Vehicular Social Dynamic Anomaly Detection With Recurrent Multi-Mask Aggregator Enabled VAE

Vehicle driving behavior analysis and detection tasks have become an indispensable part of intelligent transportation systems. Accurate pattern recognition of potential anomalies during the movement of entities is crucial for improving transportation efficiency. Current methods typically analyze vehicle trajectories independently without considering potential interactions among vehicles. To address this limitation, some studies have integrated graph attention mechanisms to capture the influence of neighboring vehicles during the aggregation process. However, Graph Attention Networks (GATs) are constrained by the univariate nature of attention heads and coefficients, thus lacking flexibility. In this work, we not only consider the social dynamics among neighboring vehicles but also delve into the limitations of GAT models. We propose a Vehicular Social Dynamics Anomaly Detection (VSD-AD) model based on the Recurrent Multi-Mask Aggregator (MMA) enabled Variational AutoEncoder (VAE) architecture to maximize the learning of relational embeddings among neighbors in a highway vehicle network. Furthermore, we apply Node Feature Quantisation (NFQ) to the encoder output to mitigate the complexity of neighbor relationships. Our model is flexible and customizable for different highway scenarios, suitable for large-scale highway vehicle video data. To validate real-world applicability, we further assess its performance on both the simulated dataset and real-world traffic dataset, where our model outperforms other mainstream methods in terms of detection performance.

I. Introduction

Highly autonomous smart traffic management system, as a key component of smart cities, plays a crucial role in addressing urban challenges like traffic flow prediction and accident prevention. With the expansion of urban areas and populations [1], [2] [3], issues such as traffic congestion and accidents have become more prominent, impacting people’s time and safety [4], [5] [6]. Leveraging IoT technologies, such as sensor networks with Road-Side Units (RSUs) and On-Board Units (OBUs), researchers aim to extract valuable insights from data to enhance traffic management systems. Detecting traffic anomalies in a timely manner is essential for efficient traffic management [7], [8] [9], [10], considering the impact of drivers’ decisions on traffic dynamics. The challenge for human operators lies in processing vast amounts of data and the lack of a standardized approach to anomaly detection.