Radar Tracker: Moving Instance Tracking in Sparse and Noisy Radar Point Clouds

2025-07-04

AI Summary

This work addresses the challenging problem of tracking moving vehicle instances in sparse, heavily noisy radar point clouds. To this end, we propose an end-to-end learning framework that jointly leverages temporal offset prediction and attention mechanisms. Departing from conventional center-point tracking paradigms, our method introduces a direct center-point association strategy and a motion-aware segmentation module. By jointly modeling geometric structure and appearance features across frames, it achieves robust inter-frame instance matching and precise instance segmentation. Evaluated on the RadarScenes moving instance tracking benchmark, our approach substantially outperforms existing state-of-the-art methods, achieving significant improvements in key metrics—including MOTA, IDF1, and segmentation accuracy. The proposed framework delivers a more reliable and generalizable solution for motion understanding in radar-centric autonomous driving perception systems.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Robots and autonomous vehicles should be aware of what happens in their surroundings. The segmentation and tracking of moving objects are essential for reliable path planning, including collision avoidance. We investigate this estimation task for vehicles using radar sensing. We address moving instance tracking in sparse radar point clouds to enhance scene interpretation. We propose a learning-based radar tracker incorporating temporal offset predictions to enable direct center-based association and enhance segmentation performance by including additional motion cues. We implement attention-based tracking for sparse radar scans to include appearance features and enhance performance. The final association combines geometric and appearance features to overcome the limitations of center-based tracking to associate instances reliably. Our approach shows an improved performance on the moving instance tracking benchmark of the RadarScenes dataset compared to the current state of the art.

Problem

• Track moving objects in sparse noisy radar data
• Improve segmentation with motion cues and temporal offsets
• Combine geometric and appearance features for reliable tracking

Innovation

• Learning-based radar tracker with temporal offset predictions
• Attention-based tracking for sparse radar scans
• Combined geometric and appearance features for association