摘要
Contourlet变换具有多尺度,多方向性的特征,是小波的一种扩展。本文提出了一种基于Contourlet变换的红外小目标检测算法。首先对图像进行Contourlet分解;然后利用能量法提取其局部纹理特征,并计算各点的特征向量与中心向量间的距离,得到一个相关的多尺度距离像;最后根据该距离像进行直方图统计,从而实现目标的检测。文中给出了实验结果,并与基于小波变换的红外小目标检测算法进行了比较,结果表明,本方法能较精确地检测出红外小目标,优于基于小波变换的方法。
A new extension of wavelet transform called contourlet is introduced. With rich set of basis images oriented at varying directions in muhiple scales, Contourlet transform can effectively capture the smooth contours. This paper presents a new small target detection approach, which is based on contourlet transform. This method picks up the texture characteristic from the maps after contourlet transform, and calculates the distance between characteristic vector and center characteristic vector. This can gain a correlative muhiscale distance map. The histogram of distance map is employed for the automatic selection of threshold value. The results of the experiment are showed, and compared with the method based on wavelet transform. The results show that this approach can precisely detect the small infrared target and it is better than the method based on wavelet transform.
出处
《信号处理》
CSCD
北大核心
2008年第4期676-679,共4页
Journal of Signal Processing
