Identification of safety-critical events using kinematic vehicle data and the discrete fourier transform

• Using high-resolution vehicle trajectories, unsafe driving behaviors was identified.
• A Discrete-Fourier Transform was used to find crashes and near-crashes in NDS data.
• K-Means Clusters correctly identified 78% of the events in this study.
• Applicable for a variety of purposes in both the private and public sector.

Recent technological advances have made it both feasible and practical to identify unsafe driving behaviors using second-by-second trajectory data. Presented in this paper is a unique approach to detecting safety-critical events using vehicles’ longitudinal accelerations. A Discrete Fourier Transform is used in combination with K-means clustering to flag patterns in the vehicles’ accelerations in time-series that are likely to be crashes or near-crashes. The algorithm was able to detect roughly 78% of crasjavascript:void(0)hes and near-crashes (71 out of 91 validated events in the Naturalistic Driving Study data used), while generating about 1 false positive every 2.7 h. In addition to presenting the promising results, an implementation strategy is discussed and further research topics that can improve this method are suggested in the paper.

Figure optionsDownload as PowerPoint slide