基于加权引导滤波与时域高通滤波的非均匀性校正算法

Non-uniformity correction algorithm based on weighted guided filter and temporal high-pass filter

为解决基于传统时域高通滤波红外图像非均匀性校正算法存在"鬼影"现象以及固定图案噪声去除不彻底的问题,提出了一种加权引导滤波和改进时域高通滤波相结合的非均匀性校正算法。首先,利用加权引导滤波准确分离红外图像中的空域高频成分;然后,计算红外图像中像素点灰度值变化幅度;最后,在进行时域高通滤波时对红外图像中的运动区域和静止区域使用不同时间常数进行校正。采用两组真实红外图像序列进行实验,并与经典的双边滤波时域高通,均值滤波时域高通非均匀性校正算法进行比较。实验结果表明:文中所提算法在主观视觉和客观评价指标方面优于其他两种算法,有效降低了红外图像的非均匀性,不会产生"鬼影",取得了较好的非均匀性校正效果。

The drawbacks of traditional temporal high pass filter were"ghost artifacts"and fixed pattern noise can′t be removed completely.A non-uniformity correction algorithm that combines weighted guided filter and improved temporal high pass filter was proposed.Firstly,weighted guided filter was used to separate spatial high frequent components from infrared images accurately.Then,the change amplitude of every pixel value was calculated.Finally,different time constants were applied to motion regions and static regions to conduct non-uniformity correction.Two real infrared sequences were adopted in experiments,and space low-pass and temporal high-pass(SLTH)as well as bilateral filter based temporal high-pass filter(BFTH)were used to compare with the proposed algorithm.The experimental results show that the proposed algorithm is superior to the other two algorithms in subjective visual effect and objective evaluation inder.The proposed algorithm can reduce non-uniformity without causing"ghost artifacts"and achieves a better effect of non-uniformity correction.