张宝华，刘艳仙，焦豆豆，周文涛
(内蒙古科技大学信息工程学院，内蒙包头 014010 )
摘要：针对红外小目标图像背景复杂、受杂波干扰严重、目标识别难度高等问题，提出一种基于改进鲁棒性主成分分析与引导滤波的背景抑制方法。首先，利用改进的鲁棒性主成分分析算法对图像降维分解，得到低秩背景块和稀疏前景块，实现背景与目标分离；再利用引导滤波增强稀疏前景块的目标区域边缘轮廓，并利用均值滤波平滑背景区域、抑制杂波和噪声；最后重建低秩矩阵与增强的稀疏矩阵，得到背景抑制图像。实验结果表明，本文方法对红外小目标图像具有较好的背景抑制效果。
关键字：红外小目标；背景抑制；鲁棒性主成分分析；引导滤波
中图分类号：TP391．41 文献标识码：A
Dim and small infrared target background suppression based on improved RPCA and guided filter
Zhang Baohua，Liu Yanxian，Jiao Doudou，Zhou Wentao
(Information Engineering School, Inner Mongolia University of Science and Technology, Baotou 014010,China )
Keywords: Infrared target; Background suppression; robust principal component analysis; Guided filter
Abstract: Infrared small target image is severely affected by the clutter, which is difficult to identify the infrared targt. A novel background suppression method is proposed based on robust principal component analysis and guided filter. Firstly, RPCA is used to decompose the infrared image to obtain a low-rank sparse background block and foreground block to achieve the separation of background and the infrared image. And then guided filter is used to enhance the edge contour of target region, and clutter and noise are smoothed by using mean Filter. Finally, the low-rank matrix and the sparse matrix are reconstructed to obtain background suppression image. The experimental results show that the proposed method has a good background suppression effect