Traffic Incident Detection: A Deep Learning Framework

Abstract

Traffic incidents cause great losses to people's lives and property, and have aroused great attention from researchers. In recent years, many machine learning methods have been utilized for traffic incident detection, e.g. Support Vector Machine (SVM) and Neural Networks (NN). However, all of them fail to consider the full spatial-temporal correlation on traffic data. In addition, the periodicity in traffic data is not well utilized. Traffic data in the same workday usually follows a similar pattern. In this paper, we introduce a deep learning framework, which captures both full spatial-temporal correlation and periodicity, to detect incidents on freeways. Experiments show that our method performs better than the state-of-the-art.