51, 041002(2014)
激光与光电子学进展
Laser & Optoelectronics Progress
©2014《中国激光》杂志社
041002-1
基于改进正态分布变换算法的点云配准
张 晓
1, 2
张爱武
1
王致华
1
1
首都师范大学三维信息获取与应用教育部重点实验室, 北京 100048
2
太原理工大学艺术遗产研究中心, 山西 晋中 030600
摘要 正态分布变换(NDT)算法是一种应用在同时定位和地图生成(SLAM)中的点云配准算法。针对地面激光扫描
(TLS)数据的特点,改进了 NDT 算法,提出了一种基于 SURF 的 NDT 配准算法,使之能应用在 TLS 中。该算法首先建
立点云和图像间的映射关系把点云影像化;利用加速稳健特征(SURF)算法提取图像的特征点并找出特征点对;根据
映射关系找到相应的 三维特征匹配点,求出变换矩阵,完成点云初始 配准。在 NDT 算法中,设置初始矩阵为单 位 矩
阵,对点云体素化并使用概率分布函数对点云精细配准。实验结果证明,该算法不但适用于地面激光数据的配准,且
其配准精度高、运算时间少,尤其对于不同分辨率的点云有良好的配准效果。
关键词 图像处理;正态分布变换算法;SURF 算法;点云影像化
中图分类号 TN959.3 文献标识码 A doi: 10.3788/LOP51.041002
Point Cloud Registration Based on Improved Normal Distribution
Transform Algorithm
Zhang Xiao
1, 2
Zhang Aiwu
1
Wang Zhihua
1
1
Key Laboratory of 3D Information Acquisition and Application, Ministry of Education, Capital Normal University,
Beijing 100048, China
2
Research Center of Artistic Heritage, Taiyuan University of Technology, Jinzhong, Shanxi 030600, China
Abstract Normal distribution transform (NDT) algorithm is a point cloud registration algorithm applied in
simultaneous localization and mapping (SLAM). According to the characteristics of terrestrial laser scanning
(TLS) technique, we propose an improved NDT algorithm based on speeded up robust feature (SURF) algorithm
so that it can be applied conveniently in TLS. In this algorithm, firstly the corresponding relation between the
point cloud and the image is created for the point cloud visualization; the feature points are extracted from the
image by using SURF algorithm and the matching feature points are identified; according to the corresponding
relation, the transformation matrix is calculated, and the initial registration of point clouds is completed. In the
NDT, the initial matrix is set as a unit matrix, and the point clouds are divided into three- dimensional voxel
grids and registered precisely by the probability distribution function. The experimental results show that this
algorithm is not only applicable to the registration for TLS, but also exhibits higher registration accuracy and
less calculating time, and it has especially a good registration effect for the point clouds with different
resolutions.
Key words image processing; normal distribution transform algorithm; SURF algorithm; point cloud visualization
OCIS codes 100.2000; 150.0155; 280.3400
收稿日期: 2013-11-05; 收到修改稿日期: 2013-12-03; 网络出版日期: 2014-03-25
基金项目: 国家科技支撑计划(2012BAH31B01)、北京市自然科学基金重点项目(B 类)(KZ201310028035)
作者简介: 张 晓(1973—),女,博士研究生,讲师,主要从事计算机视觉、三维信息获取与应用等方面的研究。
E-mail: zx_2102@163.com
导师简介: 张爱武(1972—),女,教授,博士生导师,主要从事计算机视觉与模式识别、三维信息获取与应用、图像处理等方
面的研究。E-mail: zhangaw98@163.com(通信联系人)
本文电子版彩色效果请详见中国光学期刊网 www.opticsjournal.net