High-Speed Rear-End Collision Risk Scenario Classification Dataset

The current transportation industry faces the challenge of frequent highway rear-end collisions, leading to severe casualties and property damage. Existing accident warning systems mostly rely on traditional sensors and data analysis methods, lacking effective recognition and classification capabilities for complex traffic scenarios. This dataset aims to enhance the capability of identifying and warning about rear-end risks through high-quality image classification. The dataset contains 5000 clearly annotated images covering different high-speed rear-end risk scenarios. Data collection was conducted using high-resolution cameras in real highway environments, ensuring data authenticity and diversity. In terms of quality control, a multi-round annotation and expert review process was used to ensure the accuracy of each image's annotation. The data is stored in JPG format and organized by folder structure, facilitating subsequent model training and testing.