测绘学报 ›› 2016, Vol. 45 ›› Issue (1): 96-102.doi: 10.11947/j.AGCS.2016.20140627

• 摄影测量学与遥感 • 上一篇    下一篇

结合图像信息的快速点云拼接算法

王瑞岩, 姜光, 高全学   

  1. 西安电子科技大学通信工程学院综合业务网理论及关键技术国家重点实验室, 陕西 西安 710071
  • 收稿日期:2014-12-03 修回日期:2015-08-18 出版日期:2016-01-20 发布日期:2016-01-28
  • 通讯作者: 姜光, gjiang@mail.xidian.edu.cn E-mail:gjiang@mail.xidian.edu.cn
  • 作者简介:王瑞岩(1986—),女,博士生,研究方向为计算机视觉和三维重建。
  • 基金资助:
    国家自然科学基金(61271296;61403292);高等学校科学创新引智计划基金(B08038)

Fast Registration Method for Point Clouds Using the Image Information

WANG Ruiyan, JIANG Guang, GAO Quanxue   

  1. State Key Laboratory of Integrated Services Networks, School of Telecommunications Engineering, Xidian University, Xi'an 710071, China
  • Received:2014-12-03 Revised:2015-08-18 Online:2016-01-20 Published:2016-01-28
  • Supported by:
    The National Natural Science Foundation of China (Nos. 61271296;61403292);The Program of Introducing Talents of Discipline to Universities (No. B08038)

摘要: 现有三维激光扫描设备通常配有一个同轴相机,它可以对扫描场景进行拍摄。针对带有同轴相机的激光扫描设备,本文提出了一种结合图像信息的快速点云拼接算法。与传统拼接算法同时计算点云间的旋转和平移变换不同,本文对这两种变换分别进行求解。其中,不同扫描点云间的旋转变换是利用视觉几何知识由同轴相机在不同扫描站点下拍摄的图像直接获得,而平移变换是由本文提出的改进ICP 算法得到。在改进的ICP算法中,只有平移变换的3个未知量被迭代计算,其输入是去除旋转变换后的点云。试验结果表明利用图像获得的点云旋转变换具有很高的准确性;并且由于本文算法中迭代过程只针对平移变换的3个变量进行计算,因此与需要迭代计算6个变量的传统ICP算法相比,本文算法计算复杂度大幅降低,同时更易收敛于全局最优值且收敛速度有所提高。

关键词: 点云拼接, 图像信息, 视觉几何, ICP算法

Abstract: On the existing laser scanners, there usually is a coaxial camera, which could capture images in the scanning site. For the laser scanners with a coaxial camera, we propose a fast registration method using the image information. Unlike the traditional registration methods that computing the rotation and translation simultaneously, our method calculates them individually. The rotation transformation between the point clouds is obtained by the knowledge of the vision geometry and the image information, while their translation is acquired by our improved ICP algorithm. In the improved ICP algorithm, only the translation vector is updated iteratively, whose input is the point clouds that removing the rotation transformation. Experimental results show that the rotation matrix obtained by the images has a high accuracy. In addition, compared with the traditional ICP algorithm, our algorithm converges faster and is easier to fall into the global optimum.

Key words: point clouds registration, image information, vision geometry, ICP algorithm

中图分类号: