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.

We present a terrain mapping system for walking robots that constructs quantitative models of surface geometry.

Structured Light (SL) sensing is a well established method of range acquisition for Computer Vision. This chapter provides thorough discussions of design issues, calibration methodologies and implementation schemes for SL sensors. The challenges for SL sensor development are described and a range of approaches are surveyed. A novel SL sensor, PRIME, the PRofile Imaging ModulE has recently been developed and is used as a design example in the detailed discussions. KEYWORDS: Computer Vision,Range Image Acquisition, Structured Light Ranging, Real-Time Machine Vision, Sensor Calibration 0y This research is sponsored in part by grants awarded by the Japan Railways and the Office of Technology Development, U.S. Department of Energy. 1 Introduction Machine vision as a discipline and technology owes its creation, development and growth to digital computers. Without computers machine vision is not possible. The main objective of machine vision is to extract information useful for performin...

In this paper we present an algorithm for robust absolute position estimation in natural terrain based on landmarks extracted from dense 3-0 surfaces. Our landmarks are constructed by concatenating pose dependent oriented surface points with pose invariant surface signatures into a single feature vector; this definition of landmarks allows a priori pose information to be used to constrain the search for landmark matches. The first step in our algorithm is to extract landmarks from stable and salient surface patches. These landmarks are then stored in a closest point search structure with which landmarks are matched eficiently using available pose constraints and invariant values. Finalb, an iterative pose estimation algorithm, based on least median squares, is wrapped around landmark matching to eliminate outliers and estimate absolute position. To validate our algorithm, we show hundreds of absolute position estimation results from three different natural scenes. These results show that our algorithm can incorporate constraints on position and attitude for eficient landmark matching and match small and dense scene surface patches to large and coarse model surfaces. 1

We investigate the use of interpretation trees to solve the correspondence problem for a mobile robot fusing data from a range image into a world model consisting of planar surface patches. Uncertainty is handled by stochastic techniques where errors are represented by normal joint probability distributions. We show that for problems of a typical size the search time is too long unless the world model can be structured into parts only one of which can be occupied by the robot at any given moment. 1 Introduction This paper is concerned with the correspondence problem within the context of data fusion for a mobile robot. We restrict our attention to the case of a single range imaging sensor delivering planar surface patch features which are to be fused into a world model which also consists of planar patches. A separate problem, which we do not cover here, is how to update the world model once the correspondences have been established, a problem which is not easy because of partial occl...

We describe an analytical method for recovering 3D motion and structure of four or more points from one motion of a stereo rig. The extrinsic parameters are unknown. The motion of the stereo rig is also unknown. Because of the exploitation of information redundancy, the approach gains over the traditional "motion and structure from motion" approach in that less features and less motions are required, and thus more robust estimation of motion and structure can be obtained. Since the constraint on the rotation matrix is not fully exploited in the analytical method, nonlinear minimization can be used to improve the result. Both computer simulated data and real data are used to validate the proposed algorithm, and very promising results are obtained. 1 Introduction We address the general problem of determining 3-D motion and structure from 2-D feature points observed by a binocular stereo rig at two different times. The relative location and orientation between the two cameras, i.e., the...

We derive the analytic transformation for minimizing the summed-squared-distance between three movable points in one three-space pose to three corresponding xed points in another three-space pose. This change of basis is a general rigid-body transformation (translation and rotation), with the addition of a uniform scale. We also derive and present the root-mean-squared distance between the nal transformed points and the xed points. i 1

. In this paper we study the limitations of current verification strategies in object recognition and suggest how they may be enhanced. On the whole object topology is exploited little during verification. In practice, understanding the connectivity relationships between features in the image, or on the object, can lead to significantly more accurate evaluations of recognition hypotheses. We study how topology reasoning allows us to hypothesize the presence of occlusions in the image. Analysis of these hypotheses provides information which turns out to be crucial to the quality of our overall verification results. 1 Introduction In an object recognition system, the process which is most used to differentiate between identification hypotheses is the final stage, called verification. The typical processing path for a recognition system is to start off by extracting features from the image, then to do feature grouping and model selection (indexing), and penultimately a correspondence sta...

We present a method for building models of complex environments from range data gathered at multiple viewpoints. Our approach is unique in that no prior knowledge of the relative positions of the viewpoints is needed in order to register data from them. Furthermore, we present a technique for specification and utilization of so-called “common-sense ” constraints on the transformations between views to improve the accuracy and speed of the registration process. Results are shown from our effort to map a 60 m. by 20 m. multiple-room storage area containing a cluttered array of objects. The problem of building models from multiple views is critical in various applications, including remote operation,

This paper describes a complete stereovision system, which was originally developed for planetary applications, but can be used for other applications such as object modeling. A new effective on-site calibration technique has been developed, which can make use of the information from the surrounding environment as well as the information from the calibration apparatus. A correlation-based stereo algorithm is used, which can produce sufficient dense range maps with an algorithmic structure for fast implementations. A technique based on iterative closest-point matching has been developed for registration of successive depth maps and computation of the displacements between successive positions. A statistical method based on the distance distribution is integrated into this registration technique, which allows us to deal with the important problems such as outliers, occlusion, appearance and disappearance. Finally, the registered maps are expressed in the same coordinate system and are fu...