应用分形特征的景象匹配仿真
摘 要
为了提高数字景象匹配的技术性能,将分形理论应用于景象匹配领域,提出了一种用于景象匹配的采用归一化方法改进的双毯覆盖算法,并阐述了数字景物图象分形维数的求解方法,同时采用粗匹配和精匹配两级匹配来改善匹配性能.通过仿真,并与常规的平均绝对差算法(MAD)对比,证明方案可行,且技术性能有所提高.另外,还发现匹配概率与实时图的亮度和对比度等因素有关,这对于进一步探索改善该算法的匹配性能,具有重要意义.
关键词
Application of the fractal characteristics for the scene matching simulation
() Abstract
To improve the performance of algorithm, theory of fractal is applied in fields of image registration in this paper. The algorithm improved by unitized covered carpet is provided, and registration probability and speed are improved effectively. The paper also presents the method of calculating fractal character. Through simulation and compared with MAD, the algorithm demonstrates its satisfying effect and value to image registration.
Keywords
|
中国图象图形学报 │ 京ICP备05080539号-4 │ 本系统由