摘要
该文提出了一种从背景移动红外图像中自动检测运动目标的算法。该算法首先采用图像灰度互相关度量的匹配算法对连续的6帧序列进行配准,用第1帧和第4帧配准,第2帧和第5帧配准,第3帧和第6帧配准,然后用配准后的图像对分别做差分运算,再将3个差分图像按像素相乘,在运动目标处得到了非常尖锐的相关峰。这为进一步自动跟踪目标提供了一个跟踪窗口的中心点。实验结果验证了该方法的有效性。
An approach to detecting moving objects from infrared image sequence on displacing background is proposed in this paper. First the correlation matching technique is used for registering five pictures with the sixth one. Then the registered images are processed to calculate the image differences between the first and fourth, the second and fifth, the third and sixth. After these difference images are multiplied, a very high correlation peak is obtained. Using this method a central point for tracking window can be provided. The experimental results illustrate that this approach is available to this situation.
出处
《电子与信息学报》
EI
CSCD
北大核心
2005年第1期43-46,共4页
Journal of Electronics & Information Technology
关键词
运动目标检测
红外图像
配准
相关度量
图像差分
Detecting moving objects, Infrared image, Registration, Correlation measurement, Image differences
