Please use this identifier to cite or link to this item: http://hdl.handle.net/10773/30863
Title: Optical camera communications with convolutional neural network for vehicle-tovehicle links
Author: Soares, Miguel Roque
Chaudhary, Neha
Eso, Elisabeth
Younus, Othman Isam
Nero Alves, Luís
Ghassemlooy, Zabih
Keywords: VLC
OCC
CNN
ITS
Visible light
Camera
Car
Driver
Image Processing
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers Inc.
Abstract: This paper describes a vehicle-to-vehicle (V2V) communication system, employing optical camera communications (OCC). The system comprises the light emitting diode (LED)-based taillights and a raspberry camera used as the transmitter (Tx) and the receiver (Rx), respectively. The sectorized taillights (i.e., Tx) are intensity modulated at different frequencies, and a convolutional neural network (CNN) at the Rx is used for scene analysis, the region of interest (RoI) selection, and symbol detection. Results show that, the system data rates are constrained by the camera frame rate and symbol duration. The link performance is dependent on the CNN training set and we show that, the use of CNN allows a robust implementation, able to provide response under multiple situations: taillight obstruction, variable link distances, and misaligned Tx-Rx. Furthermore, CNN enables multiple input multiple output (MIMO) signal detection without the need for dedicated training.
Peer review: yes
URI: http://hdl.handle.net/10773/30863
DOI: 10.1109/CSNDSP49049.2020.9249499
ISBN: 978-1-7281-6051-1
Appears in Collections:DETI - Capítulo de livro
IT - Capítulo de livro

Files in This Item:
File Description SizeFormat 
09249499.pdf1.54 MBAdobe PDFrestrictedAccess


FacebookTwitterLinkedIn
Formato BibTex MendeleyEndnote Degois 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.