Good Practices and A Strong Baseline for Traffic Anomaly Detection

TL;DR

This paper introduces a simple yet effective traffic anomaly detection framework that combines pre-processing, dynamic tracking, and post-processing, achieving top performance in the NVIDIA AI CITY 2021 competition.

Contribution

It presents a novel, handcrafted approach for traffic anomaly detection that outperforms existing methods and provides a strong baseline for future research.

Findings

Ranked 1st in NVIDIA AI CITY 2021 leaderboard

Effective combination of pre-processing, tracking, and post-processing

Open-source code available for reproducibility

Abstract

The detection of traffic anomalies is a critical component of the intelligent city transportation management system. Previous works have proposed a variety of notable insights and taken a step forward in this field, however, dealing with the complex traffic environment remains a challenge. Moreover, the lack of high-quality data and the complexity of the traffic scene, motivate us to study this problem from a hand-crafted perspective. In this paper, we propose a straightforward and efficient framework that includes pre-processing, a dynamic track module, and post-processing. With video stabilization, background modeling, and vehicle detection, the pro-processing phase aims to generate candidate anomalies. The dynamic tracking module seeks and locates the start time of anomalies by utilizing vehicle motion patterns and spatiotemporal status. Finally, we use post-processing to fine-tune the temporal boundary of anomalies. Not surprisingly, our proposed framework was ranked $1^{st}$ in the NVIDIA AI CITY 2021 leaderboard for traffic anomaly detection. The code is available at: https://github.com/Endeavour10020/AICity2021-Anomaly-Detection .