结构化场景重建中一种融合直线信息的平面拟合方法  

A plane fitting approach using line information to reconstruct structured scenes

作　　者：傅康平[1] 王伟[1] 胡立华[2] 胡占义[1] 

机构地区：[1]中国科学院自动化研究所模式识别国家重点实验室,北京100190 [2]太原科技大学计算机学院,太原030024

出　　处：《中国科学：信息科学》2015年第7期889-902,共14页Scientia Sinica(Informationis)

基　　金：国家自然科学基金(批准号:61333015,61273280)资助项目

摘　　要：结构化场景是三维重建中非常重要的一类场景.本文分析了结构化场景的特点,并针对该类场景下多视立体点云的平面拟合问题,提出了一种融合直线信息的改进PEaRL算法.本文方法首先利用三维直线模型和三维点云模型生成候选平面.直线信息的引入使候选平面的数量得以降低,同时其可靠性得以提升.然后,利用直线对点云的邻接关系进行约束,提高了平面相交处的平面拟合准确性.在能量优化过程中,本文方法对PEaRL算法所使用能量函数的平滑项和标记惩罚项进行了改进,以更好地适应多视立体点云的不规则性.在模拟数据和真实数据集上的对比实验表明,本文方法有较高的运行效率,且可获得比PEaRL等多模型拟合算法更可靠的平面拟合结果.Structured scenes are an important element of 3D reconstruction. Characteristics of structured scenes are analyzed, based on which a modified PEARL algorithm is proposed to perform plane fitting on points pro- vided by multiple view stereo algorithms. In this method, candidate planes are generated from both 3D lines and 3D points. The number of candidate planes is reduced using information provided by the 3D lines further- more, the reliability of the planes is improved. Subsequently, 3D lines are employed to obtain a more reliable neighborhood system, which leads to more accurate plane fitting results at plane intersections. For energy opti- mization, the smoothness term and label cost term are improved to better manage the irregularity of multi-view stereo （MVS） point clouds. Experiments on synthesized and actual data show that the proposed method provides satisfactory time efficiency, and obtains more reliable plane fitting results than other multi-model fitting methods, including PEARL.

关 键 词：结构化场景 平面拟合 模型拟合 能量优化 MVS PEARL 三维直线 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]