摘要
针对LiDAR数据与航空影像融合中的配准问题,提出一种将面特征与点特征相结合的配准方法,首先由LiDAR点云生成深度影像,对深度影像和航空影像提取面特征,在此基础上采用SIFT算子提取点特征,完成LiDAR点云与航空影像的配准。文中方法采取了由面特征到SIFT特征的配准策略,减少了面特征配准的数据量和SIFT算法的计算量。从ISPRS提供的数据集中选取了3组数据进行实验,实验结果表明该方法能有效减少SIFT算子的特征描述符的数量,减少寻找正确匹配点的时间,在保证配准精度的情况下提高配准的效率,适用于城市地区等包含大量面特征地区的LiDAR点云与航空影像配准。
In view of the registration between LiDAR data and aerial image fusion, this paper presents a registration method combining surface feature and point feature. Firstly, the depth image is generated by LiDAR point cloud, and the surface feature is extracted from the depth image and aerial image. On the basis of this, the SIFT operator is used to extract the point features for the registration of LiDAR point cloud and the aerial image. This method adopts a registration strategy from the surface features to the SIFT features, reducing the amount of data for registration of features and the computational complexity of SIFT algorithm. In this paper, three sets of data are selected from the data set provided by ISPRS. The experimental results show that this method can effectively reduce the number of feature descriptors of SIFT operator and the time of finding the correct matching point, and improve the registration efficiency under condition of ensuring the registration accuracy. This is applicable to LiDAR point cloud and aerial image registration including large area of feature area in urban area.
作者
赵中阳
程英蕾
何曼芸
ZHAO Zhongyang;CHENG Yinglei;HE Manyun(Information and Navigation College,Air Force Engineering University,Xi＇an,710077)
出处
《空军工程大学学报（自然科学版）》
CSCD
北大核心
2018年第5期65-70,共6页
Journal of Air Force Engineering University(Natural Science Edition)
基金
国家自然科学基金(41601436)
