vision.

This paper discusses how local measurements of three-dimensional pool[ions and surface normals (recorded by a set of tactile sensors, or by threedimensional range sensors), may be used o identify and locate objects, from among a set, of known objects. The objects are modeled as po!yhedra having up to six degrees of freedom relative to the sensors. We show tiat inconsistent, hypotheses about pairings between sensed points and object, surfaces can be discarded efficiently by using local constraints on: distoances bet,ween faces, angles betwee, face normals, and angles (reiatAve to t. he surface normals) of vectors between sensed points. We show by simulation and by mathematical bounds that the number of hypotheses consisten; with these constraints is small. We also show how to recover the position and orient, at, ion of the object from the sense daiwa. The algorithm's performance on data obt,ained from a triangulation range sensor is illustrated.

Motion correspondence is a fundamental problem in computer vision and many other disciplines. This article describes statistical data association techniques originally developed in the context of target tracking and surveillance and now beginning to be used in dynamic motion analysis by the computer vision community. The Mahalanobis distance measure is first introduced before discussing the limitations of nearest neighbor algorithms. Then, the track-splitting, joint likelihood, multiple hypothesis algorithms are described, each method solving an increasing-ly more complicated optimization. Real-time constraints may prohibit the application of these optimal methods. The suboptimal joint probabilistic data association algorithm is therefore described. The advantages, limitations, and relationships between the approaches are discussed. 1

We address in this paper the problem of self-calibration and metric reconstruction (up to a scale) from one unknown motion of an uncalibrated stereo rig, assuming the coordinates of the principal point of each camera are known (This assumption is not necessary if one more motion is available). The epipolar constraint is first formulated for two uncalibrated images. The problem then becomes one of estimating unknowns such that the discrepancy from the epipolar constraint, in terms of distances between points and their corresponding epipolar lines, is minimized. The initialization of the unknowns is based on the work of Maybank, Luong and Faugeras on self-calibration of a single moving camera, which requires to solve a set of so-called Kruppa equations. Redundancy of the information contained in a sequence of stereo images makes this method more robust than using a sequence of monocular images. Real data have been used to test the proposed method, and the results obtained are quite goo...

We examined how depth information from two different cue types (object motion and texture gradient) is integrated into a single estimate in human vision. Two critical assumptions of a recent model of depth cue combination (termed modified weak fusion) were tested. The first assumption is that the overall depth estimate is a weighted linear combination of the estimates derived from the individual cues, after initial processing needed to bring them to a common format. The second assumption is that the weight assigned to a cue reflects the apparent reliability of that cue in a particular scene. By this account, the depth combination rule is linear and dynamic, changing in a predictable fashion in response to the particular scene and viewing conditions. A novel procedure was used to measure the weights assigned to the texture and motion cues across experimental conditions. This procedure uses a type of perturbation analysis. The results are consistent with the weighted linear combination rule. In addition, when either cue is corrupted by added noise, the weighted linear combination rule shifts in favor of the uncontaminated cue.

Abstract not found

Visual processing tasks often require the matching of contours in two images. Examples include determining image motion and matching features for object recognition. We propose a scheme that takes partial constraints on the matching between contours in two images and finds the matches between these contours using local affine transformations.

Abstract not found

Zero-crossing or feature-point based stereo algorithms can, by definition, determine explicit depth information only at particular points in the image. To compute a complete surface description, this sparse depth map must be interpolated. A computational theory of this interpolation or reconstruction process, based on a surface consisteno' onslrain has previously been proposed. In order to provide stronger boundary conditions for the interpolation process, other visual cues to surhce shape are examined in this paper. In particular, it is shown that, in principle, shading information from the two views can be used to determine the orientation of the surface normal along the feature-point contours, as well as the parameters of the reflective properties of the surface material. The numerical stability of the resulting equations is also examined.