一种小目标快速识别与跟踪方法

A New Method for Small Target Detection and Tracking

提出了一种基于多帧相关技术与波门选通技术相结合的快速目标识别与跟踪方法。利用多级滤波抑制噪声的方法对单帧采集图像进行处理,得到潜在的目标信息,然后利用多帧相关性和目标的运动连续性确定目标;对于后续图像引入波门选通技术,在波门内进行预处理、分割与识别跟踪。探讨了多帧相关技术中目标确定的理论判据,综合考虑目标的尺寸因素和目标的运动特征,提出一种新的波门设定方法。实验结果表明,对于信噪比(SNR)大于等于2.0的图像,该方法能够在获得目标的运动参数及运行轨迹的基础上显著地提高识别效率,实现对运动目标的实时分析,同时更好地抑制背景噪声。

A novel method to detect and track small moving point target in image sequence is proposed in this paper, based on combination of the correlation of multi-frames and wave gate techniques. The detection is divided into two parts： the first part is to identify potential targets in a single frame by using multilevel filter and then to localize the target according to the correlation of multiple frames and the concatenation of the movement. The second part is to detect the target in a selected gate in the following images. In addition, the qualifications to confirm the target and the establishment of the wave gate based on size and moving parameters of the target are stressed in the paper. Based on the experimental results,the method can successfully detect small moving point target and accurately estimate its trajectory in the image sequence with SNR≥2.0. The method is efficient and adaptable to real-time target detection and tracking.