Lane-Wise Highway Anomaly Detection

TL;DR

This paper introduces a scalable, AI-driven lane-wise highway anomaly detection framework using multi-modal video data, outperforming existing methods in accuracy and cost-effectiveness for real-world traffic monitoring.

Contribution

It presents a novel, interpretable multi-branch system leveraging vision models and a new annotated dataset for lane-specific traffic anomaly detection.

Findings

Outperforms state-of-the-art in precision, recall, and F1-score.

Uses a new dataset with 73,139 lane-wise samples and four anomaly classes.

Achieves cost-effective, scalable traffic monitoring.

Abstract

This paper proposes a scalable and interpretable framework for lane-wise highway traffic anomaly detection, leveraging multi-modal time series data extracted from surveillance cameras. Unlike traditional sensor-dependent methods, our approach uses AI-powered vision models to extract lane-specific features, including vehicle count, occupancy, and truck percentage, without relying on costly hardware or complex road modeling. We introduce a novel dataset containing 73,139 lane-wise samples, annotated with four classes of expert-validated anomalies: three traffic-related anomalies (lane blockage and recovery, foreign object intrusion, and sustained congestion) and one sensor-related anomaly (camera angle shift). Our multi-branch detection system integrates deep learning, rule-based logic, and machine learning to improve robustness and precision. Extensive experiments demonstrate that our framework outperforms state-of-the-art methods in precision, recall, and F1-score, providing a cost-effective and scalable solution for real-world intelligent transportation systems.