基于可视空间的未知三维物体自动建模视点规划方法研究  

Research on view planning method for automatic reconstruction of 3-D unknown objects based on visual region

作　　者：何炳蔚[1,2] 周小龙[1] 

机构地区：[1]福州大学,福建350108 [2]天津大学精密测试技术及仪器国家重点实验室,天津300072

出　　处：《仪器仪表学报》2009年第7期1552-1559,共8页Chinese Journal of Scientific Instrument

基　　金：国家自然科学基金项目(50605007);天津大学精密测试技术及仪器国家重点实验室开放基金;福建省高等学校新世纪优秀人才支持计划(XSJRC2007-07)资助项目

摘　　要：视点规划在三维物体模型自动测量和重建过程中起很重要的作用。本文通过确定线激光视觉测量系统的可视区域,提出将系统可视区域与模型趋势面相结合的未知模型三维自动重建新方法。依据初始视点下所获模型信息,结合可视区域以及趋势面模型确定出有效视点的空间位置参数,并通过比较这些视点下所获模型的曲面面积,将所获面积最大者的位置定为下一个最优视点的位置。最后,通过实体模型的自动重构,验证方法的可行性及有效性。Automatic reconstruction of 3-D object has attracted much attention both in computer vision and graphics communities. In this paper, a new planning approach of generating 3-D model automatically is proposed. The new algorithm incorporates the visual region of the Laser-vision system with the trend surface of the model and selects the suitability of viewpoints as the NBV on scanning coverage. The candidate NBV position is obtained according to the visual region of the system based on the trend surface model. The candidate that obtains maximum surface area is selected as the next-bestview position. Experimental results show that the method is effective in practical implementation.

关 键 词：视点规划 传感器规划 趋势面 3D重建 下一最优视点 

分 类 号：TN248.4[电子电信—物理电子学]