Online multi-target intelligent tracking using a deep long-short term memory network

作     者：Yongquan ZHANG Zhenyun SHI Hongbing JI Zhenzhen SU Yongquan ZHANG;Zhenyun SHI;Hongbing JI;Zhenzhen SU

作者机构：School of Electronic EngineeringXidian UniversityXi’an 710071China School of Computer Science and TechnologyXidian UniversityXi’an 710071China 

出 版 物：《Chinese Journal of Aeronautics》 (中国航空学报（英文版）)

年 卷 期：2023年第36卷第9期

页      面：313-329页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 080202[工学-机械电子工程] 08[工学] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.62276204) Open Foundation of Science and Technology on Electronic Information Control Laboratory,Natural Science Basic Research Program of Shanxi,China(Nos.2022JM-340 and 2023-JC-QN-0710) China Postdoctoral Science Foundation(Nos.2020T130494 and 2018M633470) 

主　　题：Data association Deep long-short term memory network Historical sequence Multi-target tracking Target tuple set Track management 

摘      要：Multi-target tracking is facing the difficulties of modeling uncertain motion and observation *** tracking algorithms are limited by specific models and priors that may mismatch a real-world *** this paper,considering the model-free purpose,we present an online Multi-Target Intelligent Tracking(MTIT)algorithm based on a Deep Long-Short Term Memory(DLSTM)network for complex tracking requirements,named the MTIT-DLSTM ***,to distinguish trajectories and concatenate the tracking task in a time sequence,we define a target tuple set that is the labeled Random Finite Set(RFS).Then,prediction and update blocks based on the DLSTM network are constructed to predict and estimate the state of targets,***,the prediction block can learn the movement trend from the historical state sequence,while the update block can capture the noise characteristic from the historical measurement ***,a data association scheme based on Hungarian algorithm and the heuristic track management strategy are employed to assign measurements to targets and adapt births and *** results manifest that,compared with the existing tracking algorithms,our proposed MTIT-DLSTM algorithm can improve effectively the accuracy and robustness in estimating the state of targets appearing at random positions,and be applied to linear and nonlinear multi-target tracking scenarios.