Published in Scientific Papers. Series E. Land Reclamation, Earth Observation & Surveying, Environmental Engineering, Vol. XIII
Written by Mihaita Nicolae ARDELEANU, Emil Mihail DIACONU, Otilia NEDELCU, Marius-Alexandru DINCA, Petru NICOLAE, Sorin IONITESCU
The development of deep learning technologies and digital image processing have brought innovative solutions for various fields of activity. One area that has benefited from these technological innovations is urban traffic analysis. Architectures based on convolutional neural networks are used in a wide variety of intelligent systems that rely on image detection and analysis. This micro-review aims to provide a comprehensive overview of strategies for reducing pollution in traffic congestions through carbon footprint-based methods. The emphasis is on methodologies that quantify and mitigate the environmental impact of traffic congestion, combining advances in technology with authority measures. Examining current methodologies, new trends and case studies, this study seeks to highlight modern and effective strategies that can be implemented to provide practical solutions for more efficient and sustainable urban transport and pollution reduction.
[Read full article] [Citation]
