基于背景差分法的红外图像弱小运动目标识别方法  

A method for recognizing weak moving targets in infrared images based on background difference method

作　　者：李司思 尚帅锟 LI Sisi;SHANG Shuaikun(North China Institute Of Science&Technology,Langfang Hebei 065201,China;Institute of Disaster Prevention,Langfang Hebei 065201,China)

机构地区：[1]华北科技学院,河北廊坊065201 [2]防灾科技学院,河北廊坊065201

出　　处：《激光杂志》2025年第3期142-147,共6页Laser Journal

基　　金：国家重点研发计划资助(No.2017YFC 1500805-02);中央级公益性研究所基本科研业务费专项(No.2020B04);新疆克拉玛依市燃气管网地震安全控制系统研究(No.基本科研业务专项2017B13);河北省自然科学基金面上项目(No.D2022508002);廊坊市哲学社会科学研究课题(No.2023046)。

摘　　要：针对红外图像中目标识别难度较大的问题,提出基于背景差分法的红外图像弱小运动目标识别方法。首先通过时空正则化相关滤波算法处理目标附近大范围内背景区域,并利用侧窗滤波进一步剔除噪声,对低质红外图像降噪保边,提升图像质量,然后采用背景差分法初步识别图像中弱小目标,最后基于初步识别结果,引入卡尔曼滤波预测弱小目标在红外图像中的运动轨迹位置,实现弱小运动目标识别。实验结果表明,所提方法识别成功率较高且识别位置更加准确。Aiming at the difficulty of target recognition in infrared images,a method for identifying weak and small moving targets in infrared images based on background difference method is proposed.Firstly,a spatiotemporal regularization correlation filtering algorithm is used to process a large range of background areas near the target,and side window filtering is used to further remove noise,denoise and preserve edges in low-quality infrared images,and improve image quality.Then,the background difference method is used to preliminarily identify weak and small targets in the image,Finally,based on the preliminary recognition results,Kalman filtering is introduced to predict the motion trajectory position of weak targets in infrared images,achieving weak motion target recognition.The experimental results show that the proposed method has a higher recognition success rate and more accurate recognition position.

关 键 词：背景差分法 红外图像 弱小运动目标 目标识别 卡尔曼滤波 

分 类 号：TN219[电子电信—物理电子学]