Learning-Based Extended Object Tracking Using Hierarchical Truncation Measurement Model With Automotive Radar
Artikel i vetenskaplig tidskrift, 2021

This paper presents a data-driven measurement model for extended object tracking (EOT) with automotive radar. Specifically, the spatial distribution of automotive radar measurements is modeled as a hierarchical truncated Gaussian (HTG) with structural geometry parameters that can be learned from the training data. The HTG measurement model provides an adequate resemblance to the spatial distribution of real-world automotive radar measurements. Moreover, large-scale radar datasets can be leveraged to learn the geometry-related model parameters and offload the computationally demanding model parameter estimation from the state update step. The learned HTG measurement model is further incorporated into a random matrix based EOT approach with two (multi-sensor) measurement updates: one is based on a factorized Gaussian inverse-Wishart density representation and the other is based on a Rao-Blackwellized particle density representation. The effectiveness of the proposed approaches is verified on both synthetic data and real-world nuScenes dataset over 300 trajectories.

autonomous driving

Computational modeling

Density measurement

Radar measurements

Automotive engineering

Time measurement

extended object tracking

Automotive radar

NuScenes

Radar

random matrix

Sensors

Författare

Yuxuan Xia

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Pu Wang

Mitsubishi Electric Research Laboratories

Karl Berntorp

Mitsubishi Electric Research Laboratories

Lennart Svensson

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Karl Granström

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik

Hassan Mansour

Mitsubishi Electric Research Laboratories

Petros Boufounos

Mitsubishi Electric Research Laboratories

Philip V. Orlik

Mitsubishi Electric Research Laboratories

IEEE Journal on Selected Topics in Signal Processing

1932-4553 (ISSN)

Vol. 15 4 1013-1029 9351598

Målföljning och djup maskininlärning för trajektorieskattning med tillämpning mot noggranna referenssystem

VINNOVA (2017-05521), 2018-07-01 -- 2022-06-30.

Ämneskategorier

Geofysik

Sannolikhetsteori och statistik

Datorseende och robotik (autonoma system)

DOI

10.1109/JSTSP.2021.3058062

Mer information

Senast uppdaterat

2022-04-05