Automatic recognition of dangerous objects in front of the vehicle’s windshield
[ 1 ] Instytut Automatyki i Robotyki, Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ 2 ] Wydział Automatyki, Robotyki i Elektrotechniki, Politechnika Poznańska | [ P ] pracownik | [ S ] student
[2.2] Automatyka, elektronika, elektrotechnika i technologie kosmiczne
2024
rozdział w monografii naukowej / referat
angielski
- threat object recognition
- vision system
- artificial neural networks
- video recorders
- image recognition
- image processing
EN In this article, an automatic recognition system, of objects that threaten the safety of vehicle users is proposed. These objects are detected in front of the vehicle's windshield based on images from video recorders and then classified. The tests were conducted using artificial neural networks on a specially prepared database of frames from real recordings. Recognized objects include: car wheels, car parts, birds, stones and ice. They were recognized in single- and multi-class detections for various parameters of the network model. Detection efficiency of 95% was achieved in the best case.
91 - 96
20