Driver Anomaly Detection: A Dataset and Contrastive Learning Approach

TL;DR

This paper introduces a new dataset and a contrastive learning method for detecting driver anomalies, effectively distinguishing normal from anomalous driving actions, including unseen anomalies, to reduce accidents.

Contribution

It presents the first video-based driver anomaly detection dataset and a contrastive learning approach for open set anomaly recognition in driving scenarios.

Findings

Achieved 0.9673 AUC on the test set

Demonstrated effectiveness of contrastive learning for anomaly detection

Provided publicly available dataset, code, and models

Abstract

Distracted drivers are more likely to fail to anticipate hazards, which result in car accidents. Therefore, detecting anomalies in drivers' actions (i.e., any action deviating from normal driving) contains the utmost importance to reduce driver-related accidents. However, there are unbounded many anomalous actions that a driver can do while driving, which leads to an 'open set recognition' problem. Accordingly, instead of recognizing a set of anomalous actions that are commonly defined by previous dataset providers, in this work, we propose a contrastive learning approach to learn a metric to differentiate normal driving from anomalous driving. For this task, we introduce a new video-based benchmark, the Driver Anomaly Detection (DAD) dataset, which contains normal driving videos together with a set of anomalous actions in its training set. In the test set of the DAD dataset, there are unseen anomalous actions that still need to be winnowed out from normal driving. Our method reaches 0.9673 AUC on the test set, demonstrating the effectiveness of the contrastive learning approach on the anomaly detection task. Our dataset, codes and pre-trained models are publicly available.