DriftNet: Aggressive Driving Behavior Classification using 3D EfficientNet Architecture

TL;DR

This paper introduces DriftNet, a novel 3D EfficientNet-based neural network for detecting aggressive driving behaviors like car drifting in videos, supported by a new dataset from Saudi Arabia, marking the first deep learning approach for this problem.

Contribution

Development of a 3D EfficientNet-based neural network architecture for aggressive driving detection and creation of a new dataset for this purpose.

Findings

Effective detection of aggressive driving behavior in videos.

Comparison shows the proposed 3D EfficientNet outperforms existing feature extractors.

First application of deep learning to aggressive driving anomaly detection.

Abstract

Aggressive driving (i.e., car drifting) is a dangerous behavior that puts human safety and life into a significant risk. This behavior is considered as an anomaly concerning the regular traffic in public transportation roads. Recent techniques in deep learning proposed new approaches for anomaly detection in different contexts such as pedestrian monitoring, street fighting, and threat detection. In this paper, we propose a new anomaly detection framework applied to the detection of aggressive driving behavior. Our contribution consists in the development of a 3D neural network architecture, based on the state-of-the-art EfficientNet 2D image classifier, for the aggressive driving detection in videos. We propose an EfficientNet3D CNN feature extractor for video analysis, and we compare it with existing feature extractors. We also created a dataset of car drifting in Saudi Arabian context https://www.youtube.com/watch?v=vLzgye1-d1k . To the best of our knowledge, this is the first work that addresses the problem of aggressive driving behavior using deep learning.