Adaptive Non-Linear Joint Probabilistic Data Association for Vehicle Target Tracking

Shijie Zhao,Tianfei Ma,Pengyu Wang,Konghui Guo,Yang Wang

doi:10.1109/access.2021.3052555

Shijie Zhao, Tianfei Ma + Show 3 more

Open Access

https://doi.org/10.1109/access.2021.3052555

Copy DOI

Abstract

This paper investigated the problem of multi-target tracking (MTT) over a vehicle sensor network. A novel adaptive square root cubature joint probabilistic data association (ASRCJPDA) was proposed. Motivated by enhancing the stability of joint probabilistic data association (JPDA) in practical application, the proposed methodology implemented a numerically stabled cubature Kalman filter for JPDA state estimate process. It improved numerical stability and acquired more accurate estimated results. Additionally, enlightened by enhancing the real time efficiency of JPDA, an adaptive tracking gate designed for the JPDA measurement associate process was proposed. It combined with the kinematics of vehicle to reduce the computational complexity of data association, which improved the robustness of MTT in complex scenarios. The virtual vehicle target tracking scenarios were built in PreScan software in order to better simulate the real traffic condition. Simulations of target tracking examples are presented to show great effectiveness and superiority of the proposed method.

Highlights

Reliable state estimation and rapid data association are critical for real-time multi-target tracking especially in selfdriving field
Taking target 1 longitudinal relative distance for example, the joint probabilistic data association (JPDA)-extend Kalman filter (EKF)-elliptical gate (EG) is about half meter by the metric of mean root mean square position error (MRMSE) in the 50 simulations, which is much higher than ASRCJPDA and JPDA-unscented Kalman filter (UKF)-EG
This paper developed an enhanced version of JPDA by incorporating with the spherical-radial principle and adaptive gating strategy to accommodate the non-linear and unknown clutter environment

Summary

INTRODUCTION

Reliable state estimation and rapid data association are critical for real-time multi-target tracking especially in selfdriving field. S. Zhao et al.: Adaptive Non-Linear Joint Probabilistic Data Association for Vehicle Target Tracking sense [15], [18], [20], [24]. A novel adaptive square root cubature joint probabilistic data association is proposed for multi-target tracking with vehicle sensors in the non-linear cluttered environment. 1) A joint probabilistic data association with square root cubature Kalman filter is presented for multi-target tracking. CONVENTIONAL GATING TECHNIQUES Gating is a general term used to describe techniques that reduce the number of candidate measurements to be considered for further data association This is typically done by defining a validation area on the basis of noise statistics and the set of predicted measurements [28]. Through equation (9), which is proved in APPENDIX, the approximation of posterior mean and error covariance can be addressed

NUMERICALLY STABLE CUBATURE JOINT PROBABILIISTIC DATA ASSOCIATION

ADAPTIVE GATING STRATEGY FOR TARGET TRACKING

NUMERICAL SIMULATIONS

CONCLUSION