Applying Deep Learning to Detect Traffic Accidents in Real Time Using Spatiotemporal Sequential Data

TL;DR

This paper applies LSTM and GRU deep learning models to real-time traffic accident detection using spatiotemporal data from Chicago, demonstrating high accuracy and slight performance advantages of GRU over LSTM.

Contribution

The study introduces the use of LSTM and GRU models for traffic accident detection with imbalanced spatiotemporal data, showing their effectiveness in real-time scenarios.

Findings

Both models achieved an AUC of 0.85.

GRU performed slightly better than LSTM.

Models maintained similar false alarm rates.

Abstract

Accident detection is a vital part of traffic safety. Many road users suffer from traffic accidents, as well as their consequences such as delay, congestion, air pollution, and so on. In this study, we utilize two advanced deep learning techniques, Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs), to detect traffic accidents in Chicago. These two techniques are selected because they are known to perform well with sequential data (i.e., time series). The full dataset consists of 241 accident and 6,038 non-accident cases selected from Chicago expressway, and it includes traffic spatiotemporal data, weather condition data, and congestion status data. Moreover, because the dataset is imbalanced (i.e., the dataset contains many more non-accident cases than accident cases), Synthetic Minority Over-sampling Technique (SMOTE) is employed. Overall, the two models perform significantly well, both with an Area Under Curve (AUC) of 0.85. Nonetheless, the GRU model is observed to perform slightly better than LSTM model with respect to detection rate. The performance of both models is similar in terms of false alarm rate.