Driver Behavior Extraction from Videos in Naturalistic Driving Datasets with 3D ConvNets

TL;DR

This paper presents a 3D ConvNet approach to automatically detect cell-phone-related driver behaviors in naturalistic driving videos, significantly improving efficiency over manual review.

Contribution

The study introduces a novel 3D ConvNet method for automatic extraction of driver behaviors from videos in naturalistic driving datasets.

Findings

Approximately 79% of extracted video chunks contain cell-phone behaviors.

The method reduces manual review time for driver behavior analysis.

Automatic extraction improves data utilization in naturalistic driving studies.

Abstract

Naturalistic driving data (NDD) is an important source of information to understand crash causation and human factors and to further develop crash avoidance countermeasures. Videos recorded while driving are often included in such datasets. While there is often a large amount of video data in NDD, only a small portion of them can be annotated by human coders and used for research, which underuses all video data. In this paper, we explored a computer vision method to automatically extract the information we need from videos. More specifically, we developed a 3D ConvNet algorithm to automatically extract cell-phone-related behaviors from videos. The experiments show that our method can extract chunks from videos, most of which (~79%) contain the automatically labeled cell phone behaviors. In conjunction with human review of the extracted chunks, this approach can find cell-phone-related driver behaviors much more efficiently than simply viewing video.