Deep Learning Technique for Improving Data Reception in Optical Camera Communication-Based V2I
Dong Nyeok Choi, Sung Yooun Jin, Ju-Hee Lee, Byung Wook Kim · 2019
Recently, as the existing lighting infrastructures are replaced by LED lighting, optical camera communication (OCC) technology in vehicle-infrastructure communication (V2I) systems have been actively researched. In this paper, we introduce a method to improve data packet reception rate of OCC-based V2I by using deep learning based region-of-interest (ROI) detector. In the V2I environment, traffic lights on the roadside are ROIs that perform as transmitters sending OCC data, and should be detected at the receiving camera. If ROI detectors utilize a deep learning model, data can be extracted stably during actual driving. From the experiment result, it was found that data packet reception rate using deep-learning based ROI detection technique outperforms that of conventional method based on image differentiation.