摘要
根据序列胶片图像中运动目标帧间相关特性,提出一种弱小目标检测的方法。采用图像积累的方法,提高信噪比,去除图像背景;采用自适应门限进行阈值分割,得到二值化的图像;利用帧间目标相关的特性去掉噪声点,检测出目标点。实验结果表明,该方法能够有效地提取出低信噪比下序列图像中的微小运动目标。
A detection method for small moving target is proposed according to the COlTelauon oI me target frame - to - frame in sequential images. Image SNR is improved by using energy accumulation meth- od, the background of image is removed. Binaryzation image is obtained through adaptive threshold segmentation. Noise spot is removed and target is detected based on the correlation of target frame - to- frame. The experimental results show that this method can effectively find small target from the sequential images with low SNR.
出处
《长春理工大学学报(自然科学版)》
2007年第2期22-25,共4页
Journal of Changchun University of Science and Technology(Natural Science Edition)
关键词
帧间目标相关
序列图像
运动目标检测
图像处理
correlation of target frame - to - frame
sequence image
moving target detection
image process