Detection of Crosswalks and Pedestrian Signals Using Machine Learning for Walking Assistance of Visually Impaired Persons

抄録

We propose a YOLO11-based segmentation model for detecting crosswalks and pedestrian signals. In addition, it is confirmed that the nighttime detection accuracy is improved by adding a sufficient number of nighttime images to the training dataset. The model performance is evaluated using daytime and nighttime test images by calculating precision, recall, and AP50.