# Lane-Wise Highway Anomaly Detection

arXiv: https://arxiv.org/abs/2505.02613 · HTML: https://mlsanity.com/paper/2505.02613/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 5 May 2025.

## Builds on (most cited first, 8 of 8)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Simple Online and Realtime Tracking with a Deep Association Metric](https://mlsanity.com/paper/1703.07402/) (2017)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling](https://mlsanity.com/paper/2311.12550/) (2023)
- [FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection](https://mlsanity.com/paper/2406.15283/) (2024)
- [An Iterative Method for Unsupervised Robust Anomaly Detection Under Data Contamination](https://mlsanity.com/paper/2309.09436/) (2023)
- [Real-time Lane-wise Traffic Monitoring in Optimal ROIs](https://mlsanity.com/paper/2404.15212/) (2024)
- [Enhancing Traffic Flow Prediction using Outlier-Weighted AutoEncoders: Handling Real-Time Changes](https://mlsanity.com/paper/2312.16596/) (2023)

## Abstract (arXiv)

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.