Recognizing driver inattention by convolutional neural networks

Chao Yan; Huiying Jiang; Bailing Zhang; Frans Coenen

doi:10.1109/CISP.2015.7407964

Recognizing driver inattention by convolutional neural networks

Chao Yan
, Huiying Jiang
, Bailing Zhang
, Frans Coenen

School of Advanced Technology

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

25 Citations (Scopus)

Abstract

Driver inattention has long been recognized as the main contributing factors in traffic accidents. Development of intelligent driver assistance systems with embedded functionality of driver vigilance monitoring is therefore an urgent and challenging task. This paper presents a novel system which applies convolutional neural network to automatically learn and predict the state of driver's eye, mouth and ear. The initial inspiration is to predict driver fatigue and distraction by analysing these states. In our works, a CNN model was trained with six classes of labeled data. The Approach was verified using self-specified Driving Dataset, which comprised of four activities, including normal driving, responding to a cell phone call, eating and falling asleep. Experiment results demonstrate that our design achieves a promising performance with a overall accuracy of 95.56% in classifying six states of the driver's eye, mouth and ear.

Original language	English
Title of host publication	Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015
Editors	Lipo Wang, Sen Lin, Zhiyong Tao, Bing Zeng, Xiaowei Hui, Liangshan Shao, Jie Liang
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	680-685
Number of pages	6
ISBN (Electronic)	9781467390989
DOIs	https://doi.org/10.1109/CISP.2015.7407964
Publication status	Published - 16 Feb 2016
Event	8th International Congress on Image and Signal Processing, CISP 2015 - Shenyang, China Duration: 14 Oct 2015 → 16 Oct 2015

Publication series

Name	Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015

Conference

Conference	8th International Congress on Image and Signal Processing, CISP 2015
Country/Territory	China
City	Shenyang
Period	14/10/15 → 16/10/15

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Driving assistance system
Driving inattention recognition

Access to Document

10.1109/CISP.2015.7407964

Cite this

Yan, C., Jiang, H., Zhang, B., & Coenen, F. (2016). Recognizing driver inattention by convolutional neural networks. In L. Wang, S. Lin, Z. Tao, B. Zeng, X. Hui, L. Shao, & J. Liang (Eds.), Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015 (pp. 680-685). Article 7407964 (Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CISP.2015.7407964

Yan, Chao ; Jiang, Huiying ; Zhang, Bailing et al. / Recognizing driver inattention by convolutional neural networks. Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015. editor / Lipo Wang ; Sen Lin ; Zhiyong Tao ; Bing Zeng ; Xiaowei Hui ; Liangshan Shao ; Jie Liang. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 680-685 (Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015).

@inproceedings{6cac97ccff0d439caf29c5a8e6a1690e,

title = "Recognizing driver inattention by convolutional neural networks",

abstract = "Driver inattention has long been recognized as the main contributing factors in traffic accidents. Development of intelligent driver assistance systems with embedded functionality of driver vigilance monitoring is therefore an urgent and challenging task. This paper presents a novel system which applies convolutional neural network to automatically learn and predict the state of driver's eye, mouth and ear. The initial inspiration is to predict driver fatigue and distraction by analysing these states. In our works, a CNN model was trained with six classes of labeled data. The Approach was verified using self-specified Driving Dataset, which comprised of four activities, including normal driving, responding to a cell phone call, eating and falling asleep. Experiment results demonstrate that our design achieves a promising performance with a overall accuracy of 95.56\% in classifying six states of the driver's eye, mouth and ear.",

keywords = "Driving assistance system, Driving inattention recognition",

author = "Chao Yan and Huiying Jiang and Bailing Zhang and Frans Coenen",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 8th International Congress on Image and Signal Processing, CISP 2015 ; Conference date: 14-10-2015 Through 16-10-2015",

year = "2016",

month = feb,

day = "16",

doi = "10.1109/CISP.2015.7407964",

language = "English",

series = "Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015",

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

pages = "680--685",

editor = "Lipo Wang and Sen Lin and Zhiyong Tao and Bing Zeng and Xiaowei Hui and Liangshan Shao and Jie Liang",

booktitle = "Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015",

}

Yan, C, Jiang, H, Zhang, B & Coenen, F 2016, Recognizing driver inattention by convolutional neural networks. in L Wang, S Lin, Z Tao, B Zeng, X Hui, L Shao & J Liang (eds), Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015., 7407964, Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015, Institute of Electrical and Electronics Engineers Inc., pp. 680-685, 8th International Congress on Image and Signal Processing, CISP 2015, Shenyang, China, 14/10/15. https://doi.org/10.1109/CISP.2015.7407964

Recognizing driver inattention by convolutional neural networks. / Yan, Chao; Jiang, Huiying; Zhang, Bailing et al.
Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015. ed. / Lipo Wang; Sen Lin; Zhiyong Tao; Bing Zeng; Xiaowei Hui; Liangshan Shao; Jie Liang. Institute of Electrical and Electronics Engineers Inc., 2016. p. 680-685 7407964 (Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015).

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

TY - GEN

T1 - Recognizing driver inattention by convolutional neural networks

AU - Yan, Chao

AU - Jiang, Huiying

AU - Zhang, Bailing

AU - Coenen, Frans

PY - 2016/2/16

Y1 - 2016/2/16

N2 - Driver inattention has long been recognized as the main contributing factors in traffic accidents. Development of intelligent driver assistance systems with embedded functionality of driver vigilance monitoring is therefore an urgent and challenging task. This paper presents a novel system which applies convolutional neural network to automatically learn and predict the state of driver's eye, mouth and ear. The initial inspiration is to predict driver fatigue and distraction by analysing these states. In our works, a CNN model was trained with six classes of labeled data. The Approach was verified using self-specified Driving Dataset, which comprised of four activities, including normal driving, responding to a cell phone call, eating and falling asleep. Experiment results demonstrate that our design achieves a promising performance with a overall accuracy of 95.56% in classifying six states of the driver's eye, mouth and ear.

AB - Driver inattention has long been recognized as the main contributing factors in traffic accidents. Development of intelligent driver assistance systems with embedded functionality of driver vigilance monitoring is therefore an urgent and challenging task. This paper presents a novel system which applies convolutional neural network to automatically learn and predict the state of driver's eye, mouth and ear. The initial inspiration is to predict driver fatigue and distraction by analysing these states. In our works, a CNN model was trained with six classes of labeled data. The Approach was verified using self-specified Driving Dataset, which comprised of four activities, including normal driving, responding to a cell phone call, eating and falling asleep. Experiment results demonstrate that our design achieves a promising performance with a overall accuracy of 95.56% in classifying six states of the driver's eye, mouth and ear.

KW - Driving assistance system

KW - Driving inattention recognition

UR - https://www.scopus.com/pages/publications/84966546468

U2 - 10.1109/CISP.2015.7407964

DO - 10.1109/CISP.2015.7407964

M3 - Conference Proceeding

AN - SCOPUS:84966546468

T3 - Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015

SP - 680

EP - 685

BT - Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015

A2 - Wang, Lipo

A2 - Lin, Sen

A2 - Tao, Zhiyong

A2 - Zeng, Bing

A2 - Hui, Xiaowei

A2 - Shao, Liangshan

A2 - Liang, Jie

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th International Congress on Image and Signal Processing, CISP 2015

Y2 - 14 October 2015 through 16 October 2015

ER -

Yan C, Jiang H, Zhang B, Coenen F. Recognizing driver inattention by convolutional neural networks. In Wang L, Lin S, Tao Z, Zeng B, Hui X, Shao L, Liang J, editors, Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015. Institute of Electrical and Electronics Engineers Inc. 2016. p. 680-685. 7407964. (Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015). doi: 10.1109/CISP.2015.7407964

Recognizing driver inattention by convolutional neural networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this