ABSTRACT
The predominant focus on individual motorized transport is neither sustainable nor socially just. One goal of a more sustainable design of the transport sector is to encourage people to use public transport. One barrier for passengers to use public transport are heavily occupied vehicles and the uncertainty about whether an empty seat is available on the desired connection. In this paper, a model is presented that is able to forecast the occupancy of vehicles in public transport. This information can be provided to passengers to increase customer satisfaction. Different sub models are presented, which differ according to their forecast horizon and the data sources used. The most important data source is data from automatic passenger counting systems collected in vehicles in the region of Northern Hesse during the project period of the research project U-hoch-3. After linking further data sources such as weather and timetable data, stratification characteristics are developed based on which occupancy states can be derived for future journeys. By linking the data with real-time data, the forecast quality can be significantly improved. It is shown which influences the Covid-19 pandemic and the introduction of the 9 € ticket in Germany had on the model development and by which functions these changes in demand can be correctly represented by the model. The results presented in this paper show that it is possible to reliably predict occupancy rates for vehicles in public transport. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Intelligent Transport System should be renovated in many aspects in post-pandemic situation like COVID-19. The passenger-count inside a car will be restricted based on the vehicle capacity and the COVID-19 hot-spot zone. Traffic rules will be impacted to align with a similar contagious outbreak. The on-road 'Yellow-Vulture' cameras need to incorporate such surveillance rules to monitor related anomalies for preventing contamination. To maintain safe-distance, an automatic surveillance system will be preferred by the Government very soon. Moreover, facial mask usage during the journey has become an essential habit to stop the spread of the infection. In this article, we have proposed a deep-Learning based framework that employs an augmented image data set to provide proper surveillance in the transport system to maintain the health protocols. Fast and accurate detection of the number of passengers inside a car and their face masks from the traffic inspection camera feed has been demonstrated. We have exploited the advantages of the popular Transfer Learning approach with novel variations of images while performing the training. To the best of our knowledge, this is the first attempt to watch over in-vehicle social-distancing in post-pandemic circumstances through deep-Learning based image analysis. The superiority of the proposed framework has been established over several state-of-the-art techniques using different numerical metrics and visual comparisons along with a support of statistical hypothesis test. Our technique has achieved 98.5 % testing accuracy in various adverse conditions. Zero-shot evaluation has been explored for the Real-Time-Medical-Mask-Detection data set Wang et al. (Real-Time-Medical-Mask-Detection, 2020a https://github.com/TheSSJ2612/Real-Time-Medical-Mask-Detection/, Accessed 14 Nov 2020), where we have attained 96.4 % accuracy that manifests the generalization of the network.