Track‐to‐track association algorithm for passive multisensor system based on trajectory parameter

Abstract

Asynchronous sampling and the ghost point are significant issues in the track-to-track association (TTTA) for passive multisensor system. A TTTA algorithm is proposed based on a trajectory parameter to address these issues. According to advantages in which the trajectory information can represent the target motion state and will not change with the sampling time, we turn the TTTA problem into the trajectory parameter matching problem. First, a TTTA model is established by the heading angle and the target velocity. Then, an estimation of target velocity that is suitable for asynchronous sampling is modelled using trajectory parameters from different sensors. Furthermore, to avoid the ghost point in the data association, we use only the bearing measurement of a single sensor to derive the trajectory parameters. Finally, an assignment method is adopted to determine the correspondence between different tracks. The simulation results demonstrate the effectiveness of the proposed method compared with competing algorithms. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Traffic trajectory data analysis technology based on HMM model map matching algorithm

“…Due to the limited accuracy of existing positioning instruments, there may be some deviation between the data collected by the instruments and the actual road conditions. Therefore, it is necessary to match the data with the actual road conditions [ 17 , 18 ]. Track data T is a series of data generated in chronological order, including longitude, dimensionality, and time information, as shown in Eq (1) [ 19 ].…”

Track Correlation Algorithm Based on CNN-LSTM for Swarm Targets

“…(iv) Time series features are extracted, and the track with length is input into LSTM network to extract the characteristic values of the overall track in time series. [7] is the time interval between two track points. The output of LSTM is 1×B vector, and B is the number of final output targets.…”

“…The algorithm in [7] uses LSTM network to replace the flattening layer of CNN. After the CNN network extracts the features of one-dimensional range image, the output features of one-dimensional range image are splicing with the location features, and all the data features after splic-ing are input into LSTM to extract the temporal track features.…”

“…These track correlation algorithms above are mainly aimed at the situation where the number of targets is small and the error is small [7][8][9][10][11]. However, when facing UAV swarm targets, the correlation effect seriously decreases.…”

Multipath Track Association Technique using Characteristics of Conical Bearing in Horizontal Line Array Sonar

“…두 번째 분류로는 다중경로를 이용 한 표적 위치 추정 연구 [5][6][7][8][9] 소나에서 시간에 따라 탐지되는 측정치는 자료 연 관(Data Association)을 통해 트랙으로 추적되며 [10] , 트 랙 간 연관(TTA : Track-to-Track Association)을 통해 관리된다 [11] . 일반적으로 트랙 간 연관은 하나의 표적 을 단일 또는 다종 센서로 탐지하여 발생한 중복 트 랙을 제거하기 위한 목적으로 연구되었지만 [11][12][13][14] 산을 위해서는 음파전달모델인 Bellhop [16] 을 사용하여 음선 추적을 수행하였다. 음선 추적을 위해 GMRT [17] 해저 지형 정보를 이용하였고 수직 음속 구조는 실험 해역에서 XBT로 측정된 자료를 이용하였다(Fig.…”