Traffic sign detection and recognition using event camera image reconstruction
This addresses traffic sign recognition for autonomous driving systems, but it is incremental as it applies existing methods to event camera data.
The paper tackled traffic sign detection and recognition using event camera data by reconstructing events into greyscale frames with a FireNet CNN and training YOLOv4 models, achieving an efficiency of 87.03% with the greyscale model.
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%.