摘要
针对树木骨架重建要求手工交互多、不精确的问题,提出了用增强Pyr LK光流法对树木骨架进行重建,且可以基于多幅图像完全自动化地进行树木建模.首先在传统Pyr LK光流法的基础上加入了特征点的仿射变换和迭代追踪,提出增强Pyr LK光流法,解决了传统Pyr LK光流法不支持特征点旋转和双向匹配验证的问题;其次利用邻域的泛洪和局部点云的拟合进行高速、准确的树木骨架抽取,提出了三维体素泛洪和最小二乘拟合的方法.实验结果表明,文中方法能够快速重建出极具真实感的三维树木骨架模型.
The reconstruction of tree skeleton suffers from the problems of low accuracy and heavy user in- teraction. In this paper, we propose a new reconstruction method based on an enhanced PyrLK optical flow algorithm to alleviate such problems. First, affine transformation of feature points and interactive tracking are incorporated into traditional PyrLK to improve the robustness of feature matching. Second, we also pro- pose to use 3D voxel-based flooding and least square to extract the tree skeleton after point cloud recon- struction with higher efficiency and accuracy. Experiments show that our reconstruction method is effective and efficient in 3D tree skeletons.
出处
《计算机辅助设计与图形学学报》
EI
CSCD
北大核心
2015年第7期1247-1254,共8页
Journal of Computer-Aided Design & Computer Graphics
基金
国家自然科学基金面上项目(61272276)
国家自然科学基金青年项目(61305091)
国家"十二五"计划重大科技支撑项目(2012BAC11B00-04-03)
高等学校博士学科点专项科研基金项目(博导类)(20130072110035)
吉林省重点科技攻关课题(20140204088GX)
上海市浦江人才计划(13PJ1408200)
长春高新区"长白慧谷"英才计划(3-2013006)
中央高校基本科研业务费专项资金(2100219038)
