基于波原子变换的红外复杂背景杂波抑制算法

针对红外图像弱小目标检测技术中复杂背景杂波干扰问题，提出了一种基于波原子变换的红外图像背景抑制算法。首先，采用波原子变换对图像进行多尺度和多方向分解，获得原始图像的多尺度和多方向细节特征；然后，根据目标和背景杂波信号的差异，通过频域变换设计的系数调整函数修正经波原子变换后各子带系数，再经波原子逆变换重构得到估计的背景图像；最后，将其与原始图像相减获得背景杂波抑制后的图像。用真实的红外图像序列进行实验，结果显示，与最大中值和小波变换两种算法相比，该算法能有效地抑制红外弱小目标复杂背景杂波，突出目标信号，提高信杂比，具有良好的背景抑制性能。

Infrared complex background clutter suppression algorithm based on wave atom transform

A background suppression algorithm based on the wave atom transform (WAT) is proposed to remove the complex background clutter in the detection technique of dim and small targets in infrared images. WAT is used to decompose the input image, and to extract multi-scale and multi-direction detail features of the original image. According to the difference between the target and background clutter signal, each coefficient of the WAT decomposed level is modified by the frequency domain adjustment function, then the predicted background image is reconstructed using wave atom inverse transform. Finally, the result image is obtained by subtracting the background image from the original image. Experimental results demonstrate that the proposed algorithm can highlight targets, improve signal-to-clutter ratio, and suppress complicated background clutter in infrared images with dim and small targets effectively when compared with the max-median and wavelet algorithms.