The ICP (Iterative Closest Point) algorithm is widely used for geometric alignment of three-dimensional models when an initial estimate of the relative pose is known. Many variants of ICP have been proposed, affecting all phases of the algorithm from the selection and matching of points to the minimization strategy. We enumerate and classify many of these variants, and evaluate their effect on the speed with which the correct alignment is reached. In order to improve convergence for nearly-flat meshes with small features, such as inscribed surfaces, we introduce a new variant based on uniform sampling of the space of normals. We conclude by proposing a combination of ICP variants optimized for high speed. We demonstrate an implementation that is able to align two range images in a few tens of milliseconds, assuming a good initial guess. This capability has potential application to real-time 3D model acquisition and model-based tracking.

Model-based recognition and motion tracking depends upon the ability to solve for projection and model parameters that will best fit a 3-D model to matching 2-D image features. This paper extends current methods of parameter solving to handle objects with arbitrary curved surfaces and with any number of internal parameters representing articulations, variable dimensions, or surface deformations. Numerical

We present a 3-D shape-based object recognition system for simultaneous recognition of multiple objects in scenes containing clutter and occlusion. Recognition is based on matching surfaces by matching points using the spin-image representation. The spin-image is a data level shape descriptor that is used to match surfaces represented as surface meshes. We present a compression scheme for spin-images that results in efficient multiple object recognition which we verify with results showing the simultaneous recognition of multiple objects from a library of 20 models. Furthermore, we demonstrate the robust performance of recognition in the presence of clutter and occlusion through analysis of recognition trials on 100 scenes. This research was performed at Carnegie Mellon University and was supported by the US Department Surface matching is a technique from 3-D computer vision that has many applications in the area of robotics and automation. Through surface matching, an object can be recognized in a scene by comparing a sensed surface to an object surface stored in memory. When the object surface is matched to the scene surface, an association is made between something known (the object) and

In this paper we present a multiview registration method for aligning range data. We first align scans pairwise with each other and use the pairwise alignments as constraints that the multiview step enforces while evenly diffusing the pairwise registration errors. This approach is especially suitable for registering large data sets, since using constraints from pairwise alignments does not require loading the entire data set into memory to perform the alignment. The alignment method is efficient, and it is less likely to get stuck into a local minimum than previous methods, and can be used in conjunction with any pairwise method based on aligning overlapping surface sections.

Accurate registration between real and virtual objects is crucial for augmented reality applications. Existing tracking methods are individually inadequate: magnetic trackers are inaccurate, mechanical trackers are cumbersome, and vision-based trackers are computationally problematic. We present a hybrid tracking method that combines the accuracy of vision-based tracking with the robustness of magnetic tracking without compromising real-time performance or usability. We demonstrate excellent registration in three sample applications.

Finding people in pictures presents a particularly difficult object recognition problem. We show how to find people by finding candidate body segments, and then constructing assemblies of segments that are consistent with the constraints on the appearance of a person that result from kinematic properties. Since a reasonable model of a person requires at least nine segments, it is not possible to inspect every group, due to the huge combinatorial complexity. We propose two

This paper presents an algorithm for computing the exact aspect graph of an opaque solid bounded by a smooth algebraic surface and observed under orthographic projection. The algorithm uses curve tracing, cell decomposition, and ray tracing to construct the regions of the view sphere delineated by visual events. It has been fully implemented, and examples are presented.

We present a new method for user controlled morphing of two homeomorphic triangle meshes of arbitrary topology. In particular we focus on the problem of establishing a correspondence map between source and target meshes. Our method employs the MAPS algorithm to parameterize both meshes over simple base domains and an additional harmonic map bringing the latter into correspondence. To control the mapping the user specifies any number of feature pairs, which control the parameterizations produced by the MAPS algorithm. Additional controls are provided through a direct manipulation interface allowing the user to tune the mapping between the base domains. We give several examples of sthetically pleasing morphs which can be created in this manner with little user input. Additionally we demonstrate examples of temporal and spatial control over the morph.

AbstractÐThe determination of camera position and orientation from known correspondences of 3D reference points and their images is known as pose estimation in computer vision and space resection in photogrammetry. It is wellknown that from three corresponding points there are at most four algebraic solutions. Less appears to be known about the cases of four and five corresponding points. In this paper, we propose a family of linear methods that yield a unique solution to 4- and 5-point pose determination for generic reference points. We first review the 3-point algebraic method. Then we present our twostep, 4-point and one-step, 5-point linear algorithms. The 5-point method can also be extended to handle more than five points. Finally, we demonstrate our methods on both simulated and real images. We show that they do not degenerate for coplanar configurations and even outperform the special linear algorithm for coplanar configurations in practice. Index TermsÐPose estimation, space resection, 2D-3D image orientation, exterior orientation determination, perspective-n-point-problem, four points, five points. 1

In general, multiple views are required to create a complete 3-D model of an object or a multiroomed indoor scene. In this work, we address the problem of merging multiple textured 3-D data sets, each of which corresponding to a different view of a scene or object. There are two steps to the merging process: registration and integration. Registration is the process by which data sets are brought into alignment. To this end, we use a modified version of the Iterative Closest Point algorithm (ICP); our version, which we call color ICP, considers not only 3-D information, but color as well. This has shown to have resulted in improved performance. Once the 3-D data sets have been registered, we then integrate them to produce a seamless, composite 3-D textured model. Our approach to integration uses a 3-D occupancy grid to represent likelihood of spatial occupancy through voting. The occupancy grid representation allows the incorporation of sensor modeling. The surface of the merged model i...