Research Article
A Novel Parking Lot Occupancy Detection System Based on LED Sensing
@INPROCEEDINGS{10.1007/978-3-030-66785-6_37, author={Dazhuang Sun and Jing Chen and Jie Hao}, title={A Novel Parking Lot Occupancy Detection System Based on LED Sensing}, proceedings={Machine Learning and Intelligent Communications. 5th International Conference, MLICOM 2020, Shenzhen, China, September 26-27, 2020, Proceedings}, proceedings_a={MLICOM}, year={2021}, month={1}, keywords={Visible light technology Machine learning Intelligent parking system Support Vector Machine Automatic parking space detection}, doi={10.1007/978-3-030-66785-6_37} }- Dazhuang Sun
Jing Chen
Jie Hao
Year: 2021
A Novel Parking Lot Occupancy Detection System Based on LED Sensing
MLICOM
Springer
DOI: 10.1007/978-3-030-66785-6_37
Abstract
For the great market value, intelligent parking lot detection system has been studied extensively. Generally, additional sensors such as wide-angle lens cameras, ultrasonic detectors, pressure sensors and so on are required to be deployed in the parking lots, which incur high deployment cost. Considering the lighting infrastructures are widely deployed in the underground garage and the occupancy of a parking lot changes the ambient light intensity, in this paper we novelly reuse the existing lighting infrastructure and exploit the light sensing capacity of the light emitting diode (LED) to monitor the occupancy of the parking lots. The LED illuminators can be switched between light emitting and sensing state so that during sensing state, LED illuminators can work as light sensors. In our scheme, we feed the data collected by LED illuminators in a typical machine learning method, Support Vector Machine (SVM) algorithm to achieve accurate detection accuracy. We conduct simulative experiments and demonstrate the feasibility and effectiveness of the proposed LED sensing based parking lot occupancy detection system. The detection accuracy reaches 98.70%.
