摘要

针对红外复杂背景下的弱小目标检测难题, 提出一种基于背景自适应的多特征融合的复杂背景下弱小目标的检测算法。首先, 通过对红外图像进行空域滤波去除孤立噪声点, 并利用恒虚警率分割消除大面积平稳背景, 获得疑似目标集。然后融合红外图像的背景信息、弱小运动目标的灰度特征、目标与周围像素的方向梯度特征等多个典型特征, 消除疑似目标集中的大部分假目标, 最后运用运动特征获取真实目标的轨迹, 最终实现复杂背景下的红外弱小目标的检测。实验表明: 该算法能实现复杂背景下低信噪比的红外弱小目标快速检测, 具有检测概率高, 算法速度快, 鲁棒性好的特点。

Abstract

In order to solve the problem of infrared dim and small target detection under the complex background of infrared, a detection algorithm for dim and small targets in complex background based on background adaptive multi feature fusion was proposed. Firstly, the isolated noise points are removed by spatial filtering of infrared images, and the constant false alarm rate was used to eliminate large area stationary background and obtain a suspected target set. And then most of the false targets in the suspected target were eliminated by combining the background information of the infrared image, the gray feature of the dim and small moving target and the direction gradient feature of the target and the surrounding pixels. Finally, the detection of infrared dim and small targets in complex background was realized. The experiment shows that the algorithm can realize fast infrared dim and small target detection with low signal to noise ratio under complex background, which has the characteristics of high detection probability, fast speed and good robustness.

补充资料

中图分类号：TP751.1

DOI：10.3788/irla201948.0326002

所属栏目：信息获取与辨识

基金项目：装备预先研究基金(30502030101); 预研项目(2015SQ701033)

收稿日期：2018-10-03

修改稿日期：2018-11-20

网络出版日期：--

作者单位    点击查看

联系人作者：陆福星(lfx110@foxmail.com)

备注：陆福星(1991-), 男, 博士生, 主要从事红外信息处理技术方面的研究。

【1】Huang Fuyu, Shen Xueju, Liu Xumin, et al. Detection of large field of view infrared targets based on spatial-temporal fusion processing [J]. Optical and Precision Engineering, 2015, 23(8): 2328-2338. (in Chinese)
黄富瑜, 沈学举, 刘旭敏,等. 基于空时域融合处理检测超大视场红外目标[J]. 光学 精密工程, 2015, 23(8): 2328-2338.

【2】Wang Fengzhao, Liu Xingtang, Huang Shucai. Multi feature target fusion detection algorithm based on fuzzy evidence theory [J]. Acta Optica Sinica, 2010, 30(3): 713-719. (in Chinese)
王凤朝, 刘兴堂, 黄树采. 基于模糊证据理论的多特征目标融合检测算法[J]. 光学学报, 2010, 30(3): 713-719.

【3】Zhang Qiang, Cai Jingju, Zhang Qiheng. Anisotropic infrared background prediction method[J]. High Power Laser and Particle Beams, 2012, 24(2): 301-306. (in Chinese)
张强, 蔡敬菊, 张启衡. 各向异性的红外背景预测方法[J].强激光与粒子束, 2012, 24(2): 301-306.

【4】Chen Hao, Ma Caiwen, Chen Yuecheng, et al. Multi dim feature detection and tracking algorithm based on multi feature fusion in complex background[J]. Acta Photonica Sinica, 2009, 38(9): 2444-2448. (in Chinese)
陈皓, 马彩文, 陈岳承,等. 基于多特征融合的复杂背景下弱小多目标检测和跟踪算法[J]. 光子学报, 2009, 38(9):2444-2448.

【5】Qin Hanlin, Han Jiaojiao, Yan Xiang, et al. Infrared small moving target detection using sparse representation-based image decomposition[J]. Infrared Physics & Technology, 2016, 76: 148-156.

【6】Yang L, Yang J, Yang K. Adaptive detection for infrared small target under sea-sky complex background [J]. Electronics Letters, 2004, 40(17): 1083-1085.

【7】Hadhoud M M, Thomas D W. The two-dimensional adaptive LMS (TDLMS) algorithm [J]. IEEE Trans Circuits & Syst, 1988, 35(5): 485-494.

【8】Kim S, Lee J. Scale invariant small target detection by optimizing signal-to-clutter ratio in heterogeneous background for infrared search and track[J]. Pattern Recognit, 2012, 45(1): 393-406.

【9】Strickland R N, Hahn H I. Wavelet transform methods for objects detection and recovery[J]. IEEE Transactions on Image Processing, 1997, 6(5): 724-735.

【10】Zhang Zhongyu, Jiao Shuhong. Multi feature fusion infrared ship target detection method[J]. Infrared and Laser Engineering, 2015, 44(S1): 29-34. (in Chinese)
张仲瑜, 焦淑红. 多特征融合的红外舰船目标检测方法[J]. 红外与激光工程, 2015, 44(S1): 29-34.

【11】Zhang Xiangyue, Ding Qinghai, Luo Haibo, et al. Infrared small target detection algorithm based on improved LCM [J].Infrared and Laser Engineering, 2017, 46(7): 0726002. (in Chinese)
张祥越, 丁庆海, 罗海波, 等. 基于改进LCM的红外小目标检测算法[J]. 红外与激光工程, 2017, 46(7): 0726002.

【12】Wang Tian. Infrared dim target detection method based on multi feature fusion technology in cloud background [J]. Information and Computer, 2016(13): 58-59. (in Chinese)
王田. 采用多特征融合技术的云背景红外弱小目标检测方法[J]. 信息与电脑, 2016(13): 58-59.

【13】Li Qiuhua, Li Jicheng, Shen Zhenkang. Infrared image small target detection based on multi-scale feature fusion [J]. System Engineering and Electronic Technology, 2005, 27 (9): 1557-1560. (in Chinese)
李秋华, 李吉成, 沈振康. 基于多尺度特征融合的红外图像小目标检测[J]. 系统工程与电子技术, 2005, 27(9): 1557-1560.

【14】Liu Rang, Wang Dejiang, Jia Ping, et al. Omnidirectional morphology combined with local feature criteria for point target detection[J]. Acta Optica Sinica, 2017, 37(11): 1104001. (in Chinese)
刘让, 王德江, 贾平,等. 全方位形态学联合局部特征准则的点目标检测[J]. 光学学报, 2017, 37(11): 1104001.

【15】Mao Yuxin, Yang Junqiang, Qu Jinsong, et al. Point target detection algorithm based on local entropy. Journal of [J]. Artillery Launch and Control, 2014(3): 41-44. (in Chinese)
毛羽忻, 杨俊强, 曲劲松,等. 基于局部熵的点目标检测算法分析[J]. 火炮发射与控制学报, 2014(3): 41-44.

【16】Liu Y, Chen F, Huang J, et al. Research on the detection technology to dim and small target[C]//Selected Papers From Conferences of the Photo electronic Technology Committee of the Chinese Society of Astronautics. International Society for Optics and Photonics, 2015: 952111.

【17】Salari E, M Li. Dim target tracking with total variation and genetic algorithm[C]//IEEE International Conference on Electro/information Technology, Proc. of IEEE, 2014: 270-274.

引用该论文

Lu Fuxing,Chen Xin,Chen Guilin,Rao Peng. Dim and small target detection based on background adaptive multi-feature fusion[J]. Infrared and Laser Engineering, 2019, 48(3): 0326002

陆福星,陈 忻,陈桂林,饶 鹏. 背景自适应的多特征融合的弱小目标检测[J]. 红外与激光工程, 2019, 48(3): 0326002

被引情况

【1】董 超,冯俊健,田联房,郑 兵. 梯度纹理直方图与多层感知器船舶快速检测. 红外与激光工程, 2019, 48(10): 1026004--1

【2】赵尚男,王灵杰,张 新,吴洪波. 采用视觉特征整合的红外弱小目标检测. 光学 精密工程, 2020, 28(2): 497-506