Parking Stall Vacancy Indicator System Based on Deep Convolutional Neural Networks

TL;DR

This paper introduces a robust deep learning-based system for detecting parking vacancy using existing cameras, aiming to improve accuracy and practicality in urban parking management.

Contribution

The paper presents a novel deep convolutional neural network approach for parking vacancy detection, validated on large datasets and real-world camera feeds, with a complete system implementation.

Findings

High detection accuracy on large datasets

Effective real-world application demonstrated

System is practical and scalable

Abstract

Parking management systems, and vacancy-indication services in particular, can play a valuable role in reducing traffic and energy waste in large cities. Visual detection methods represent a cost-effective option, since they can take advantage of hardware usually already available in many parking lots, namely cameras. However, visual detection methods can be fragile and not easily generalizable. In this paper, we present a robust detection algorithm based on deep convolutional neural networks. We implemented and tested our algorithm on a large baseline dataset, and also on a set of image feeds from actual cameras already installed in parking lots. We have developed a fully functional system, from server-side image analysis to front-end user interface, to demonstrate the practicality of our method.