Open AccessComputer-vision–based intelligent adaptive transmission for optical wireless communication
Author(s) -
Zhitong Huang,
Lijia Zu,
Zhiping Zhou,
Xizi Tang,
Yuefeng Ji
Publication year - 2019
Publication title -
optics express
Language(s) - Uncategorized
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.27.007979
Subject(s) - optical wireless , computer science , channel (broadcasting) , free space optical communication , transmission (telecommunications) , wireless , image quality , optical wireless communications , computer vision , underwater , artificial intelligence , optical communication , optics , electronic engineering , telecommunications , engineering , image (mathematics) , physics , oceanography , geology
Optical wireless communication (OWC) has been presented as a promising candidate for future space-air-ground-ocean-integrated communication. However, the OWC is quite sensitive to the variation of the channel transmission characteristics. The light beam absorption and the scattering in the transmission media affect not only the channel feature, but also the imaging quality. Thus, there is an inherent relationship between the OWC performance and the optical imaging quality. Based on this consideration, we firstly present the idea of introducing computer vision mechanisms into the OWC systems, and then propose a computer vision-based multi-domain cooperative adjustment (CV-MDCA) mechanism's functional modules to realize the intelligent adaptive transmission in OWC systems. The CV-MDCA mechanism are specifically designed, with the emphasis on how to quantitatively determine the exact on-line channel quality from the captured images by using effective computer vision schemes. Two groups of experiments, the indoor-simulated underwater visible light communication and the outdoor-practical atmospheric free-space optics, are implemented in order to evaluate the presented CV-MDCA mechanism's performance. The results not only validate the feasibility to determine the channel quality, according to the captured channel images, but also reveal the presented three computer vision-based criteria's limitations.