首页> 外文会议>International Conference on Precision Instrumentation and Measurement >Extraction of Building Facades in Urban Space and Texture Mapping to 3D Polygon Map by Using In-vehicle Camera
【24h】

Extraction of Building Facades in Urban Space and Texture Mapping to 3D Polygon Map by Using In-vehicle Camera

机译:用车载相机提取城市空间和纹理映射到3D多边形地图的建筑立面

获取原文

摘要

Due to the wide diffusion of 3D maps, supporting tools for constructing the 3D maps are required. Individual information necessary for constructing the 3D maps is gathered by some measurement instruments. For example, 3D information and wall textures are acquired by triangulation (or GPS measurement) and optical devices, respectively. Building polygons in a 3D map can be constructed easily by combining the 3D (height) information and a 2D map. It is, however, difficult to obtain an appropriate texture for an arbitrary building polygon by combining those measurements information. In general, the texture mapping with the acquired image is performed manually. However, it takes huge costs to perform in a wide area. Therefore, the demand of the automation is extremely high. In this study, we aim to automatize the texture mapping by image information from the in-vehicle camera. An in-vehicle camera has the advantage that it is possible to take a picture of the building wall while driving over the broad area. But, the vibration and the traffic lane have influences on the photography environment. As a result, it is difficult to specify the building area in the image. In the proposed method, tracks of the camera are calculated from the acquired continuous image, the building area that corresponds to the polygon on the map is specified. In this paper, we described our observation about the result of a miniature model.
机译:由于3D地图的广泛扩散,需要用于构建3D地图的支持工具。构建3D地图所需的个别信息由某些测量仪器收集。例如,通过三角测量(或GPS测量)和光学设备来获取3D信息和墙纹理。通过组合3D(高度)信息和2D地图,可以轻松构建3D地图中的构建多边形。然而,通过组合这些测量信息,难以获得任意构建多边形的适当纹理。通常,手动执行与所获取的图像的纹理映射。但是,在广泛的区域中表现需要巨大的成本。因此,自动化的需求非常高。在本研究中,我们的目标是通过车载相机的图像信息自动化纹理映射。车载摄像机具有以下优点,即可以在宽面积上行驶时拍摄建筑物的照片。但是,振动和交通车道对拍摄环境有影响。结果,很难在图像中指定建筑区域。在所提出的方法中,从获取的连续图像计算相机的轨道,指定与地图上的多边形对应的建筑区域。在本文中,我们描述了我们对微型模型的结果的观察。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号