Deep Representation of Imbalanced Spatio-temporal Traffic Flow Data for Traffic Accident Detection

TL;DR

This paper presents a deep learning approach using LSTM networks to detect freeway accidents from imbalanced spatio-temporal traffic data, significantly reducing detection time and improving accuracy.

Contribution

It introduces a novel deep representation framework with LSTM that enhances accident detection in imbalanced traffic datasets, outperforming existing methods.

Findings

Accidents can be detected in less than 18 minutes.

The method achieves a true positive rate of 0.71.

False positive rate is reduced to 0.25.

Abstract

Automatic detection of traffic accidents has a crucial effect on improving transportation, public safety, and path planning. Many lives can be saved by the consequent decrease in the time between when the accidents occur and when rescue teams are dispatched, and much travelling time can be saved by notifying drivers to select alternative routes. This problem is challenging mainly because of the rareness of accidents and spatial heterogeneity of the environment. This paper studies deep representation of loop detector data using Long-Short Term Memory (LSTM) network for automatic detection of freeway accidents. The LSTM-based framework increases class separability in the encoded feature space while reducing the dimension of data. Our experiments on real accident and loop detector data collected from the Twin Cities Metro freeways of Minnesota demonstrate that deep representation of traffic flow data using LSTM network has the potential to detect freeway accidents in less than 18 minutes with a true positive rate of 0.71 and a false positive rate of 0.25 which outperforms other competing methods in the same arrangement.