天空地一体化多目标跟踪算法研究综述  

Survey on Space-Air-Ground Integrated Multi-target Tracking Algorithms

作　　者：闫莉萍[1] 刘晗钊 夏元清[1] YAN Liping;LIU Hanzhao;XIA Yuanqing(School of Automation,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]北京理工大学自动化学院,北京100081

出　　处：《信号处理》2024年第11期1951-1971,共21页Journal of Signal Processing

基　　金：国家自然科学基金(62073036);北京市自然科学基金(4242049)。

摘　　要：为实现全时全域“泛在连接”,构建天空地一体化网络已成为国家重大需求,而基于天空地一体化网络下跨域协同系统进行多目标跟踪是其中一个重要的发展方向,其在军民用领域都极具应用价值。本文详细阐述了天空地一体化网络背景下多目标跟踪方法研究进展。首先,介绍了天空地一体化跨域协同多目标跟踪的研究背景与意义。其次,从基于视觉的多目标跟踪、基于模型的多目标跟踪和基于多模态融合的多目标跟踪三个方面概述了当前的代表性研究方法:在基于视觉的多目标跟踪算法方面,介绍了单摄像头和多摄像头融合的多目标跟踪方法;对于基于模型的多目标跟踪,先介绍了单传感器多目标跟踪方法,以及在多种复杂场景下的改进,然后介绍了多传感器融合方法;在基于多模态信息融合的目标跟踪方面,在对多传感器时空配准方法和有代表性的多模态信息融合方法介绍的基础上,概括了基于多模态融合的多目标跟踪算法。最后探讨了当前存在的问题和未来发展方向:无论基于视觉的还是基于模型的多目标跟踪方法都有不少问题有待解决,特别是两种方法的结合值得深入研究;在面临复杂干扰时,基于多传感器信息融合的多目标跟踪由于能实现信息的互补,成为未来的主流发展方向;此外,跨域协同系统,由于能利用更多的资源和信息,其多目标跟踪问题研究极具价值,不过其中通信安全问题和多目标跟踪模型轻量化问题值得探讨。本文对从事目标跟踪及空天地一体化协同控制相关理论与技术研究的科研工作者具有重要参考价值。Building a space-air-ground integrated network has become a national demand to achieve ubiquitous connectivity in all time and space.Multi-target tracking based on cross domain collaborative systems under the space-air-ground integrated network is important,having great application value in both military and civilian fields.This paper elaborates on the research progress of multi-target tracking methods in the context of a space-air-ground integrated network.First,the research background and significance of cross domain collaborative multi-target tracking for space-air-ground integration are introduced.Second,representative research methods are reviewed from three aspects:visual-based,modelbased,and multi-modal fusion-based multi-target tracking.In terms of vision-based multi-target tracking algorithms,single camera and cross camera fusion multi-target tracking are introduced.Regarding model-based multi-target tracking,we first introduce the single-sensor multi-target tracking method and its improvement in a variety of complex scenarios,and then introduce the multi-sensor fusion method.In terms of target tracking based on multimodal information fusion,after introducing the multi-sensor spatiotemporal registration methods and representative multimodal information fusion methods,the main algorithms of multi-target tracking based on multimodal fusion are summarized.Finally,the existing problems and future development directions in the field of multi-target tracking are discussed.Both visualand model-based multi-target tracking methods have numerous problems that need to be solved,and the combination of the two methods is worthy of in-depth research.When facing complex interference,multi-target tracking based on multisensor information fusion has become the mainstream development direction owing to its ability to achieve complementary information.In addition,cross-domain collaborative systems,owing to their ability to utilize more resources and information,have great application potential in multi-target tracking prob

关 键 词：天空地一体化 视觉目标跟踪 随机有限集 多模型 多模态信息融合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]