Multi-Object Tracking based on Imaging Radar 3D Object Detection

TL;DR

This paper evaluates various multi-object tracking methods using imaging radar data, addressing challenges posed by sparse radar point clouds and proposing probabilistic association enhancements for improved tracking accuracy.

Contribution

It compares multiple tracking approaches on imaging radar data and introduces probabilistic association algorithms to enhance tracking performance.

Findings

Imaging radar data presents unique challenges for multi-object tracking.

Probabilistic association algorithms improve tracking robustness.

Comparison reveals limitations of existing methods on radar data.

Abstract

Effective tracking of surrounding traffic participants allows for an accurate state estimation as a necessary ingredient for prediction of future behavior and therefore adequate planning of the ego vehicle trajectory. One approach for detecting and tracking surrounding traffic participants is the combination of a learning based object detector with a classical tracking algorithm. Learning based object detectors have been shown to work adequately on lidar and camera data, while learning based object detectors using standard radar data input have proven to be inferior. Recently, with the improvements to radar sensor technology in the form of imaging radars, the object detection performance on radar was greatly improved but is still limited compared to lidar sensors due to the sparsity of the radar point cloud. This presents a unique challenge for the task of multi-object tracking. The tracking algorithm must overcome the limited detection quality while generating consistent tracks. To this end, a comparison between different multi-object tracking methods on imaging radar data is required to investigate its potential for downstream tasks. The work at hand compares multiple approaches and analyzes their limitations when applied to imaging radar data. Furthermore, enhancements to the presented approaches in the form of probabilistic association algorithms are considered for this task.