Vision system for automatic recognition of selected road users
Julian Balcerek, Adam Konieczka, Paweł Pawłowski, Wojciech Rusinek, Wojciech Trojanowski · 2022
In this article, a system for automatic recognition of selected road users using artificial neural networks is proposed. Five models of neural networks were tested with various configurations. With the special prepared image database, training, validation and tests were conducted to identify five classes of road users: cyclists, people on electric scooters, roller skates, pedestrians and people using personal transport devices. A web application that recognize these classes of road users was also prepared.