U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers
In recent years, the number of deaths and injuries resulting from traffic accidents has been increasing dramatically all over the world due to distracted drivers. Thus, a key element in developing intelligent vehicles and safe roads is monitoring driver behaviors. In this paper, we modify and extend...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/21/11898 |
_version_ | 1797632171597365248 |
---|---|
author | Nawaf O. Alsrehin Mohit Gupta Izzat Alsmadi Saif Addeen Alrababah |
author_facet | Nawaf O. Alsrehin Mohit Gupta Izzat Alsmadi Saif Addeen Alrababah |
author_sort | Nawaf O. Alsrehin |
collection | DOAJ |
description | In recent years, the number of deaths and injuries resulting from traffic accidents has been increasing dramatically all over the world due to distracted drivers. Thus, a key element in developing intelligent vehicles and safe roads is monitoring driver behaviors. In this paper, we modify and extend the U-net convolutional neural network so that it provides deep layers to represent image features and yields more precise classification results. It is the basis of a very deep convolution neural network, called U2-net, to detect distracted drivers. The U2-net model has two paths (contracting and expanding) in addition to a fully-connected dense layer. The contracting path is used to extract the context around the objects to provide better object representation while the symmetric expanding path enables precise localization. The motivation behind this model is that it provides precise object features to provide a better object representation and classification. We used two public datasets: MI-AUC and State Farm, to evaluate the U2 model in detecting distracted driving. The accuracy of U2-net on MI-AUC and State Farm is 98.34 % and 99.64%, respectively. These evaluation results show higher accuracy than achieved by many other state-of-the-art methods. |
first_indexed | 2024-03-11T11:34:08Z |
format | Article |
id | doaj.art-ec59595d52884f07859bcfef21b65213 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T11:34:08Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-ec59595d52884f07859bcfef21b652132023-11-10T14:59:06ZengMDPI AGApplied Sciences2076-34172023-10-0113211189810.3390/app132111898U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted DriversNawaf O. Alsrehin0Mohit Gupta1Izzat Alsmadi2Saif Addeen Alrababah3Computer Sciences Department, University of Wisconsin-Madison, Madison, WI 53706, USAComputer Sciences Department, University of Wisconsin-Madison, Madison, WI 53706, USADepartment of Computing and Cyber Security, Texas A&M University-San Antonio, San Antonio, TX 78224, USAFaculty of Information Technology, Al Albayt University, Al-Mafraq 25113, JordanIn recent years, the number of deaths and injuries resulting from traffic accidents has been increasing dramatically all over the world due to distracted drivers. Thus, a key element in developing intelligent vehicles and safe roads is monitoring driver behaviors. In this paper, we modify and extend the U-net convolutional neural network so that it provides deep layers to represent image features and yields more precise classification results. It is the basis of a very deep convolution neural network, called U2-net, to detect distracted drivers. The U2-net model has two paths (contracting and expanding) in addition to a fully-connected dense layer. The contracting path is used to extract the context around the objects to provide better object representation while the symmetric expanding path enables precise localization. The motivation behind this model is that it provides precise object features to provide a better object representation and classification. We used two public datasets: MI-AUC and State Farm, to evaluate the U2 model in detecting distracted driving. The accuracy of U2-net on MI-AUC and State Farm is 98.34 % and 99.64%, respectively. These evaluation results show higher accuracy than achieved by many other state-of-the-art methods.https://www.mdpi.com/2076-3417/13/21/11898convolutional neural networksdeep learningdistracted driversobject detection |
spellingShingle | Nawaf O. Alsrehin Mohit Gupta Izzat Alsmadi Saif Addeen Alrababah U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers Applied Sciences convolutional neural networks deep learning distracted drivers object detection |
title | U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers |
title_full | U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers |
title_fullStr | U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers |
title_full_unstemmed | U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers |
title_short | U2-Net: A Very-Deep Convolutional Neural Network for Detecting Distracted Drivers |
title_sort | u2 net a very deep convolutional neural network for detecting distracted drivers |
topic | convolutional neural networks deep learning distracted drivers object detection |
url | https://www.mdpi.com/2076-3417/13/21/11898 |
work_keys_str_mv | AT nawafoalsrehin u2netaverydeepconvolutionalneuralnetworkfordetectingdistracteddrivers AT mohitgupta u2netaverydeepconvolutionalneuralnetworkfordetectingdistracteddrivers AT izzatalsmadi u2netaverydeepconvolutionalneuralnetworkfordetectingdistracteddrivers AT saifaddeenalrababah u2netaverydeepconvolutionalneuralnetworkfordetectingdistracteddrivers |