This paper addresses the loop closure detection problem in slam, and presents a method for solving the problem using pairwise comparison of point clouds in both 2D and 3D. The point clouds are mathematically described using features that capture important geometric and statistical properties. The features are used as input to the machine learning algorithm AdaBoost, which is used to build a non...

Different structures are used in peer-to-peer networks to represent their inherently distributed, self-organized, and decentralized memory structure. In this paper, a simple range-queriable distributed data structure, called RAQ, is proposed to efficiently support exact match and range queries over multi-dimensional data. In RAQ, the key space is partitioned among the network with n nodes, in w...

We present new general techniques for static orthogonal range searching problems in two and higher dimensions. For the general range reporting problem in , we achieve query time using space , where denotes the number of stored points and the number of points to be reported. For the range reporting problem on an ! " grid, we achieve query time # $ % & using space ' ( . For the two-dimensional se...

The DALSA Origin camera is an 8 megapixel (MP) single CCD sensor motion picture production camera capable of capturing images containing in excess of 12 stops of exposure latitude and outputting 16bit per pixel linear RAW data files directly to non-linear recording media. This paper examines the key workflow elements required to move through the entire production and post production process in ...

In this paper we report on a successful cooperation of three institutes in the areas of applied image analysis for dentistry. In the application, range images recorded with a high{precision laser sensor are the input to image analysis. Surface patches of varying size and type are tted to the data (Sect. 2). Various views from known positions are used to fuse the computed patches to complete 3D ...

3D facial data has a great potential in overcoming the problems of illumination and pose variation in face recognition. In this paper, we investigate face recognition from range data by facial profiles and surface. An efficient symmetry plane detection method for facial range data is presented to help extract facial profile. A global profile matching method is then exploited to align and compar...

1 . Introduction Outdoor scene analysis is a major Dart of an autonomous vehicle. It allows a vehicle to navigate safely through an unknown environment, to build a internal model Of me environment, and to identify landmarks. Several sources of data can be used to build such a vision system: range finders, color cameras. sonars. While a reliable system would probably use all of these Sensors, ou...

This paper presents a new approach to the problem of building a global map from laser range data, utilizing shape based object recognition techniques originally developed for tasks in computer vision. In contrast to classical approaches, the perceived environment is represented by polygonal curves (polylines), possibly containing rich shape information yet consisting of a relatively small numbe...

This paper describes a volumetric view-merging algorithm that generates a consensus surface of an object from its range images. Our original method merges a set of range images into a volumetric implicit-surface representation, which is converted to a surface mesh by using a variant of the marching-cubes algorithm. We propose a method that increases the computation and memory efficiency for com...