现阶段无人艇自主航行环境感知，主要用到雷达和光电传感器的射光频信息。雷达可作为导航设备在舰船上广泛使用，但雷达本身不具有判别目标属性的能力，在海洋环境中应用时，易受到海杂波的影响，雷达分辨不出是目标还是海杂波，容易将目标淹没在杂波中，严重时会造成撞船事故。而光电设备分辨率高，可构建海洋环境图像，基于图像的目标识别技术已得到极大发展。本文采用多模态融合的思想，将雷达探测与光电探测两种不同模态的信息融合处理，结合利用各路输入数据的优势互补，有效降低低信噪比环境下雷达虚警率，能够同时获得目标的位置信息和类型信息，经试验数据验证，可以提升水面目标检测的准确率和效率。
At present, the autonomous navigation environment perception of USV uses the radio frequency information of radar and photoelectric sensor. Radar can be widely used on ships as navigation equipment, but it does not have the ability to distinguish target attributes. When it is used in the marine environment, it is vulnerable to sea clutter. The radar can not distinguish whether it is a target or a sea clutter. It is easy to submerge the target in the clutter, which will cause a ship collision accident in serious cases. The photoelectric equipment has high resolution and can construct marine environment images. The image-based target recognition technology has been greatly developed. In this paper, the idea of multi-modal fusion is adopted. The information fusion processing of two different modes of radar detection and photoelectric detection, combined with the complementary advantages of each input data, can effectively reduce the radar false alarm rate in the environment of low signal-to-noise ratio, and can simultaneously obtain the position information and type information of the target. The experimental data verify that the accuracy and efficiency of water surface target detection can be improved.
2022,44(24): 76-80 收稿日期：2022-07-05
DOI：10.3404/j.issn.1672-7649.2022.24.016
分类号：U666
作者简介：柯涛(1981-),高级工程师,主要从事探测系统总体设计研究
参考文献：
[1] 杨勇虎. 基于雷达信息的海上溢油与小目标识别方法[D], 大连:大连海事大学, 2018.
[2] 高铮, 张安清. 海杂波典型幅度分布模型的仿真分析[J]. 舰船电子工程, 2018, 38(9):76-78+94
[3] LI Weibo, ZHANG Youzhi, ZHANG Guangyi. Sea Clutter Simulation Research based on Lognormal Distribution[C]. 信息化与工程国际学会:计算机科学与电子技术国际学会(Computer Science and Electronic Technology International Society), 2016:555-558.
[4] 宋希珍. 海杂波幅度分布参数矩估计和恒虚警检测[D], 西安:西安电子科技大学, 2014.
[5] 张国栋. 基于海杂波混沌特性的杂波抑制的研究[D], 大连:大连海事大学, 2019.
[6] 关泽文, 陈建文, 鲍拯. 一种改进的基于峰值信噪比-高阶奇异值分解的天波超视距雷达自适应海杂波抑制算法[J]. 电子与信息学报, 2019, 41(7):1743-1750
[7] CALLAGHAN D, BURGER J, MISHRA A K. A machine learning approach to radar sea clutter suppression[C]. IEEE Radar Conference, 2017.
