E-Park: Automated-Ticketing Parking Meter System
Citation
Kulesza, Mateusz J. 2015. E-Park: Automated-Ticketing Parking Meter System. Bachelor's thesis, Harvard College.Abstract
E-Park is an electronic parking meter system which enables real-time ticketing of illegally parked vehicles. The system is a drop-in replacement for existing curb-side parking meters. It consists of lowpower front-end parking meter hardware and a back-end server that handles the information database management. Wireless network communication enables the parking meter to accept electronic payment, enforce parking regulation, and ticket parking violators by capturing an image of the vehicle license plate. The image is sent to the central server where the license plate number is automatically extracted from the image using an Automated License Plate Recognition (ALPR) algorithm. The meter includes a visual feedback system which tells the driver how to optimally position the vehicle relative to the parking meter. This is done in order to ensure that any images captured by the camera contain a good view of the vehicle license plate. The system relies on solar rechargeable batteries so that it may function completely untethered and without the need for human intervention.Field tests of the system proved that the visual driver feedback successfully allowed 5 different drivers to consistently position their vehicles at the correct distance relative to the meter. Testing of the OpenALPR algorithm utilized to automatically extract license plate information from the images showed that the relative angle with which the camera views the license plate can be no larger than 55°. Although this presents some limitations, the proposed parking meter architecture introduces redundancies that successfully circumvent this limitation and can ensure that the system achieves ticketing rates upwards of 90% of vehicles.
Terms of Use
This article is made available under the terms and conditions applicable to Other Posted Material, as set forth at http://nrs.harvard.edu/urn-3:HUL.InstRepos:dash.current.terms-of-use#LAACitable link to this page
http://nrs.harvard.edu/urn-3:HUL.InstRepos:17417570
Collections
- FAS Theses and Dissertations [6136]
Contact administrator regarding this item (to report mistakes or request changes)