DeepFlow: Abnormal Traffic Flow Detection Using Siamese Networks

TL;DR

DeepFlow is a novel traffic anomaly detection system using Siamese neural networks that effectively identifies abnormal traffic patterns with limited training data, outperforming existing methods in simulation tests.

Contribution

This paper introduces DeepFlow, a Siamese network-based approach for traffic anomaly detection that works well with small datasets, addressing limitations of prior data-intensive methods.

Findings

DeepFlow achieves an F1 score of 78% in detecting traffic anomalies.

DeepFlow outperforms DTW, GAK, and iForest in simulation evaluations.

The method is suitable for scenarios with limited training data.

Abstract

Nowadays, many cities are equipped with surveillance systems and traffic control centers to monitor vehicular traffic for road safety and efficiency. The monitoring process is mostly done manually which is inefficient and expensive. In recent years, several data-driven solutions have been proposed in the literature to automatically analyze traffic flow data using machine learning techniques. However, existing solutions require large and comprehensive datasets for training which are not readily available, thus limiting their application. In this paper, we develop a traffic anomaly detection system, referred to as DeepFlow, based on Siamese neural networks, which are suitable in scenarios where only small datasets are available for training. Our model can detect abnormal traffic flows by analyzing the trajectory data collected from the vehicles in a fleet. To evaluate DeepFlow, we use realistic vehicular traffic simulations in SUMO. Our results show that DeepFlow detects abnormal traffic patterns with an F1 score of 78%, while outperforming other existing approaches including: Dynamic Time Warping (DTW), Global Alignment Kernels (GAK), and iForest.