Predicting Road Surface Anomalies by Visual Tracking of a Preceding Vehicle

2025-05-07

AI Summary

To address the challenge of real-time road surface anomaly detection (e.g., potholes, bumps) under low-visibility conditions, high traffic density, and vehicle-induced camera vibration, this paper proposes a proactive prediction method based on visual tracking of preceding vehicle motion. Using a monocular camera, the approach robustly tracks the preceding vehicle’s trajectory and compensates for camera motion errors caused by vehicle pitch oscillations via an iteratively optimized pitch-angle estimation model. This enables long-range (>30 m), forward-looking inference of road anomalies without requiring explicit anomaly labels. Departing from conventional end-to-end detection paradigms, the method generalizes to unseen anomaly types and demonstrates stable performance in both real-world traffic scenarios and controlled experiments. Implemented on consumer-grade hardware, it operates in real time and provides reliable input for autonomous vehicle chassis-level anticipation and obstacle-avoidance planning.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

A novel approach to detect road surface anomalies by visual tracking of a preceding vehicle is proposed. The method is versatile, predicting any kind of road anomalies, such as potholes, bumps, debris, etc., unlike direct observation methods that rely on training visual detectors of those cases. The method operates in low visibility conditions or in dense traffic where the anomaly is occluded by a preceding vehicle. Anomalies are detected predictively, i.e., before a vehicle encounters them, which allows to pre-configure low-level vehicle systems (such as chassis) or to plan an avoidance maneuver in case of autonomous driving. A challenge is that the signal coming from camera-based tracking of a preceding vehicle may be weak and disturbed by camera ego motion due to vibrations affecting the ego vehicle. Therefore, we propose an efficient method to compensate camera pitch rotation by an iterative robust estimator. Our experiments on both controlled setup and normal traffic conditions show that road anomalies can be detected reliably at a distance even in challenging cases where the ego vehicle traverses imperfect road surfaces. The method is effective and performs in real time on standard consumer hardware.

Problem

• Detecting road anomalies via visual tracking of preceding vehicles
• Compensating camera pitch rotation for accurate anomaly prediction
• Enabling real-time anomaly detection in low visibility conditions

Innovation

• Visual tracking of preceding vehicle for anomaly detection
• Compensate camera pitch rotation robustly
• Real-time performance on consumer hardware