Polygonal Model Creation with Precise Boundary Edges from a Mobile Mapping Data
نویسندگان
چکیده
In this paper, we propose a method for creating a threedimensional polygonal model reflecting precise boundary of physical objects from a point cloud which has strong anisotropic distribution of points obtained by a mobile mapping system. Our method creates boundary information of physical objects based on the planar region segmentation by the line-based region growing approach from a point cloud. Then, the boundary information is used for constraining an edge of a polygon in the polygonal model creation procedure. As a result, boundary edges of actual physical objects appear as edges of the polygonal model adequately. The accuracy of boundary edge representation is evaluated by applying the proposed method to a point cloud obtained by simulation of scanning a road polygonal model. Finally, we create a polygonal model from the actual mobile mapping data.
منابع مشابه
Building Solid Models from Polygonal Data
Boundary representations (BRep) of three-dimensional solids are complex data structures that have to be created with topological and geometrical integrity. In many applications, the boundary of a solid may he specified as a list of polygons. In this paper, we consider the problem of constructing a BRep solid model from a list of polygons with the assumption that the points of each polygon lie i...
متن کاملView-invariant Regions and Mobile Robot
| This paper addresses the problem of mobile robot self-localization given a polygonal map and a set of observed edge segments. The standard approach uses interpretation tree search with pruning heuristics to match observed edges to map edges. Our approach introduces a preprocessing step in which the map is decomposed into view-invariant regions (VIRs). The VIR decomposition captures informatio...
متن کاملView-invariant regions and mobile robot self-localization
| This paper addresses the problem of mobile robot self-localization given a polygonal map and a set of observed edge segments. The standard approach uses interpretation tree search with pruning heuristics to match observed edges to map edges. Our approach introduces a preprocessing step in which the map is decomposed into view-invariant regions (VIRs). The VIR decomposition captures informatio...
متن کاملSurface Reconstruction for 3D Robotic Mapping
An important task in mobile robotics is generating consistent environment maps, based on the collected sensor data. In this talk we present a novel method to construct a metric discrete map of the environment, abstracting from the sensor data: The output of a 6D SLAM algorithm is postprocessed to compute a polygonal model. In indoor environments, the model is augmented by an interpretation of t...
متن کاملFeature Line Extraction System for Painter Robots
Our laboratory is constructing a painter robot. The first step in painting is to extract desirable feature lines such as silhouette and boundary lines, which represent the object to be drawn. For this purpose, this thesis proposes a system that extracts feature lines from a textured 3D polygonal model. First, the system builds a textured 3D model of the target object from multiple cameras using...
متن کامل