一种新的红外弱小目标检测与跟踪算法

针对低信噪比下红外序列图像中弱小目标的检测与跟踪问题,提出了一种新的基于双边滤波的方法.首先将传统的二维双边滤波扩展为空-时三维双边滤波,由于同时利用了红外序列的空域信息和时域信息,该三维双边滤波能在抑制噪声的同时增强目标和背景之间的对比度.用其实现红外图像的预处理,再用门限分割检测出红外序列中的弱小目标.同时,用序贯蒙特卡洛方法对检测到的弱小目标进行跟踪.实验中,用实际红外序列图像对算法进行了验证,结果表明,在低信噪比下,所提算法能对红外弱小目标进行实时检测和跟踪.

A New Method for IR Dim Small Target Detection and Tracking

A new method based on bilateral filter for detecting dim moving point target in IR image sequence is proposed. To make use of temporal information of IR sequence,the traditional 2D bilateral filter is extended to a 3D spatial-temporal bilateral filter in this paper. The 3D bilateral filter has the ability of remove noise efficiently and enhance the contrast between targets and the back- ground. In addition,the Sequential Monte Carlo (SMC) method is employed to track the dim point target on the basis of preprocessing of IR image sequence using 3D bilateral filter. The results in the experiments show that the proposed method is effective in detecting and tracking dim point target in IR sequence.