3D Extended Object Tracking by Fusing Roadside Sparse Radar Point Clouds and Pixel Keypoints

TL;DR

This paper introduces a novel 3D extended object tracking method that fuses roadside radar point clouds and camera keypoints, improving accuracy in estimating object kinematics and extent in complex roadside perception scenarios.

Contribution

It proposes a spherical Gaussian mixture model, elastic skeleton fusion, and a new 3D motion model, advancing the state-of-the-art in roadside 3D object tracking with sensor fusion and probabilistic modeling.

Findings

Outperforms existing 3D EOT methods in simulations and real-world datasets.

Effectively fuses radar and camera data for improved object extent estimation.

Demonstrates robustness in complex 3D vehicle motion scenarios.

Abstract

Roadside perception is a key component in intelligent transportation systems. In this paper, we present a novel three-dimensional (3D) extended object tracking (EOT) method, which simultaneously estimates the object kinematics and extent state, in roadside perception using both the radar and camera data. Because of the influence of sensor viewing angle and limited angle resolution, radar measurements from objects are sparse and non-uniformly distributed, leading to inaccuracies in object extent and position estimation. To address this problem, we present a novel spherical Gaussian function weighted Gaussian mixture model. This model assumes that radar measurements originate from a series of probabilistic weighted radar reflectors on the vehicle's extent. Additionally, we utilize visual detection of vehicle keypoints to provide additional information on the positions of radar reflectors. Since keypoints may not always correspond to radar reflectors, we propose an elastic skeleton fusion mechanism, which constructs a virtual force to establish the relationship between the radar reflectors on the vehicle and its extent. Furthermore, to better describe the kinematic state of the vehicle and constrain its extent state, we develop a new 3D constant turn rate and velocity motion model, considering the complex 3D motion of the vehicle relative to the roadside sensor. Finally, we apply variational Bayesian approximation to the intractable measurement update step to enable recursive Bayesian estimation of the object's state. Simulation results using the Carla simulator and experimental results on the nuScenes dataset demonstrate the effectiveness and superiority of the proposed method in comparison to several state-of-the-art 3D EOT methods.