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

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.

Computing reflective symmetries of 2D and 3D shapes is a classical problem in computer vision and computational geometry. Most prior work has focused on finding the main axes of symmetry, or determining that none exists.

Much of the recent research in object recognition has adopted an appearance-based scheme, wherein objects to be recognized are represented as a collection of prototypes in a multidimensional space spanned by a number of characteristic vectors (eigen-images) obtained from training views. In this paper, we extend the appearance-based recognition scheme to handle range (shape) data. The result of training is a set of `eigensurfaces ' that capture the gross shape of the objects. These techniques are used to form a system that recognizes objects under an arbitrary rotational pose transformation. The system has been tested on a 20 object database including free-form objects and a 54 object database of manufactured parts. Experiments with the system point out advantages and also highlight challenges that must be studied in future research. 1 Introduction Appearance-based (or `eigenface') approaches to object recognition have demonstrated the ability to recognize large numbers of general obj...

Abstract—We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from multiple object views in determining the final object class and pose estimate. A probabilistic feature space trajectory (FST) in a global eigenspace is used to represent 3D distorted views of an object and to estimate the class and pose of an input object. Confidence measures for the class and pose estimates, derived using the probabilistic FST object representation, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information. We demonstrate the ability to use FSTs constructed from images rendered from computer-aided design models to recognize real objects in real images and present test results for a set of metal machined parts. Index Terms—Active vision, classification, object recognition, pose estimation. 1

We describe a system for querying 3D model databases using the spin image representation as a shape signature for objects depicted as triangular meshes. The spin image representation facilitates the task of aligning the query object with respect to matched models (coarsegrain registration). The main contribution of this work is the introduction of a three-level indexing schema based on artificial neural networks. The indexing schema improves significantly the efficiency in matching query spin images against those stored in the database. Our results are suitable for content-based retrieval in 3D general object databases. A particular application to molecular databases is also presented.

Abstract. In this paper we address the challenge of matching patient geometry to facilitate the design of patient treatment plans in radiotherapy. To this end we propose a novel shape descriptor, the Overlap Volume Histogram, which provides a rotation and translation invariant representation of a patient’s organs at risk relative to the tumor volume. Using our descriptor, it is possible to accurately identify database patients with similar constellations of organ and tumor geometries, enabling the transfer of treatment plans between patients with similar geometries. We demonstrate the utility of our method for such tasks by outperforming state of the art shape descriptors in the retrieval of patients with similar treatment plans. We also preliminarily show its potential as a quality control tool by demonstrating how it is used to identify an organ at risk whose dose can be significantly reduced. 1

eral categories, there are geometric representations in terms of points, lines, and surfaces; symbolic representations in terms of primitive components and their spatial relationships; and functional representations in terms of functional parts and their functional relationships. We will begin with a survey of the most common methods for representing 3D objects and then proceed to the representations required by the most common types of object recognition algorithms. 14.1 Survey of Common Representation Methods Computer vision began with the work of Roberts in 1965 on recognition of polyhedral objects, using simple wire-frame models and matching to straight line segments extracted from images. Line-segment-based models have remained popular even today, but there are also a number of alternatives that attempt to more closely represent the data from objects that can have curved and even free-form surfaces. In this section, we will look at mesh models, surface-edge-vertex models,

Integration of three-dimensional textured scene mapping and object recognition presents many opportunities for assisted automation. We present Artisan, a software package that synthesizes these elements to form a user-friendly whole. Artisan uses a variety of 3D sensors, including laser range scanners and stereo systems, to acquire both image and range data. Artisan automatically finds the transformations between data taken at multiple sensor viewpoints using matching algorithms. The data from these viewpoints are then merged together to form an integrated textured map of the entire scene. Other user or sensor input can also inserted into the scene. Using object recognition with an expandable library of objects, Artisan can identify and locate simple and complex scene features. With this identity and transformation information, it is able to support many operations, including semi-automatic robotic teleoperation and navigation. After mapping and recognition, the identity, position, and orientation of the objects in the scene can be automatically transferred from the Artisan system into other software, including robotic teleoperation packages. Numerous opportunities for automation exist during the operations stage as a result of this increased world knowledge. This work was performed under contracts DE-AR26-97FT34314 and DE-AC21-92MC29104 for the Department of Energy, Federal Energy Technology Center, Morgantown, West Virginia. [BACK TO INDEX] Page 2 of 14 Broz-1 1.

ition. In general categories, there are geometric representations in terms of points, lines, and surfaces; symbolic representations in terms of primitive components and their spatial relationships; and functional representations in terms of functional parts and their functional relationships. We will begin with a survey of the most common methods for representing 3D objects and then proceed to the representations required by the most common types of object recognition algorithms. 14.1 Survey of Common Representation Methods Computer vision began with the work of Roberts in 1965 on recognition of polyhedral objects, using simple wire-frame models and matching to straight line segments extracted from images. Line-segment-based models have remained popular even today, but there are also a number of alternatives that attempt to more closely represent the data from objects that can have curved and even free-form surfaces. In this section, we will look at mesh models, surfa