MWAIS 2024 Proceedings
Abstract
This study presents a computer vision approach aimed at detecting snow on sidewalks and pavements to reduce winter-related fall injuries, especially among elderly and visually impaired individuals. Leveraging fine-tuned VGG-19 and ResNet-50 convolutional neural networks (CNNs), the research focuses on identifying snow presence in pavement images. The dataset comprises 98 images evenly split between snowy and snow-free conditions, evaluated with a separate test set using the F1 score and accuracy metrics. This work builds upon existing research by employing fine-tuned CNN architectures to accurately detect snow on pavements from smartphone-captured images. The methodology incorporates transfer learning and model ensembling techniques to integrate the best predictions from both the VGG-19 and ResNet-50 architectures. The study yields accuracy and F1 scores of 81.8% and 0.817, respectively, showcasing the potential of computer vision in addressing winter-related hazards for vulnerable populations.
Recommended Citation
de Deijn, Ricardo and Bukralia, Rajeev, "Image Classification for Snow Detection to Improve Pedestrian Safety" (2024). MWAIS 2024 Proceedings. 15.
https://aisel.aisnet.org/mwais2024/15