Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework

Yajuan Wei; Zhaoli Guo; Chuan Dai; Minsi Chen; Zhijie Xu; Ying Liu; Jiulun Fan

doi:10.1109/ICAC55051.2022.9911167

Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework

Yajuan Wei
, Zhaoli Guo
, Chuan Dai
, Minsi Chen
, Zhijie Xu
, Ying Liu
, Jiulun Fan

Xi'an Institute of Posts and Telecommunications
University of Huddersfield

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

3 Citations (Scopus)

Abstract

With the surge of the number of cars, road traffic accidents occur frequently because of drivers' distracted attention and abnormal behaviors, which causes huge losses to people's lives and property. To alleviate this issue, an improved deep learning algorithm based on YOLOX framework was proposed in this research to detect driving behavior changes in live. An attention mechanism - Convolutional Block Attention Module (CBAM) - was introduced in multiple scales of feature layers to form the backbone of YOLOX network. A widely used data science competition platform was adopted for distracted behavior model training. The State Farm Distracted Driver Detection Dataset was used for model validation and performance benchmarking. Experimental results have indicated promising performance gain using the devised model over the original YOLOX framework in terms of mAP and inference time.

Original language	English
Title of host publication	2022 27th International Conference on Automation and Computing
Subtitle of host publication	Smart Systems and Manufacturing, ICAC 2022
Editors	Chenguang Yang, Yuchun Xu
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665498074
DOIs	https://doi.org/10.1109/ICAC55051.2022.9911167
Publication status	Published - 2022
Externally published	Yes
Event	27th International Conference on Automation and Computing, ICAC 2022 - Bristol, United Kingdom Duration: 1 Sept 2022 → 3 Sept 2022

Publication series

Name	2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022

Conference

Conference	27th International Conference on Automation and Computing, ICAC 2022
Country/Territory	United Kingdom
City	Bristol
Period	1/09/22 → 3/09/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

CBAM module
Distracted driving behavior
mAP
YOLOX

Access to Document

10.1109/ICAC55051.2022.9911167

Cite this

Wei, Y., Guo, Z., Dai, C., Chen, M., Xu, Z., Liu, Y., & Fan, J. (2022). Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework. In C. Yang, & Y. Xu (Eds.), 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022 (2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAC55051.2022.9911167

Wei, Yajuan ; Guo, Zhaoli ; Dai, Chuan et al. / Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework. 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022. editor / Chenguang Yang ; Yuchun Xu. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022).

@inproceedings{2af251075b8a444f81c685fedd5ef7d7,

title = "Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework",

abstract = "With the surge of the number of cars, road traffic accidents occur frequently because of drivers' distracted attention and abnormal behaviors, which causes huge losses to people's lives and property. To alleviate this issue, an improved deep learning algorithm based on YOLOX framework was proposed in this research to detect driving behavior changes in live. An attention mechanism - Convolutional Block Attention Module (CBAM) - was introduced in multiple scales of feature layers to form the backbone of YOLOX network. A widely used data science competition platform was adopted for distracted behavior model training. The State Farm Distracted Driver Detection Dataset was used for model validation and performance benchmarking. Experimental results have indicated promising performance gain using the devised model over the original YOLOX framework in terms of mAP and inference time.",

keywords = "CBAM module, Distracted driving behavior, mAP, YOLOX",

author = "Yajuan Wei and Zhaoli Guo and Chuan Dai and Minsi Chen and Zhijie Xu and Ying Liu and Jiulun Fan",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 27th International Conference on Automation and Computing, ICAC 2022 ; Conference date: 01-09-2022 Through 03-09-2022",

year = "2022",

doi = "10.1109/ICAC55051.2022.9911167",

language = "English",

series = "2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Chenguang Yang and Yuchun Xu",

booktitle = "2022 27th International Conference on Automation and Computing",

}

Wei, Y, Guo, Z, Dai, C, Chen, M, Xu, Z, Liu, Y & Fan, J 2022, Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework. in C Yang & Y Xu (eds), 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022. 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022, Institute of Electrical and Electronics Engineers Inc., 27th International Conference on Automation and Computing, ICAC 2022, Bristol, United Kingdom, 1/09/22. https://doi.org/10.1109/ICAC55051.2022.9911167

Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework. / Wei, Yajuan; Guo, Zhaoli; Dai, Chuan et al.
2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022. ed. / Chenguang Yang; Yuchun Xu. Institute of Electrical and Electronics Engineers Inc., 2022. (2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework

AU - Wei, Yajuan

AU - Guo, Zhaoli

AU - Dai, Chuan

AU - Chen, Minsi

AU - Xu, Zhijie

AU - Liu, Ying

AU - Fan, Jiulun

PY - 2022

Y1 - 2022

N2 - With the surge of the number of cars, road traffic accidents occur frequently because of drivers' distracted attention and abnormal behaviors, which causes huge losses to people's lives and property. To alleviate this issue, an improved deep learning algorithm based on YOLOX framework was proposed in this research to detect driving behavior changes in live. An attention mechanism - Convolutional Block Attention Module (CBAM) - was introduced in multiple scales of feature layers to form the backbone of YOLOX network. A widely used data science competition platform was adopted for distracted behavior model training. The State Farm Distracted Driver Detection Dataset was used for model validation and performance benchmarking. Experimental results have indicated promising performance gain using the devised model over the original YOLOX framework in terms of mAP and inference time.

AB - With the surge of the number of cars, road traffic accidents occur frequently because of drivers' distracted attention and abnormal behaviors, which causes huge losses to people's lives and property. To alleviate this issue, an improved deep learning algorithm based on YOLOX framework was proposed in this research to detect driving behavior changes in live. An attention mechanism - Convolutional Block Attention Module (CBAM) - was introduced in multiple scales of feature layers to form the backbone of YOLOX network. A widely used data science competition platform was adopted for distracted behavior model training. The State Farm Distracted Driver Detection Dataset was used for model validation and performance benchmarking. Experimental results have indicated promising performance gain using the devised model over the original YOLOX framework in terms of mAP and inference time.

KW - CBAM module

KW - Distracted driving behavior

KW - mAP

KW - YOLOX

UR - https://www.scopus.com/pages/publications/85141210319

U2 - 10.1109/ICAC55051.2022.9911167

DO - 10.1109/ICAC55051.2022.9911167

M3 - Conference Proceeding

AN - SCOPUS:85141210319

T3 - 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022

BT - 2022 27th International Conference on Automation and Computing

A2 - Yang, Chenguang

A2 - Xu, Yuchun

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th International Conference on Automation and Computing, ICAC 2022

Y2 - 1 September 2022 through 3 September 2022

ER -

Wei Y, Guo Z, Dai C, Chen M, Xu Z, Liu Y et al. Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework. In Yang C, Xu Y, editors, 2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. (2022 27th International Conference on Automation and Computing: Smart Systems and Manufacturing, ICAC 2022). doi: 10.1109/ICAC55051.2022.9911167

Distracted Driver Behavior Detection Based-on An Improved YOLOX Framework

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this