基于人工智能的机动目标跟踪处理研究  

Research on maneuvering target tracking processing based on artificial intelligence

作　　者：曲成华 史新虎[3] 张程 吴金海[4] QU Cheng-hua;SHI Xin-hu;ZHANG Cheng;WU Jin-hai(Key laboratory of aperture array and space detection in anhui province,Hefei Anhui 230088;Institute of the 38th China electronic technology corporation,Hefei Anhui 230088;Unit 63726,people's liberation army of China,Yinchuan Ningxia 750004;Taiyuan satellite launch center,Taiyuan Shanxi 030027)

机构地区：[1]孔径阵列与空间探测安徽省重点实验室 [2]中国电子科技集团公司第三十八研究所 [3]中国人民解放军63726部队 [4]太原卫星发射中心

出　　处：《科技视界》2018年第13期3-5,共3页Science & Technology Vision

摘　　要：现代科技工业的发展促进了各种战斗机、直升机等武器的机动性能和隐身性能,水平机动、垂直机动、空中悬停等战斗动作成为国土防空预警探测领域急需解决的技术难点;近年来,人工智能技术取得了一系列突破性进展,可以用来解决这一难题。此篇论文介绍了人工智能及深度学习知识在雷达信息处理中的相关应用情况,并尝试应用深度学习相关成果和先进理论来解决低小慢目标发现跟踪、高机动目标跟踪、直升机/无人机悬停跟踪等疑难问题,有效提升对机动目标的发现和稳定跟踪能力。the development of modern science,technology and industry to promote the various of motor performance and stealth fighter jets,helicopters and other weapons performance,the level of motor,vertical motor,hovering combat action become urgently needs to solve the technical difficulties of homeland air defense early warning detection field;In recent years,a series of breakthroughs have been made in artificial intelligence technology,which can be used to solve this problem.This paper introduces the artificial intelligence and deep learning knowledge of related applications in radar information processing,and try the deep learning achievements and advanced theory to solve the low found little slow target tracking,high maneuvering target tracking,helicopter/unmanned aerial vehicle(uav)hovering tracking problems,effectively improve the ability of discovery and stability of the maneuvering target tracking.

关 键 词：人工智能 深度学习 机动目标跟踪 航迹相关 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]