摘要
为了实现异源遥感图像在部分遮挡情况下配准,提出一种改进粒子群和Hausdorff距离测度图像配准算法。利用尺度不变特征变换算法提取图像特征集,融合部分平均和标准方差思想改进Hausdorff距离,将其作为特征匹配相似性测度。引入正余弦变化动态改变粒子群算法中惯性因子和学习因子,并加入Levy飞行和Logistic混沌机制避免粒子群算法陷入局部最优,将改进的粒子群算法作为特征匹配搜索策略,得到最优解值,从而完成图像配准。实验结果表明,改进的Hausdorff距离测度适应性更强,粒子群算法寻优性能更佳。该图像配准算法具有较好地图像配准效果。
In order to realize the registration of remote sensing images with partial occlusion,an improved particle swarm optimization and Hausdorff distance measure image registration algorithm is proposed.In this algorithm,scale invariant feature transformation algorithm is used to extract image feature set,the idea of partial average and standard deviation is fused to improve Hausdorff distance as feature matching similarity measure;sine cosine change is introduced to dynamically change the inertia factor and learning factor in particle swarm optimization algorithm,and Levy flight and logistic chaos mechanism are added to avoid particle swarm optimization algorithm falling into local optimization.This improved particle algorithm is then used as a searching strategy of feature matching;the optimal solution value is obtained by the group algorithm to complete image registration.Experimental results show that the improved Hausdorff distance measure is more adaptive and the particle swarm optimization algorithm has better performance.The image registration algorithm has a good map image registration effect.
作者
胡明娣
张中茂
许天倚
杨洁
HU Mingdi;ZHANG Zhongmao;XU Tianyi;YANG Jie(School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an 710121,China)
出处
《西安邮电大学学报》
2019年第5期41-46,共6页
Journal of Xi’an University of Posts and Telecommunications
基金
陕西省重点研发计划资助项目(2018KW-050)
