基于梯度互信息的光学影像和LIDAR强度图配准  

Registration of Optical Image and LIDAR Intensity Map by Mutual Information Based on the Gradient

作　　者：王蕾[1] 林立文[1] 

机构地区：[1]武汉大学遥感信息工程学院,湖北武汉430079

出　　处：《地理空间信息》2010年第3期56-58,61,共4页Geospatial Information

基　　金：国家自然科学基金资助项目(40771177);国家863计划资助项目(2006AA12Z136)

摘　　要：LIDAR(激光雷达)数据与其相应的光学影像数据具有诸多互补性,通过配准将这两种影像数据纳入到统一的坐标系下,是实现多源数据融合处理的前提。提出一种顾及两影像空间梯度信息的互信息配准方法。利用高斯核函数构成梯度向量,并结合互信息作为相似性测度,使用粒子群优化算法作为搜索策略;设计在相同投影方式下的LIDAR强度图和航空光学影像的局部配准试验,验证了配准方法的有效性。There are many complementarities between LIDAR（laser radar） data and the corresponding optical image data.It is the premise of multi-resource data fusion by allocating the two data into a unified co-ordinate system through registration.In this paper,registration of the two images with mutual information which took account the gradient had been introduced.It combined the gradient vector which constitute by Gaussian kernel with mutual information as similarity measure,and used Particle Swarm Optimization as a search strategy.At last,it used a local registration test with the aerial imagine and LIDAR intensity map which in a same projection manner to investigate the validity of registration method.

关 键 词：激光雷达 航空影像 强度图 互信息 梯度信息 影像配准 

分 类 号：P237[天文地球—摄影测量与遥感]