Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography

TL;DR

This paper introduces a novel monocular vehicle distance estimation method using license plates as passive markers, leveraging geometric priors to achieve accurate, training-free, and robust measurements for ADAS and autonomous driving.

Contribution

It proposes a framework that exploits license plate typography as passive fiducial markers, eliminating the need for training data and active illumination, and integrates multiple detection and identification methods for robustness.

Findings

Achieved 2.3% variation in character height measurements on static datasets.

Reduced distance-estimate variance by 36% compared to prior plate-width methods.

Validated the approach with a hybrid depth fusion and Kalman filtering for real-time collision warning.

Abstract

Accurate inter-vehicle distance estimation is a cornerstone of Advanced Driver Assistance Systems (ADAS) and autonomous driving. While LiDAR and radar provide high precision, their high cost prohibits widespread adoption in mass-market vehicles. Monocular camera-based estimation offers a low-cost alternative but suffers from fundamental scale ambiguity. Recent deep learning methods for monocular depth achieve impressive results yet require expensive supervised training, suffer from domain shift, and produce predictions that are difficult to certify for safety-critical deployment. This paper presents a framework that exploits the standardized typography of United States license plates as passive fiducial markers for metric ranging, resolving scale ambiguity through explicit geometric priors without any training data or active illumination. First, a four-method parallel plate detector achieves robust plate reading across the full automotive lighting range. Second, a three-stage state identification engine fusing optical character recognition text matching, multi-design color scoring, and a lightweight neural network classifier provides robust identification across all ambient conditions. Third, hybrid depth fusion with inverse-variance weighting and online scale alignment, combined with a one-dimensional constant-velocity Kalman filter, delivers smoothed distance, relative velocity, and time-to-collision for collision warning. Baseline validation on a controlled static dataset reproduces a 2.3% coefficient of variation in character height measurements and a 36% reduction in distance-estimate variance compared with plate-width methods from prior work.