Smart Tramway Systems for Smart Cities: A Deep Learning Application in ADAS Systems

Abstract Artificial intelligence and deep learning-based techniques undoubtedly are the future of Advanced Driver-Assistance Systems (ADAS) technologies. In this article is presented a technique for detecting, recognizing tracking pedestrians, vehicles cyclists along tramway infrastructure in complex urban environment by Computer Vision, Deep Learning approaches YOLOv3 algorithm. Experiments have been conducted Line 2 “Borgonuovo –Notarbartolo” (Palermo, Italy) correspondence segments crossing roundabout having an external diameter 24 m. A survey vehicle equipped with video camera was used study. The results research show that proposed method able to search detect position speed road users near over rails front tram very precise way as demonstrate estimated values Accuracy, Loss Precision obtained during neural networks training process. implementation advanced detection ADAS systems may increase safety novel autonomous trams rapid (ARTs).