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.

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

Shape indexing is a way of making rapid associations between features detected in an image and object models that could have produced them. When model databases are large, the use of high-dimensional features is critical, due to the improved level of discrimination they can provide. Unfortunately, finding the nearest neighbour to a query point rapidly becomes inefficient as the dimensionality of the feature space increases. Past indexing methods have used hash tables for hypothesis recovery, but only in low-dimensional situations. In this paper, we show that a new variant of the k-d tree search algorithm makes indexing in higherdimensional spaces practical. This Best Bin First, or BBF, search is an approximate algorithm which finds the nearest neighbour for a large fraction of the queries, and a very close neighbour in the remaining cases. The technique has been integrated into a fully developed recognition system, which is able to detect complex objects in real, cluttered scenes in just a few seconds.

easurement error distributions is dependent on the type of geometric feature, the measurement noise model and the nature of the unknown scene-to-model transformation: some examples are presented. A number of variations on the basic labelling algorithm are described, of which some have implications for real-time applications. The algorithm can also be readily implementated on several different types of parallel-processing computers. Key words: Matching, Labelling, Probabilistic Relaxation, Object Recognition. Email: w.christmas@ee.surrey.ac.uk WWW: http://www.surrey.ac.uk/ Acknowledgements I would like to thank my supervisors, Josef Kittler and Maria Petrou, for their guidance and stimulating discussions during the course of this work, and for providing the ideas and motivation that led to the work in the first place. I would also like to thank my other colleagues in the VSSP Group, for their interest and discussions. In particular thanks are due to Ge

. This paper demonstrates a content-based retrieval strategy that can tell whether there are naked people present in an image. No manual intervention is required. The approach combines color and texture properties to obtain an effective mask for skin regions. The skin mask is shown to be effective for a wide range of shades and colors of skin. These skin regions are then fed to a specialized grouper, which attempts to group a human figure using geometric constraints on human structure. This approach introduces a new view of object recognition, where an object model is an organized collection of grouping hints obtained from a combination of constraints on geometric properties such as the structure of individual parts, and the relationships between parts, and constraints on color and texture. The system is demonstrated to have 60% precision and 52% recall on a test set of 138 uncontrolled images of naked people, mostly obtained from the internet, and 1401 assorted control images, drawn f...

Advances in computer speed, memory capacity, and hardware graphics acceleration have made the interactive manipulation and visualization of complex, detailed (and therefore large) three-dimensional models feasible. These models are either painstakingly designed through an elaborate CAD process or reverse engineered from sculpted prototypes using modern scanning technologies and integration methods. The availability of detailed data describing the shape of an object offers the computer vision practitioner new ways to recognize and localize free-form objects. This survey reviews recent literature on both the 3D model building process and techniques used to match and identify free-form objects from imagery. c ○ 2001 Academic Press 1.

Recognition of three dimensional (3D) objects in noisy and cluttered scenes is a challenging problem in 3D computer vision. One approach that has been successful in past research is the regional shape descriptor. In this paper, we introduce two new regional shape descriptors: 3D shape contexts and harmonic shape contexts. We evaluate the performance of these descriptors on the task of recognizing vehicles in range scans of scenes using a database of 56 cars. We compare the two novel descriptors to an existing descriptor, the spin image, showing that the shape context based descriptors have a higher recognition rate on noisy scenes and that 3D shape contexts outperform the others on cluttered scenes.

In this thesis, we describe a statistical method for 3D object detection. In this method, we decompose the 3D geometry of each object into a small number of viewpoints. For each viewpoint, we construct a decision rule that determines if the object is present at that specific orientation. Each decision rule uses the statistics of both object appearance and "non-object " visual appearance. We represent each set of statistics using a product of histograms. Each histogram represents the joint statistics of a subset of wavelet coefficients and their position on the object. Our approach is to use many such histograms representing a wide variety of visual attributes. Using this method, we have developed the first algorithm that can reliably detect faces that vary from frontal view to full profile view and the first algorithm that can reliably detect cars over a wide range of viewpoints.

This paper presents a method for automatically registering multiple three dimensional (3D) data sets. Previous approaches required manual specification of initial pose estimates or relied on external pose measurement systems. In contrast, our method does not assume any knowledge of initial poses or even which data sets overlap. Our automatic registration algorithm begins by converting the input data into surface meshes, which are pair-wise registered using a surface matching engine. The resulting matches are tested for surface consistency, but some incorrect matches may be locally undetectable. A global optimization process searches a graph constructed from these potentially faulty pair-wise matches for a connected sub-graph containing only correct matches, employing a global consistency measure to detect incorrect, but locally consistent matches. From this sub-graph, the final poses of all views can be computed directly. We apply our algorithm to the problem of 3D digital reconstruction of real world objects and show results for a collection of automatically digitized objects.

Registration of two partially-overlapping range images taken from different views is an important task in 3D computer vision. In general, if there is no initial knowledge about the poses of these two views, the information used for solving the 3D registration problem is mainly the 3D shape of the common parts of the two partially-overlapping data sets.