Multimodal Detection of Driver Distraction

Eskenazi, Maxine; Morency, Louis-Phillippe; Black, Alan W.; Du, Yulun; Carnegie-Mellon University

Advanced Search

Select up to three search categories and corresponding keywords using the fields to the right. Refer to the Help section for more detailed instructions.

Search our Collections & Repository

Advanced Search
Custom Query

All these words:

For very narrow results

This exact word or phrase:

When looking for a specific result

Any of these words:

Best used for discovery & interchangable words

None of these words:

Recommended to be used in conjunction with other fields

Language:

Dates

Publication Date Range:

to

Document Data

Title:

Document Type:

Library

Collection:

Series:

People

Author:

Clear All

Query Builder

Query box

Clear All

For additional assistance using the Custom Query please check out our Help Page

i

Multimodal Detection of Driver Distraction

2017-01-01
By Eskenazi, Maxine ; Morency, Louis-Phillippe ; Black, Alan W. ; ...

[PDF-238.99 KB]

English

Details You May Also Like

Details:

Creators:

Eskenazi, Maxine ; Morency, Louis-Phillippe ; Black, Alan W. ; Du, Yulun

Eskenazi, Maxine ; Morency, Louis-Phillippe ; Black, Alan W. ; Du, Yulun Less -
Corporate Creators:

Carnegie-Mellon University
Corporate Contributors:

University of Pennsylvania ; Technologies for Safe and Efficient Transportation. University Transportation Center

University of Pennsylvania ; Technologies for Safe and Efficient Transportation. University Transportation Center Less -
Subject/TRT Terms:

[+]

Driver Distraction Driver Monitoring Research Hub
Resource Type:

Tech Report
Geographical Coverage:

United States
Corporate Publisher:

Technologies for Safe and Efficient Transportation. University Transportation Center
Abstract:

Distracted driving has become a major cause of crashes and loss of life. While there is legislation prohibiting the use of cellphones while driving, people continue to use them. We reason that if we can create a system that automatically detects when a person is distracted and warns them (even shutting down an application if necessary), then some serious accidents could be prevented. The goal of this project was to expand on our previous work on automatically detecting driver distraction by using more modalities than simply speech. For this we needed to collect a new dataset where the car information (gas pedal, etc.) and video driver information from a good quality back-facing camera were collected. We collected data from 30 subjects driving the OpenDS simulator we had previously created. In the past, we had used third party observation to annotate the places where the driver was believed to be distracted, for this dataset. For this dataset, we asked each subject to watch the video of their session and to stop the recording at places where they felt they “noticed something else” or that “they may have been less attentive”. They were asked to mark it (a modification of the NASA Task Load Index) and this annotation was logged and synced with the rest of the data. The route conditions were modified slightly – to the hairpin turns and a stop sign in the earlier database we added different placements of the turns and a stop light as well as street signs that could be seen from a distance. We also added small packages along the roadway to represent minor visual distractions that should not have an effect on the safety of the driver but could distract their attention.
Format:

PDF
Funding:

Contract No. DTRT12GUTG11
Collection(s):

University Transportation Centers US Transportation Collection
Main Document Checksum:

[+]

urn:sha256:07995d8d53c371098a4ba9d3798c4e7bdbee7ff65652b75ca1cd86b477c0786c
Download URL:

https://rosap.ntl.bts.gov/view/dot/36243/dot_36243_DS1.pdf
File Type:

No Additional Files

More +

Multimodal Detection of Driver Distraction

Details:

Supporting Files

You May Also Like