Typography-Based Monocular Distance Estimation Framework for Vehicle Safety Systems

TL;DR

This paper presents a novel monocular distance estimation method using license plate typography as passive markers, combining geometric, deep learning, and filtering techniques for accurate, real-time vehicle distance measurement without expensive sensors.

Contribution

It introduces a typography-based monocular distance estimation framework leveraging license plates as fiducial markers, integrating multiple robust detection and fusion methods for improved accuracy.

Findings

Achieved 2.3% CV in character height consistency across frames.

Mean absolute distance estimation error of 7.7%.

Reduced estimate variability by 35% compared to plate-width methods.

Abstract

Accurate inter-vehicle distance estimation is a cornerstone of advanced driver assistance systems and autonomous driving. While LiDAR and radar provide high precision, their cost prohibits widespread adoption in mass-market vehicles. Monocular vision offers a low-cost alternative but suffers from scale ambiguity and sensitivity to environmental disturbances. This paper introduces a typography-based monocular distance estimation framework, which exploits the standardized typography of license plates as passive fiducial markers for metric distance estimation. The core geometric module uses robust plate detection and character segmentation to measure character height and computes distance via the pinhole camera model. The system incorporates interactive calibration, adaptive detection with strict and permissive modes, and multi-method character segmentation leveraging both adaptive and global thresholding. To enhance robustness, the framework further includes camera pose compensation using lane-based horizon estimation, hybrid deep-learning fusion, temporal Kalman filtering for velocity estimation, and multi-feature fusion that exploits additional typographic cues such as stroke width, character spacing, and plate border thickness. Experimental validation with a calibrated monocular camera in a controlled indoor setup achieved a coefficient of variation of 2.3% in character height across consecutive frames and a mean absolute error of 7.7%. The framework operates without GPU acceleration, demonstrating real-time feasibility. A comprehensive comparison with a plate-width based method shows that character-based ranging reduces the standard deviation of estimates by 35%, translating to smoother, more consistent distance readings in practice, where erratic estimates could trigger unnecessary braking or acceleration.