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.

The creation of three-dimensional digital content by scanning real objects has become common practice in graphics applications for which visual quality is paramount, such as animation, e-commerce, and virtual museums. While a lot of attention has been devoted recently to the problem of accurately capturing the geometry of scanned objects, the acquisition of high-quality textures is equally important, but not as widely studied. In this paper, we focus on methods to construct accurate digital models of scanned objects by integrating high-quality texture and normal maps with geometric data. These methods are designed for use with inexpensive, electronic camera-based systems in which low-resolution range images and high-resolution intensity images are acquired. The resulting models are well-suited for interactive rendering on the latest-generation graphics hardware with support for bump mapping. Our contributions include new techniques for processing range, reflectance, and surface normal data, for image-based registration of scans, and for reconstructing high-quality textures for the output digital object.

Abstract—Motivated by the problem of retinal image registration, this paper introduces and analyzes a new registration algorithm called Dual-Bootstrap Iterative Closest Point (Dual-Bootstrap ICP). The approach is to start from one or more initial, low-order estimates that are only accurate in small image regions, called bootstrap regions. In each bootstrap region, the algorithm iteratively: 1) refines the transformation estimate using constraints only from within the bootstrap region; 2) expands the bootstrap region; and 3) tests to see if a higher order transformation model can be used, stopping when the region expands to cover the overlap between images. Steps 1): and 3), the bootstrap steps, are governed by the covariance matrix of the estimated transformation. Estimation refinement [Step 2)] uses a novel robust version of the ICP algorithm. In registering retinal image pairs, Dual-Bootstrap ICP is initialized by automatically matching individual vascular landmarks, and it aligns images based on detected blood vessel centerlines. The resulting quadratic transformations are accurate to less than a pixel. On tests involving approximately 6000 image pairs, it successfully registered 99.5 % of the pairs containing at least one common landmark, and 100 % of the pairs containing at least one common landmark and at least 35 % image overlap. Index Terms—Iterative closest point, medical imaging, registration, retinal imaging, robust estimation.

The registration problem of multiple range images is fundamental for many applications that rely on precise geometric models. We propose a robust registration method that can align multiple range images comprised of a large number of data points. The proposed method minimizes an error function that is constructed to be global against all range images, providing the ability to diffusively distribute errors instead of accumulating them. The minimization strategy is designed to be efficient and robust against outliers by using conjugate gradient search utilizing M-estimator. Also, for "better" point correspondence search, the laser reflectance strength is used as an additional attribute of each 3D data point. For robustness against data noise, the framework is designed not to use secondary information, i.e. surface normals, in its error metric. We describe the details of the proposed method, and present experimental results applying the proposed method to real data.

We present a perception system, called Artisan, that semi-automatically builds 3-D models of a robot's workspace. Range images are acquired with a scanning laser rangefinder and then processed, based on a systematic sensor characterization, to remove noise and artifacts. Complex 3-D objects represented as surface meshes are subsequently recognized in the range images and inserted into a virtual workspace. This graphical virtual workspace is then used to by human operators to plan and execute remote robotic operations. 1. Introduction Artisan is a system that combines 3-D sensors, object modeling and analysis software, and an operator interface to create a 3-D model of a robot's work area. This paradigm, known as task space scene analysis, provides a much richer understanding of complex, interior work environments than that gleaned from conventional 2-D camera images, allowing an operator to view the work space from inaccessible angles and also to plan and simulate robotic actions wit...

Registration of range images requires the identification of common portions of surfaces between which a distance minimization is performed. This paper proposes a framework for the use of dense attributes of range image elements as a matching constraint in the registration. These attributes are chosen to be invariant to rigid transformations, so that their value is similar in different views of the same surface portion. Attributes can be derived from the geometry information in the range image, such as surface curvature, or be obtained from associated intensity measurements. The method is based on the Iterative Closest Compatible Point algorithm augmented with a random sampling scheme that uses the distribution of attributes as a guide for point selection. Distance minimization is performed only between pairs of points considered compatible on the basis of their attributes. The performance of the method is illustrated on a rotationally symmetric object with color patterns.

In last decade, we have witnessed an increased number of publications related to systems that combine laser scanning and close-range photogrammetry technologies in order to address the challenges posed by application fields as diverse as industrial, automotive, space exploration and cultural heritage to name a few. The need to integrate those technologies is driven by resolution, accuracy, speed and operational requirements, which can be optimized using general techniques developed in the area of multisensor and information fusion theory. This paper addresses an aspect critical to multi-sensor and information fusion, i.e., the estimation of systems uncertainties. The understanding of the basic theory and best practices associated to laser range scanners, digital photogrammetry, processing, modelling are in fact fundamental to fulfilling the requirements listed above in an optimal way. In particular, two categories of applications are covered, i.e., information augmentation and uncertainty management. Results from both space exploration and cultural heritage applications are shown.

The automatic co-registration of point clouds, representing 3D surfaces, is a relevant problem in 3D modeling. This registration problem can be defined as a surface matching problem. We treat it as least squares matching of overlapping surfaces. The point cloud may have been digitized/sampled point by point using a laser scanner device, a photogrammetric method or other surface measurement techniques. In the past, several efforts have been made concerning the registration of 3D point clouds. One of the most popular methods is the Iterative Closest Point (ICP) algorithm. Several variations and improvements of the ICP method have been proposed. In photogrammetry there have been some studies on the absolute orientation of stereo models using DEMs (Digital Elevation Model) as control information. These works are known as DEM matching, which corresponds mathematically with least squares image matching. The DEM matching concept is only applied to 2.5D surfaces. 2.5D surfaces have limited value, especially in close range applications. Our proposed method estimates the 3D similarity transformation parameters between two or more fully 3D surface patches, minimizing the Euclidean distances between the surfaces by least squares. This formulation gives the opportunity of matching arbitrarily oriented 3D surface patches. An observation equation is written for each surface element on the template surface patch, i.e. for each sampled point. The geometric relationship between the conjugate surface patches is defined as a 7-parameter 3D similarity transformation. The constant term of the adjustment is given by the observation vector whose elements are the Euclidean distances between the template and search surface elements. Since the functional model is non-linear, the solution is iteratively approaching to a global minimum. The unknown transformation parameters are treated as stochastic quantities using

Abstract RGB-D cameras are novel sensing systems that capture RGB images along with per-pixel depth information. In this paper we investigate how such cameras can be used in the context of robotics, specifically for building dense 3D maps of indoor environments. Such maps have applications in robot navigation, manipulation, semantic mapping, and telepresence. We present RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment. Visual and depth information are also combined for view-based loop closure detection, followed by pose optimization to achieve globally consistent maps. We evaluate RGB-D Mapping on two large indoor environments, and show that it effectively combines the visual and shape information available from RGB-D cameras. 1