基于形态学和小波包变换的红外弱小目标检测  

Infrared Dim Small Target Detection Based on Morphology and Wavelet Packet Transform

作　　者：冯洋[1] FENG Yang(School of Physics and Electrical Engineering,Weinan Normal University,Weinan 714000)

机构地区：[1]渭南师范学院物理与电气工程学院,渭南714000

出　　处：《计算机与数字工程》2022年第5期1001-1005,共5页Computer & Digital Engineering

基　　金：陕西省教育厅专项科学研究项目(编号:17JK0271)资助。

摘　　要：针对强起伏背景下红外弱小目标检测问题,提出了一种基于形态学和小波包变换相结合的红外弱小目标检测算法。该算法首先利用形态学Top-hat算子,实现红外小目标图像初步背景抑制,其次采用小波包变换对图像进行多尺度分解得到高低频节点系数,然后采用高频频带中能量分布居中的频带节点系数对图像进行重构完成背景抑制,最后对目标进行分割得到目标检测结果。实验仿真结果表明:该算法背景抑制效果优于Top-hat变换和小波变换的检测方法,可以很好地提升目标和背景的对比度,准确检测出目标信号。For the detection problem of infrared dim small targets under the background of strong fluctuation,an algorithm for detection of infrared dim small targets is proposed based on morphology and wavelet packet transformation.Firstly,the morphological top-hat operator is used to realize the initial background suppression of the infrared small target image.Secondly,the wavelet packet transform is used to decompose the image to obtain the high and low frequency node coefficients.Then the frequency band node coefficient in the middle of the energy distribution in the high frequency band is used to reconstruct the image to complete the background suppression.The simulation results show that the background suppression effect of this algorithm is better than the detection methods of top-hat transform and wavelet transform,which can improve the contrast between the target and the background and detect the target signal accurately.

关 键 词：图像处理 红外图像 背景抑制 形态学 小波包变换 

分 类 号：TN911.73[电子电信—通信与信息系统]