近年来,低信噪比图像序列中弱小目标跟踪问题是国内外学者研究的一个热门课题。文中针对弱小目标的背景特性、目标特性和运动特性进行了深入分析,提出了利用序列图像小目标运动的连续性滤除背景以提高信噪比,运用目标本身特征和运动信息确认目标,减少虚警率,从而有效地跟踪弱小目标。算法收敛迅速,跟踪精度高。仿真实验结果表明该方法能够准确高效的检测并跟踪运动小目标。

The effective tracking for dim target in low SNR image sequences has become a hot research field in recent years. The characteristics of background, target and motion were deeply analyzed in this paper. A novel method was proposed to filter the background based on the continuity of the movement of small targets in image sequences. The SNR was enhanced considerably after filtering. The true dim target can be accurately tracked by using the feature of moving targets and motion information. The proposed algorithm astringes rapidly, and has a high accuracy. The experimental results show that the algorithm could detect and track small moving targets with efficiency.