面向未知三维物体自动建模的视点规划方法研究  

Investigation into viewpoint planning for unknown 3D-object-oriented automatic modeling

作　　者：何炳蔚[1] 周小龙[1] 

机构地区：[1]福州大学机械工程及自动化学院,福建福州350002

出　　处：《中国工程机械学报》2008年第4期494-498,共5页Chinese Journal of Construction Machinery

基　　金：福建省自然科学基金计划资助项目(E0610013);福建省高等学校新世纪优秀人才支持计划资助项目

摘　　要：提出了1种面向未知三维物体模型的自动测量新方法,重点介绍了视点的规划策略及算法.首先根据线激光视觉测量系统的可视区域,提出1种视点规划策略.并通过比较4个视点的未知区域体积,取区域体积最大者作为下1个最优视点的位置.实验结果表明,提出的算法是可行且有效的.In this study, a new approach to automatic measurement is proposed for unknown 3D-object-oriented modeling. In particular, the viewpoint planning strategies and algorithms are presented. Firstly, a viewpoint planning strategy is developed based on the visualized zone of line-laser vision measurement system. Next, the unknown zone volume is compared from four viewpoints. Then, the viewpoint regarding the maximal value is chosen as the next best view （NBV）. Finally, it is found from the experimental results that the proposed algorithm possesses feasibility and effectiveness.

关 键 词：视点规划 传感器规划 3D重建 下一最优视点 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]