一种自适应的双门限场面运动目标检测方法  

Adaptive Double-threshold Detection Method of Airport Surface Moving Target

作　　者：吴敏[1] 吴宏刚[1] 姚辉[1] 王凯[2] 蒋李[1] 

机构地区：[1]中国民用航空总局第二研究所科研开发中心,成都610041 [2]四川大学电气信息学院,成都610065

出　　处：《计算机科学》2015年第1期312-316,共5页Computer Science

基　　金：机场增强视景监视系统(2013EG125056);机场(Ⅲ级)综合交通监视与引导系统(2011BAH24B06)资助

摘　　要：为了有效解决在复杂环境下机场场面运动目标的精确检测问题,提出了一种自适应的双门限场面运动目标检测方法。首先采用混合高斯背景模型的方法来提取背景图像,然后使用两个门限值对差分图像进行前景目标分割,低门限阈值用于粗分割以检测出较明显的运动目标,在粗分割的基础上再用高门限阈值进行细分割以去除噪声目标和伪目标,最终得到场面运动目标的准确检测和分割结果。在复杂条件下的场景进行的实验,验证了该方法具有良好的噪声抑制能力和对慢目标良好的鲁棒性,同时能有效地分割出前景目标。To solve the accurate detection of air surface moving targets effectively under complicated environment, an adaptive double-threshold detection method of airport surface moving target was proposed. Firstly, Gaussian mixture model is adopted to extract the background image, and then foreground object of difference image is partitioned off by means of the two threshold value. Namely, low-threshold is used for coarse segmentation to detect moving object, which is obvious. In addition, high-threshold is used for fine segmentation to remove noise target and false target based on coarse segmentation. Finally, airport surface moving target is detected and segmented accurately. The experimental results of complicated background show that this method can avoid the noise, has robustness for the slower moving target and is effective for detecting.

关 键 词：双门限 混合高斯背景模型 背景图像 差分图像 前景目标 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]