摘要
在有云层背景的红外序列图像中,检测和跟踪微弱小目标一直是研究的重点。介绍了一种简单可行的在云层背景下检测小目标的方案。算法中,首先进行背景抑制以获得更高的信噪比,接着是用门限分割以得到二值图像,最后依照目标在时间和空间运动的连续性,用一种管线法进行目标识别。实验结果表明算法十分有效。
It is an important task to detect and track the lowly observable and small targets in a sequence of infrared images against cloudy background. A simple and practical scheme about dim small target detection in cloudy background is given. In this scheme, the first step is to suppress the background clutter to obtain the higher SNR of the images. The second step is to segment the image using a threshold to get a binary image. According to the movement continuity of targets in temporal and spatial domain, these targets are identified by a pipeline method. The experimental results prove that the algorithm is very effective. \;
出处
《红外与激光工程》
EI
CSCD
北大核心
2003年第2期148-152,共5页
Infrared and Laser Engineering
关键词
图像处理
高通滤波
图像分割
目标检测
Image procession
High-pass filtering
Image segmentation
Target detection
