In Transportation research interdisciplinary perspectives
Due to its remarkable learning ability and benefits in several areas of real-life, deep learning-based applications have recovered to be a topic of great research importance in the last years. This article presents a method devoted to guarantee safety conditions in public transportation systems (PTS) during COVID-19 pandemic and post-pandemic era. The paper describes a viable real-time model based on deep learning for monitoring social distance between users and detecting the face masks in stop areas and inside the vehicles of public transportation systems. Detections are made using the Deep learning approach and YOLOv3 algorithm. The safety rule violations are represented by red bounding-boxes and by red circles in the "eyes' bird view" as output of the video surveillance analyses. The Datasets used to train the neural network are the "Caltech Pedestrian Dataset" and the "COVID-19 Medical Face Mask Detection Dataset". Metrics, such as the Loss, the Accuracy and the Precision, obtained in the testing process of the neural network were used to evaluate the performance of the model in detecting the users and face masks. The proposed method was recently tested in the Public Transportation System of the Municipality of Piazza Armerina (Italy). The results show a significant reliability of the proposed method in detecting in real-time the interactions between users of the PTS in terms of variations over time of the mutual distancing and recognizing cases of violation of the imposed minimum social distance and FFP2 face masks use.
Guerrieri Marco, Parla Giuseppe
Covid-19, Deep learning, Pandemic and post-pandemic era, Social distancing, YOLOv3, face mask detection