摘要
基于光学图像的目标自动检测与识别是一个研究热点,分形理论的出现为解决这个问题提供了新的技术途径.自然背景与人造目标所在区域的分形维特征差别非常明显.因此,提出了一种分形维的光电目标检测方法.实验证明,给出的目标检测方法结果稳定,优于边缘检测、阈值分割检测,是一种非常有效的方法.
Automatic detection and recognition of targets bases on optical images is a hot point of research. Fractal theory provides a new technical way. Because the difference of fractal dimension between artificial target and natural background is obvious, an electro-optical target detection method based on fractal dimension is proposed. Experiment proved that the given results obtained by the targets detecting method are stable and superior to the edge detection method and the threshold segment method, and it is an effective detection method.
出处
《光电技术应用》
2009年第4期47-50,共4页
Electro-Optic Technology Application
基金
国家自然科学基金(60572160)
关键词
分形维
光电系统
目标检测
fractal dimension
electro-optical system
target detection
