强激光与粒子束, 2005, 17 (7): 983, 网络出版: 2006-04-28   

基于小波变换和数据融合技术的弱小目标检测

Faint target detection based on wavelet transform and data fusion technology
作者单位
中国工程物理研究院应用电子学研究所,四川,绵阳,621900
摘要
鉴于弱小目标检测所固有的难点及常用的单一分辨率下的检测方法还不能准确稳定地检测出目标,提出了一种弱小目标检测新方法.考虑到实际应用中的复杂背景和大量干扰噪声,运用数据融合技术,先对图像进行小波多分辨率分解,然后将不同分辨率下的子图进行最优加权平均融合来检测弱小目标.用实地拍摄的空中弱小目标红外和可见光图像分别进行实验验证,实验图像取256×256像素点阵大小,其中目标占10×10像素左右.结果表明该方法能够准确稳定地检测弱小目标,为后续的跟踪作了很好的铺垫.
Abstract
Target detection in a sequence of image is difficult when this target is small, faint, and obscured. In this paper, a method based on wavelet multi-resolution analysis and data fusion technology is presented for faint-target detection. The detection method is put forward with the consideration of the practicality of the method, especially while the image involves the complex background and a lot of noise. First, the image is decomposed using wavelet transform. The second part of the algorithm performs a data fusion using the sub-images of different resolution. It is shown that the algorithm can detect the faint target with accuracy and stabilization in the experiment using real images. The size of these experimental images is 256×256 pixels, and the size of target in the image is under 10×10 pixels.
参考文献

[1] 顾静良, 张卫,万敏. 基于灰度形态学和邻域熵值的弱小目标检测[J]. 强激光与粒子束, 2004,16(12):1527-1530.
Gu J L, Zhang W, Wan M. Weak targets detection based on gray morphological and neighborhood entropy method[J]. High PowerLaser and Particle Beams, 2004,16(12):1527-1530.

[2] 易亨瑜, 叶一东, 张卫, 等. 云层背景中目标的相关识别[J]. 强激光与粒子束, 2002,14(5):693-696.
Yi H Y, Ye Y D, Zhang W, et al. Detection of targets under complicated background of cloud[J]. High PowerLaser and Particle Beams, 2002,14(5):693-696.

[3] Bar-Shalom Y. Multitarget-multisensor tracking: advanced applications[M]. Boston, MA: Artech House, 1989. 167-206.

[4] 晁锐, 张科, 李言俊. 一种基于小波变换的图像融合算法[J]. 电子学报, 2004, 32(5):750-753.
Huang R, Zhang K, Li Y J. An image fusion algorithm using wavelet transform[J]. Acta Electronica Sinica, 2004, 32(5):750-753.

[5] Abdelkawy E, Mcgaughy D. Wavelet-based image target detection methods[A]. Automatic target recognition XIII, Proceeding of SPIE[C]. 2003, 5094:337-347.

[6] Daubechies I. The wavelet transform, time-frequency localization and signal analysis[J]. IEEE Trans on information theory, 1990, 36(5):961-1005.

[7] Mallats. A theory for multi-resolution signal decomposition: The wavelet representation[J]. IEEE Trans on patterns analysis and machine intelligence, 1989, 11(7):674-693.

[8] 李秋华, 李吉成, 沈振康, 等. 一种基于D-S证据理论的红外小目标融合识别方法[J]. 系统工程与电子技术,2002, 24(6):25-27.
Li Q H, Li J C, Shen Z K, et al. IR small target recognition based on the D-S evidential theory[J]. Systems Engineering and Electronics, 2002, 24(6):25-27.

[9] 李宏, 刘江涛, 安玮, 等. 主观Bayes方法与神经网络相结合的多传感器数据融合空间点目标识别方法[J]. 红外与毫米波学报,1997,16(6):448-454.
Li H, Liu J T, An W, et al. Multi-sensor data fusion method to recognize spatial point targets based on the combination of subjective bayes and neural network[J]. J Infrared millim waves, 1997, 16(6):448-454.

[10] Alexander Tartakovsky, Skirmantas Kligys, Anton Petrov. Adaptive sequential algorithms for detecting targets in a heavy IR clutter[A]. Signal and data processing of small targets 1999, Processing of SPIE[C]. 1999, 3809:119-130.

顾静良, 李万敏, 张卫, 郑捷. 基于小波变换和数据融合技术的弱小目标检测[J]. 强激光与粒子束, 2005, 17(7): 983. GU Jing-liang, WAN Min, ZHANG Wei, ZHENG Jie. Faint target detection based on wavelet transform and data fusion technology[J]. High Power Laser and Particle Beams, 2005, 17(7): 983.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!