RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud

TL;DR

RaTrack is a novel radar-based moving object detection and tracking method that leverages 4D radar point cloud data, focusing on motion segmentation and estimation to outperform existing approaches in dynamic environments.

Contribution

The paper introduces RaTrack, a pioneering radar-specific tracking method that does not depend on object types or 3D bounding boxes, addressing radar noise and sparsity challenges.

Findings

RaTrack achieves superior tracking accuracy on the View-of-Delft dataset.

It surpasses existing state-of-the-art methods in radar-based moving object tracking.

The approach effectively handles radar noise and point sparsity.

Abstract

Mobile autonomy relies on the precise perception of dynamic environments. Robustly tracking moving objects in 3D world thus plays a pivotal role for applications like trajectory prediction, obstacle avoidance, and path planning. While most current methods utilize LiDARs or cameras for Multiple Object Tracking (MOT), the capabilities of 4D imaging radars remain largely unexplored. Recognizing the challenges posed by radar noise and point sparsity in 4D radar data, we introduce RaTrack, an innovative solution tailored for radar-based tracking. Bypassing the typical reliance on specific object types and 3D bounding boxes, our method focuses on motion segmentation and clustering, enriched by a motion estimation module. Evaluated on the View-of-Delft dataset, RaTrack showcases superior tracking precision of moving objects, largely surpassing the performance of the state of the art. We release our code and model at https://github.com/LJacksonPan/RaTrack.