|
一种基于多尺度分形新特征的目标检测方法
A Target Detection Method Based on a New Multi-Scale Fractal Feature
查看参考文献10篇
文摘
|
研究复杂自然背景下单帧图像的小目标检测问题。根据人造目标的分形特征随尺度变化比自然背景剧烈这一特点,提出一种多尺度分形新特征。该特征比标准分形维数更好地突出自然背景中的人造目标,对三种图像不同的背景干扰起到了较好的抑制作用。在多尺度分形新特征图像中采用局部直方图统计方法进行目标检测。实验结果表明,基于该特征的目标检测算法对复杂地面背景、海面背景的红外图像和电视图像具有较好的稳健性和普适性,能从单帧图像中较好地检测定位小目标,检测准确率达95%以上。 |
其他语种文摘
|
The detection of small single-frame image is investigated in complicated natural background. A new multi-scale fractal feature is proposed according to the fact that the fractal feature of man-made objects changes shaper than the natural background. The new feature causes the man-made objects to stand out much better from natural background than what can be done by the standard fractal dimensions, thus inhibiting well three kinds of images from different background clutters. Local gray histogram statistics is applied to object detection in the images with multi-scale fractal feature. Experimental results showed that the algorithm to detect the objects with such a feature is quite stable and generally acceptable to IR and TV images in complicated ground or sea background and, especially, it can localize small objects in a single-frame image with an accuracy up to over 95%. |
来源
|
东北大学学报. 自然科学版
,2005,26(11):1062-1065 【核心库】
|
关键词
|
图像识别
;
目标检测
;
分形特征
;
多尺度
;
直方图统计
|
地址
|
1.
东北大学信息科学与工程学院, 辽宁, 沈阳, 110004
2.
中国科学院沈阳自动化研究所, 辽宁, 沈阳, 110016
|
语种
|
中文 |
文献类型
|
研究性论文 |
ISSN
|
1005-3026 |
学科
|
自动化技术、计算机技术 |
基金
|
中国科学院国防科技创新基金
|
文献收藏号
|
CSCD:2176353
|
参考文献 共
10
共1页
|
1.
Chen J Y. A detection algorithm for optical targets in clutter[J].
IEEE Trans Aerospace Electron System,1987,23(1):46-59
|
被引
25
次
|
|
|
|
2.
Tartakovsky A. Effective adaptive spatial-temporal technique for clutter rejection in IRST[A].
SPIE Proceedings Signal and Data Processing of Small Targets,2000:1-11
|
被引
1
次
|
|
|
|
3.
Iranni M. Detection and tracking multiple moving objects using temporal integration[A].
Second European Conference on Computer Vision,1992:282-287
|
被引
2
次
|
|
|
|
4.
Lee C K. A mathematical morphological approach for segmenting heavily noise corrupted images[J].
Pattern Recognition,1996,29(8):1347-1358
|
被引
18
次
|
|
|
|
5.
Davidson G. Wavelet detection scheme for small target in sea clutter[J].
IEEE Electronics Letters,2002,38(19):1128-1130
|
被引
31
次
|
|
|
|
6.
Pentland A P. Fractal-based description of natural scenes[J].
IEEE Trans on Pattern Analysis and Machine Intelligence,1984,6(6):661-674
|
被引
198
次
|
|
|
|
7.
Peli T. Multiscale fractal theory and object characterization[J].
J Opt Soc Amer,1990,7(6):1101-1112
|
被引
13
次
|
|
|
|
8.
薛东辉. 一种基于广义多尺度分形参数的小目标检测方法.
通信学报,1997,18(6):70-75
|
被引
5
次
|
|
|
|
9.
朱红. 一种图像分形特征提取的近似算法.
西安电子科技大学学报,1999,26(2):243-245
|
被引
3
次
|
|
|
|
10.
李会芳. 一种基于多重分形新特征的图像分割算法[J].
光学精密工程,2003,11(6):627-631
|
被引
1
次
|
|
|
|
|
|