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

11/30/2020
by   Hanwen Miao, et al.
0

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 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.

READ FULL TEXT
research
10/12/2017

Clusters of Driving Behavior from Observational Smartphone Data

Understanding driving behaviors is essential for improving safety and mo...
research
11/10/2018

Detecting Work Zones in SHRP 2 NDS Videos Using Deep Learning Based Computer Vision

Naturalistic driving studies seek to perform the observations of human d...
research
06/16/2023

Vision-Language Models can Identify Distracted Driver Behavior from Naturalistic Videos

Recognizing the activities, causing distraction, in real-world driving s...
research
11/11/2021

Automatically identifying a mobile phone user's position within a vehicle

Traffic-related injuries and fatalities are major health risks in the Un...
research
11/17/2017

Training a network to attend like human drivers saves it from common but misleading loss functions

We proposed a novel FCN-ConvLSTM model to predict multi-focal human driv...
research
08/04/2014

A Pattern Recognition System for Detecting Use of Mobile Phones While Driving

It is estimated that 80 drivers inattentive to traffic for three seconds...
research
04/13/2023

DeepSegmenter: Temporal Action Localization for Detecting Anomalies in Untrimmed Naturalistic Driving Videos

Identifying unusual driving behaviors exhibited by drivers during drivin...

Please sign up or login with your details

Forgot password? Click here to reset