Ghost Points Matter: Far-Range Vehicle Detection with a Single mmWave Radar in Tunnel

2025-09-08

AI Summary

In tunnel environments, millimeter-wave radar suffers from high localization errors and false-positive rates in long-range vehicle detection due to multipath-induced ghost targets. To address this, we propose a ghost-target reutilization method that preserves—rather than filters out—ghost points. By leveraging ray-tracing to reconstruct true reflection paths and incorporating ground geometric constraints with path-loss modeling, we refine their spatial positions. Furthermore, we integrate 3D reflection-path inference with 2D point-cloud segmentation to map ghost points to actual vehicles and achieve precise localization. Evaluated across diverse tunnel scenarios, the method achieves an average F1-score of 93.7%, maintaining 91.0% and 91.5% under occlusion and real-world traffic conditions, respectively, while meeting real-time processing requirements. Our core contribution lies in transforming ghost targets—a conventional source of noise—into valuable perceptual cues, thereby significantly enhancing detection robustness and accuracy in complex multipath environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

Vehicle detection in tunnels is crucial for traffic monitoring and accident response, yet remains underexplored. In this paper, we develop mmTunnel, a millimeter-wave radar system that achieves far-range vehicle detection in tunnels. The main challenge here is coping with ghost points caused by multi-path reflections, which lead to severe localization errors and false alarms. Instead of merely removing ghost points, we propose correcting them to true vehicle positions by recovering their signal reflection paths, thus reserving more data points and improving detection performance, even in occlusion scenarios. However, recovering complex 3D reflection paths from limited 2D radar points is highly challenging. To address this problem, we develop a multi-path ray tracing algorithm that leverages the ground plane constraint and identifies the most probable reflection path based on signal path loss and spatial distance. We also introduce a curve-to-plane segmentation method to simplify tunnel surface modeling such that we can significantly reduce the computational delay and achieve real-time processing. We have evaluated mmTunnel with comprehensive experiments. In two test tunnels, we conducted controlled experiments in various scenarios with cars and trucks. Our system achieves an average F1 score of 93.7% for vehicle detection while maintaining real-time processing. Even in the challenging occlusion scenarios, the F1 score remains above 91%. Moreover, we collected extensive data from a public tunnel with heavy traffic at times and show our method could achieve an F1 score of 91.5% in real-world traffic conditions.

Problem

• Detecting vehicles in tunnels using single mmWave radar with ghost point challenges
• Correcting multi-path reflection ghost points to true vehicle positions accurately
• Recovering complex 3D reflection paths from limited 2D radar data efficiently

Innovation

• Corrects ghost points to true vehicle positions
• Uses multi-path ray tracing algorithm with constraints
• Introduces curve-to-plane segmentation for real-time processing