Rapid Reconstruct 3D window Models from Point clouds

摘要：

Present an approach which can quickly identity window features according to pre-setting parameters and 1CP algorithm, and can rapidly reconstruct their 3D window models. The approach changes the 3D data to 2D by projection, so a high processing efficiency can be reached and can deal with huge quantity of point clouds in semi-automatic style. The experimental results demonstrate that our algorithm can robustly identify window objects with the same shape, even for partial occluded windows.

关键词： point cloud window feature mining features

作者: Dean Luo Liqiong Liao

作者单位: Dept, of surveying and mapping Beijing Univ, of Civil Engineering and Architecture Beijing, PRC

会议类型: 国际会议

会议名称: 2011 6th Joint International Information Technology and Artificial Intelligence Conference(2011年第六届IEEE联合国际信息技术与人工智能会议 IEEE ITAIC 2011)

会议地点: 重庆

会议语种:英文

页码: 960-963

在线出版日期: 2011-08-20（万方平台首次上网日期，不代表论文的发表时间）