Traffic noise exposure, air pollution, road injuries, and traffic delays are some of the major problems with which residents are faced with on a daily basis in urban areas. Urban cities are facing serious environmental and quality-of-life problems due to a significant growth of vehicles, inadequate transport infrastructure, and lack of road-safety policies. For example, in many urban cities there is violation from heavy trucks to the normal roadways which leads to traffic congestion and delays. In addition, many cyclists experience frequent near misses due to the fact that cyclist’s clothing, posture changing, partial occlusions, and different observation angles all play a very challenging role in the recognition rates of the Machine Learning (ML) algorithms.
Over the last ten years, there has been an increasing interest in using machine learning and deep learning methods to analyze and visualize massive data generated from various sources in order to improve the classification and recognition of pedestrians, bicycles, special vehicles detection (e.g., emergency vehicles vs heavy trucks), and License Plate Recognition (LPR) for a safer and sustainable environment. Although deep models can capture a large variation of appearances, environment adaptation is required.
This Special Issue is designed to serve researchers and developers to publish original, innovative, and state-of-the-art machine learning methods, algorithms and architectures to analyze the modern vision of an intelligent transportation infrastructure system. Innovative solutions in the form of efficient visual object learning algorithms, prediction models and environmental sensors, which will take into account several important factors (e.g., quality of life, environment and traffic capabilities, etc.) are needed for sustainable Intelligent Transportation Systems. We are particularly interested in candidates who have conducted research in: a) ML based detection/classification: We are interested in systems, algorithms, methodologies that monitor road behavior (e.g., time-road usage violation, speed limit, special lanes overtaken, etc.) and filter different types of heavy trucks (e.g., emergency vehicles are permitted to break road rules), b) Environmental sensors and controllers: We are interested in traffic management models that gather data information from the streets via different sensors, such as cameras, microphones for noise assessments, low-cost sensors to measure air pollution, and provide recommendations to bypass city areas with abnormal noise and air pollution but with a sense of traveling times.
Dr. Peter M. Roth
Prof. Dr. Jose Garcia Rodriguez
Dr. Jude Hemanth
Dr. Anastassia Angelopoulou
Dr. Epameinondas Kapetanios