Traffic sign detection and recognition using event camera image reconstruction

TL;DR

This paper introduces a traffic sign detection and recognition method utilizing event camera data, employing deep learning models for image reconstruction and object detection, achieving high accuracy with greyscale images.

Contribution

It presents a novel approach combining event camera data with deep neural networks for traffic sign detection and recognition.

Findings

Greyscale image-based model achieved 87.03% efficiency.

Event camera data can be effectively reconstructed for traffic sign recognition.

Deep learning models outperform traditional methods in this context.

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%.