A novel traffic accident detection method with comprehensive traffic flow features extraction

Abstract

With the rapidly increasing of automobiles, traffic accidents are gradually becoming more frequent. This creates a great need for effective traffic anomaly detection algorithms. Existing methods shed light on directly inferring the abnormalities from traffic flow, which is short in features extraction and representation of traffic flows. In this paper, we propose three new traffic flow features, namely the road congestion, the traffic intensity, and the traffic state instability, for more comprehensive traffic status representation and anomaly detection. Residual analysis, quadratic discrimination, multi-resolution wavelet analysis are integrated for the extraction of the aforementioned features, which will be applied for the downstream tasks of traffic anomaly detection. Experimental results reveal that accident identification based on the proposed features is more effective than the raw traffic flow, which is supposed to provide an alternative approach for further applications and studies.

An AutoML-based approach for automatic traffic incident detection in smart cities

“…Regarding the two baseline approaches, Isolation Forests are generally used in an unsupervised manner and only require a few conditions to separate anomalies from normal observations when compared to other methods which use basic distance and density measures. There are several works in the field of AID which use Isolation Forests, including [37]. Their low linear time complexity and small memory requirements aid in eliminating major computational cost of distance calculation in all distance and density-based methods and can perform well in a multi-dimensional feature space.…”