摘要
针对红外图像目标检测问题,提出了一个改进的差分计盒方法(DBC法)。该方法利用特定应用环境中自然背景的渐变均匀性与人工目标的突变奇异性,改进了差分计盒方法的分形维数计算和J曲线的判别策略。改进后的算法没有运算量的明显增加,能够实现对多个目标的检测,并且对噪声具有更好的鲁棒性。理论分析以及两幅海上和空中目标的实验检测,验证了该算法的有效性和正确性。
A novel detection algorithm for IR artificial targets is presented. The algorithm is based on the difference of fractal dimensions between simple natural background and man-made targets. This feature is calculated and indicated by the J function of each sub-image. Under some preference strategy, the most possible areas with targets are recommended. The experiment results show that the artificial targets could be efficiently detected in maximum possibility.
出处
《火力与指挥控制》
CSCD
北大核心
2007年第9期132-134,共3页
Fire Control & Command Control
关键词
分形维数
自然背景
人工目标
红外图像
目标检测
fractal dimension, natural Background, artificial target, infrared image, target detection
