| 一种多尺度分形特征目标检测方法 |
| |
| 引用本文： | 汪国有,张天序,魏洛刚,桑农.一种多尺度分形特征目标检测方法[J].自动化学报,1997,23(1):121-124. |
| |
| 作者姓名： | 汪国有 张天序 魏洛刚 桑农 |
| |
| 作者单位： | 1.华中理工大学图象所,武汉 |
| |
| 基金项目： | 国家自然科学基金,国防科工委基金 |
| |
| 摘 要： | 自然背景干扰下的自动目标检测是目标检测的一个基本问题.根据尺度变化时自然
场景中人造目标的分形特征变化剧烈这一特点,提出了一种分形参数极值特征的自动目标检
测方法.大量的实验结果表明,分形参数极值特征的自动目标检测方法能较好地完成自然背景
干扰中人造小目标的自动检测.
|
| 关 键 词： | 多尺度 分形参数 目标检测 |
| 收稿时间： | 1994-10-13 |
A Method for Target Detection Using Multiscale Fractal |
| |
| Wang Guoyou,Zhang Tianxu,Wei Luogang,Sang Nong.A Method for Target Detection Using Multiscale Fractal[J].Acta Automatica Sinica,1997,23(1):121-124. |
| |
| Authors: | Wang Guoyou Zhang Tianxu Wei Luogang Sang Nong |
| |
| Affiliation: | 1.Institute of Pattern Recognition&Artificial Intelligence Huazhong University of Science&Technology,Wuhan |
| |
| Abstract: | Automatic object detection from natural scene clutters is fundamental to object detection.When the scale is changed,the fractal features of man made objects in a natural scene change much more violently.In terms of the characterization,this paper presents a new method for automatic target detection using fractal maximum.Experimental results show that the method based on fractal parameter maximum map(FPMM)performs very well for small man made object detection from a natural scene clutter. |
| |
| Keywords: | Multiscale fractal feature target detection |
| 本文献已被 CNKI 维普 等数据库收录！ |
| 点击此处可从《自动化学报》浏览原始摘要信息 |
|
点击此处可从《自动化学报》下载全文 |
|
