Image Classification for Snow Detection to Improve Pedestrian Safety

TL;DR

This paper develops a computer vision system using fine-tuned CNNs to detect snow on pavements from smartphone images, aiming to enhance pedestrian safety during winter conditions.

Contribution

It introduces a novel application of transfer learning and ensembling of VGG-19 and ResNet50 for snow detection on sidewalks.

Findings

Achieved 81.8% accuracy in snow detection

Demonstrated effectiveness of CNN ensembling for pavement snow identification

Showcased potential for real-time pedestrian safety improvements

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 ResNet50 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 VGG19 and ResNet50 architectures. The study yields accuracy and F1 scores of 81.8% and 81.7%, respectively, showcasing the potential of computer vision in addressing winter-related hazards for vulnerable populations.