ParkUs: A Novel Vehicle Parking Detection System

Finding on-street parking in congested urban areas is a challenging chore that most drivers worldwide dislike. Previousvehicle traffic studies have estimated that around thirty percent of vehicles travelling in inner city areas are made up ofdrivers searching for a vacant parking space. While there arehardware sensor based solutions to monitor on-street parking occupancy in real-time, instrumenting and maintainingsuch a city wide system is a substantial investment. In this paper, a novel vehicle parking activity detection method, calledParkUs, is introduced and tested with the aim to eventuallyreduce vacant car parking space search times. The systemutilises accelerometer and magnetometer sensors found in allsmartphones in order to detect parking activity within a cityenvironment. Moreover, it uses a novel sensor fusion featurecalled the Orthogonality Error Estimate (OEE). We show thatthe OEE is an excellent indicator as it’s capable of detecting parking activities with high accuracy and low energy consumption. One of the envisioned applications of the ParkUssystem will be to provide all drivers with guidelines on wherethey are most likely to find vacant parking spaces within acity. Therefore, reducing the time required to find a vacantparking space and subsequently vehicle congestion and emissions within the city.