Towards Multi-Object-Tracking with Radar on a Fast Moving Vehicle: On the Potential of Processing Radar in the Frequency Domain

2026-04-15

AI Summary

This study addresses the challenge of multi-object tracking for high-speed vehicles under strong noise, structural errors, and an unknown number of dynamic targets by proposing a purely radar-driven frequency-domain processing approach. By leveraging the Fourier transform to construct a correlation-based registration mechanism (FS2D), the method simultaneously resolves all moving structures in the scene without requiring sensor fusion, thereby significantly enhancing robustness against noise and structural perturbations. As the first systematic exploration of frequency-domain radar for multi-object tracking, this work overcomes limitations inherent in conventional feature-based methods. Experimental validation on the Boreas dataset demonstrates that radar-only sensing can effectively achieve accurate self-localization and reliable perception of multiple dynamic objects in highly dynamic environments.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

We promote in this paper the processing of radar data in the frequency domain to achieve higher robustness against noise and structural errors, especially in comparison to feature-based methods. This holds also for high dynamics in the scene, i.e., ego-motion of the vehicle with the sensor plus the presence of an unknown number of other moving objects. In addition to the high robustness, the processing in the frequency domain has the so far neglected advantage that the underlying correlation based methods used for, e.g., registration, provide information about all moving structures in the scene. A typical automotive application case is overtaking maneuvers, which in the context of autonomous racing are used here as a motivating example. Initial experiments and results with Fourier SOFT in 2D (FS2D) are presented that use the Boreas dataset to demonstrate radar-only-odometry, i.e., radar-odometry without sensor-fusion, to support our arguments.

Problem

• Multi-Object Tracking
• Radar
• Frequency Domain
• High Dynamics
• Autonomous Racing

Innovation

• frequency domain processing
• radar-only odometry
• multi-object tracking
• Fourier SOFT
• high-dynamic scenes