Traffic sign detection and recognition using event camera image reconstruction

Abstract

This paper presents a method for detection and recognition of traffic signs based on information extracted from an event camera. The solution used a FireNet deep convolutional neural network to reconstruct events into greyscale frames. Two YOLOv4 network models were trained, one based on greyscale images and the other on colour images. The best result was achieved for the model trained on the basis of greyscale images, achieving an efficiency of 87.03%.

arXiv commentPaper accepted for publication in: Zeszyty Studenckiego Towarzystwa Naukowego, 59. Hutnicza Konferencja Studenckich Kol Naukowych AGH,ISSN 1732-0925, 2022 nr 38, pp. 127-134. (original manuscript in Polish)