杨 波,杨子宜.基于遗传算法的点云注册技术研究[J].中南民族大学学报自然科学版,2018,(2):104-108
基于遗传算法的点云注册技术研究
Research on Point Cloud Registration Technology Based on Genetic Algorithm
  
DOI:
中文关键词: 遗传算法  点云配准  KD树  近邻搜索
英文关键词: genetic algorithm  point cloud registration  KD tree  neighbourhood search
基金项目:国家自然科学基金资助项目(61379059) ; 中央高校基本科研业务费专项资助项目(CZY17005)
作者单位
杨 波,杨子宜 中南民族大学 计算机科学学院武汉 430074 
摘要点击次数: 492
全文下载次数: 321
中文摘要:
      提出了一种基于遗传算法的点云配准技术,将点云数据与3D模型进行配准, 对模型建立 KD 树,进行最近邻搜索,获取点云到3D模型中最近的点,根据各点到模型的距离来作为适应度判断依据.仿真结果表明: 该算法达到一定的配准精度,具有全局收敛、 配准时间短、对初始位置要求不高的特点.
英文摘要:
      A point cloud registration technique based on genetic algorithm is proposed to register the point cloud data with the 3D model. This method establishes a KD tree for the model, performs the nearest neighbour search, and obtains the nearest point of the point cloud to the 3D model. The distance from each point to the model is used as the basis for judging fitness. The simulation results show that the algorithm has a certain registration accuracy, with global convergence,registration time is short, the initial position is not strict featured.
查看全文   查看/发表评论  下载PDF阅读器
关闭