Optoelectronic and Environmental Factors Affecting the Accuracy of Crowd-Sourced Vehicle-Mounted License Plate Recognition

Abstract

License plate recognition (LPR) technology has been used to combat vehicle-related crime in urban areas in many developed contexts. However, commercially available LPR systems are expensive and not feasible for large scale adoption in developing countries. The development of a low-cost crowdsourced solution requires an informed approach to the selection of an appropriate camera, as well as a realistic understanding of the system's performance under various environmental conditions. This work investigates the effect of optoelectronic and environmental factors on the ability of a vehicle-mounted LPR system to correctly identify license plates, specifically for a mass-deployment crowd-sourced scenario. A theoretical LPR camera model was developed to estimate the effect of different cameras, while the effects of motion, orientation and lighting were evaluated in a series of experimental tests. The most influential optoelectronic factors were shown to be focus, focal length and image sensor resolution. Furthermore, recognition was impaired during high-speed turn maneuvers, angling of license plates away from the camera and certain night-time conditions. The optoelectronic model proved useful for the selection of a cost-effective camera for use in an open-source LPR system. Moreover, the study of environmental factors provided valuable insight into the limitations of LPR systems in various environmental and traffic conditions.

License Plate Recognition System Based on Improved YOLOv5 and GRU

“…This condition includes good weather conditions, adequate lighting, fixed scenes, and facilities. License plate recognition in complex environments remains difficult, with challenges such as poor lighting at night, rain and snow, dumped, obscured or blurred license plates [42]. In traditional license plate recognition, the two modules, location and recognition, are usually divided into two separate tasks, and use more complex algorithms to solve these challenges.…”

Transport Inequalities and the Adoption of Intelligent Transportation Systems in Africa: A Research Landscape

“…In [65], a dynamic broadcast storm mitigation algorithm was proposed as an alternative to cooperative awareness messages to enhance inter-vehicular communication in Vehicle Ad Hoc Networks, especially during traffic congestion. From a security perspective, [66] proposed a model for license plate recognition using images from open/crowd-sourced cameras. In order to enhance the images from these cameras, the authors proposed a model that considered factors relating to the environment such as ambient lightning conditions and those relating to the cameras (lens, aperture size, image sensor and angles and motion blur effects).…”

“…Regarding security, most authors relied on the use of cameras. These cameras might either be connected to a Raspberry Pi to capture license plate numbers [66] or connected to a fog computing infrastructure for traffic management and vehicle tracking [44].…”

A Robust License Plate Detection System Using Smart Device

“…It is a straightforward approach and can save time. Commercially accessible License Plate Recognition (LPR) systems are costly, heavily dependent on proprietary technology, and typically provided as part of comprehensive system packages [1]. Because of new advancements in smartphone technology, many smartphones come with powerful processors and cameras.…”