CycleCrash: A Dataset of Bicycle Collision Videos for Collision Prediction and Analysis

Published: 03 Mar 2025, Last Modified: 05 Mar 2025WACV 2025EveryoneCC BY 4.0
Abstract: Self-driving research often underrepresents cyclist colli- sions and safety. To address this, we present CycleCrash, a novel dataset consisting of 3,000 dashcam videos with 436,347 frames that capture cyclists in a range of critical situations, from collisions to safe interactions. This dataset enables 9 different cyclist collision prediction and classifi- cation tasks focusing on potentially hazardous conditions for cyclists and is annotated with collision-related, cyclist- related, and scene-related labels. Next, we propose Vid- NeXt, a novel method that leverages a ConvNeXt spatial encoder and a non-stationary transformer to capture the temporal dynamics of videos for the tasks defined in our dataset. To demonstrate the effectiveness of our method and create additional baselines on CycleCrash, we apply and compare 7 models along with a detailed ablation. We re- lease the dataset and code at https://github.com/ DeSinister/CycleCrash/.
Loading