Affiliations: Escuela Técnica Superior de Ingeniería Informática, Universidad Rey Juan Carlos, Móstoles, Spain
Correspondence:
[*]
Corresponding author: Francisco J. Garcia-Espinosa, Escuela Técnica Superior de Ingeniería Informática, Universidad Rey Juan Carlos, Móstoles, Spain. E-mail: [email protected].
Note: [1] This research has been supported by the Spanish Government research funding RTI2018-098743-B-I00, PID2021-128362OB-100 (MICINN/FEDER) and TED2021-129162B-C22 (funded by the Recovery and Resilience Facility program from the NextGenerationEU Plan of the European Union and the Spanish Research Agency).
Abstract: This paper presents an Automatic Parking Space Detection (APSD) algorithm designed to reduce traffic in cities while offering an information system of available parking zones. The main aim of such a system lies in its ability to identify parking spaces in a distributed manner, achieved by installing multiple APSD systems across a fleet of vehicles. This fleet, during its regular operations, communicates the availability of parking spaces to a centralized information system. Our methodology employs a rule-based system that seamlessly integrates a variety of neural networks for different specific tasks. These tasks include depth estimation, road segmentation, and vehicle detection. This approach would fall into a modular category instead of an end-to-end solution, using the Málaga Urban Dataset in the experiments. We present a preliminary experiment for parameter settings and an ablation study to quantify each subsystem contribution to the results. The proposed system achieves a parking space detection F1 score of 0.726.
Keywords: Smart parking, parking space detection, detection networks, rule-based systems, automatic parking space detection
