Drowsiness Level Modeling Based on Facial Skin Temperature Distribution Using a Convolutional Neural Network

被引:18
作者
Adachi, Hiroko [1 ]
Oiwa, Kosuke [1 ]
Nozawa, Akio [1 ]
机构
[1] Aoyama Gakuin Univ, Coll Sci & Engn, Chuo Ku, 5-10-1 Fuchinobe, Sagamihara, Kanagawa 2520206, Japan
关键词
drowsiness detection; thermal image; facial skin temperature; deep learning; convolutional neural network; DRIVER DROWSINESS;
D O I
10.1002/tee.22876
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Several drowsiness detection technologies have been developed to combat traffic accidents. Drowsiness evaluation has been attempted using the time-series changes in nasal skin temperature. However, constructing a detection model based on this has been difficult because recent studies have reported an individual difference in skin temperature behaviors. In this study, the conventional method of extracting features was revised. The model of the level of drowsiness was constructed based on facial skin temperature distribution using a convolutional neural network (CNN). The drowsiness level was developed by the New Energy and Industrial Technology Development Organization as an objective drowsiness evaluation index based on facial expressions. With CNNs, features related to learning can be observed as feature quantity distributions. As a result, a general model created has a lack of generality and it is thought that not only the response to drowsiness, but also face shape, exhibit individual differences. Consequently, different features were found in each subject. Through feature maps in individual models, it is believed that skin temperature changes have both reproducible and individual response characteristics to drowsiness, due to the asymmetric left-right change in feature quantity distribution depending on the observed drowsiness level. This method was compared with the conventional method of extracting other features related to drowsiness. It suggested that the skin temperature of not only the nasal region but also the entire face changes as drowsiness increases. Consequently, each discrimination rate calculated by the CNN was at least 20% higher than that obtained via conventional methods. (c) 2019 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
引用
收藏
页码:870 / 876
页数:7
相关论文
共 25 条
  • [1] [Anonymous], SERIES C, DOI DOI 10.1007/S40032-016
  • [2] Evaluation of Dynamics of Forehead Skin Temperature Under Induced Drowsiness
    Bando, Shizuka
    Oiwa, Kosuke
    Nozawa, Akio
    [J]. IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2017, 12 : S104 - S109
  • [3] Causal analysis between vehicle operating data and physiological responses
    Bando S.
    Nozawa A.
    Matsuya Y.
    [J]. Artificial Life and Robotics, 2015, 20 (04) : 299 - 304
  • [4] Cabinet Office, PAP TRAFF SAF 2017, P40
  • [5] Identification of common features of vehicle motion under drowsy/distracted driving: A case study in Wuhan, China
    Chen, Zhijun
    Wu, Chaozhong
    Zhong, Ming
    Lyu, Nengchao
    Huang, Zhen
    [J]. ACCIDENT ANALYSIS AND PREVENTION, 2015, 81 : 251 - 259
  • [6] Effects of adaptive cruise control and highly automated driving on workload and situation awareness: A review of the empirical evidence
    de Winter, Joost C. F.
    Happee, Riender
    Martens, Marieke H.
    Stanton, Neville A.
    [J]. TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2014, 27 : 196 - 217
  • [7] Classification of factors influencing the use of infrared thermography in humans: A review
    Fernandez-Cuevas, Ismael
    Bouzas Marins, Joao Carlos
    Arnaiz Lastras, Javier
    Gomez Carmona, Pedro Maria
    Pinonosa Carlo, Sergio
    Angel Garcia-Concepcion, Miguel
    Sillero-Quintana, Manuel
    [J]. INFRARED PHYSICS & TECHNOLOGY, 2015, 71 : 28 - 55
  • [8] Efficient driver drowsiness detection at moderate levels of drowsiness
    Forsman, Pia M.
    Vila, Bryan J.
    Short, Robert A.
    Mott, Christopher G.
    Van Dongen, Hans P. A.
    [J]. ACCIDENT ANALYSIS AND PREVENTION, 2013, 50 : 341 - 350
  • [9] Hachisuka S, 2011, LECT NOTES ARTIF INT, V6781, P135, DOI 10.1007/978-3-642-21741-8_16
  • [10] Deep-forehead temperature correlates well with blood temperature
    Harioka, T
    Matsukawa, T
    Ozaki, M
    Nomura, K
    Sone, T
    Kakuyama, M
    Toda, H
    [J]. CANADIAN JOURNAL OF ANAESTHESIA-JOURNAL CANADIEN D ANESTHESIE, 2000, 47 (10): : 980 - 983