摘要
为了提高红外小目标的检测精度,采用双边滤波方法去除目标和噪声调整,设置双边滤波的标准差,并模糊化目标和噪声得到背景的估计,得到待选目标区域,通过估计图像的概率密度函数,再根据已有的目标模型与待处理目标区域计算巴氏距离找到最大值,获得目标的准确检测结果。实验表明,该目标检测方法不仅大大提高了检测速度,也提高了小目标的检测精度。
In order to improve the detection accuracy of small infrared target , the bilateral filter was adopted to remove target and adjust noise .The maximum value which was most likely the target position was found accord-ing to the existing target model and image to be processed to search and calculate Bhattacharyya distance though estimating the probability density function of the image .In this position , the standard deviation of bilateral filter was amplified , and target and noise were to be fuzzy to get the estimate of the background , then finally to get the detection results of the target .The experimental results show that this target detection method not only great -ly improves the detection speed , but also improves the accuracy of detection of small targets .
出处
《核电子学与探测技术》
CAS
CSCD
北大核心
2014年第10期1159-1163,共5页
Nuclear Electronics & Detection Technology
基金
国家自然科学基金资助项目(60974005)
关键词
双边滤波
巴氏距离
目标检测
概率密度
bilateral filter
Bhattacharyya distance
target detection
probability density