CrashFormer: A Multimodal Architecture to Predict the Risk of Crash
Open Access
- 13 November 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 42-51
Abstract
Reducing traffic accidents is a crucial global public safety concern. Accident prediction is key to improving traffic safety, enabling proactive measures to be taken before a crash occurs, and informing safety policies, regulations, and targeted interventions. Despite numerous studies on accident prediction over the past decades, many have limitations in terms of generalizability, reproducibility, or feasibility for practical use due to input data or problem formulation. To address existing shortcomings, we propose Crash-Former, a multi-modal architecture that utilizes comprehensive (but relatively easy to obtain) inputs such as the history of accidents, weather information, map images, and demographic information. The model predicts the future risk of accidents on a reasonably acceptable cadence (i.e., every six hours) for a geographical location of 5.161 square kilometers. CrashFormer is composed of five components: a sequential encoder to utilize historical accidents and weather data, an image encoder to use map imagery data, a raw data encoder to utilize demographic information, a feature fusion module for aggregating the encoded features, and a classifier that accepts the aggregated data and makes predictions accordingly. Results from extensive real-world experiments in 10 major US cities show that CrashFormer outperforms state-of-the-art sequential and non-sequential models by 1.8% in F1-score on average when using "sparse" input data.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Accident Risk Prediction based on Heterogeneous Sparse Data2019
- A feature learning approach based on XGBoost for driving assessment and risk predictionAccident Analysis & Prevention, 2019
- Short and Long-term Pattern Discovery Over Large-Scale Geo-Spatiotemporal Data2019
- A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source dataAccident Analysis & Prevention, 2019
- A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction2018
- Advancing usage‐based insurance – a contextual driving risk modelling and analysis approachIET Intelligent Transport Systems, 2018
- Hetero-ConvLSTM2018
- Precipitation Effects on Motor Vehicle Crashes Vary by Space, Time, and Environmental ConditionsWeather, Climate, and Society, 2016
- A novel variable selection method based on frequent pattern tree for real-time traffic accident risk predictionTransportation Research Part C: Emerging Technologies, 2015
- Geodesic Discrete Global Grid SystemsCartography and Geographic Information Science, 2003