Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing

TL;DR

This paper presents a dual-modality vehicle anomaly detection framework that effectively handles complex traffic scenes with variable lighting, using background modeling, YOLOv5 detection, and bilateral trajectory tracing, achieving high accuracy in challenging conditions.

Contribution

The paper introduces a novel dual-modality bilateral tracing method combined with multi-module vehicle detection for robust anomaly detection in complex traffic environments.

Findings

Achieved 0.9302 F1-Score on NVIDIA AI City Challenge dataset.

Demonstrated robustness under diverse lighting and scene conditions.

Reduced anomaly detection error with bilateral trajectory refinement.

Abstract

Traffic anomaly detection has played a crucial role in Intelligent Transportation System (ITS). The main challenges of this task lie in the highly diversified anomaly scenes and variational lighting conditions. Although much work has managed to identify the anomaly in homogenous weather and scene, few resolved to cope with complex ones. In this paper, we proposed a dual-modality modularized methodology for the robust detection of abnormal vehicles. We introduced an integrated anomaly detection framework comprising the following modules: background modeling, vehicle tracking with detection, mask construction, Region of Interest (ROI) backtracking, and dual-modality tracing. Concretely, we employed background modeling to filter the motion information and left the static information for later vehicle detection. For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies. Besides, we utilized the frame difference and tracking results to identify the road and obtain the mask. In addition, we introduced multiple similarity estimation metrics to refine the anomaly period via backtracking. Finally, we proposed a dual-modality bilateral tracing module to refine the time further. The experiments conducted on the Track 4 testset of the NVIDIA 2021 AI City Challenge yielded a result of 0.9302 F1-Score and 3.4039 root mean square error (RMSE), indicating the effectiveness of our framework.