Supervised Contrastive Learning for Detecting Anomalous Driving Behaviours from Multimodal Videos

TL;DR

This paper introduces a supervised contrastive learning method with a modified loss and the inclusion of a projection head for video-based anomalous driving behavior detection, achieving significant improvements over baselines.

Contribution

It proposes a novel supervised contrastive learning framework with a modified loss and the use of a projection head, tailored for detecting anomalous driving behaviors from multimodal videos.

Findings

Improved ROC AUC on 6 out of 9 modalities compared to baseline models.

Fusion of depth and infrared modalities achieved ROC AUC of 0.9738.

Statistical tests confirmed the superiority of the proposed method.

Abstract

Distracted driving is one of the major reasons for vehicle accidents. Therefore, detecting distracted driving behaviors is of paramount importance to reduce the millions of deaths and injuries occurring worldwide. Distracted or anomalous driving behaviors are deviations from 'normal' driving that need to be identified correctly to alert the driver. However, these driving behaviors do not comprise one specific type of driving style and their distribution can be different during the training and test phases of a classifier. We formulate this problem as a supervised contrastive learning approach to learn a visual representation to detect normal, and seen and unseen anomalous driving behaviors. We made a change to the standard contrastive loss function to adjust the similarity of negative pairs to aid the optimization. Normally, in a (self) supervised contrastive framework, the projection head layers are omitted during the test phase as the encoding layers are considered to contain general visual representative information. However, we assert that for a video-based supervised contrastive learning task, including a projection head can be beneficial. We showed our results on a driver anomaly detection dataset that contains 783 minutes of video recordings of normal and anomalous driving behaviors of 31 drivers from the various top and front cameras (both depth and infrared). Out of 9 video modalities combinations, our proposed contrastive approach improved the ROC AUC on 6 in comparison to the baseline models (from 4.23% to 8.91% for different modalities). We performed statistical tests that showed evidence that our proposed method performs better than the baseline contrastive learning setup. Finally, the results showed that the fusion of depth and infrared modalities from the top and front views achieved the best AUC ROC of 0.9738 and AUC PR of 0.9772.