Journal of Jilin University(Engineering and Technology Edition) ›› 2021, Vol. 51 ›› Issue (2): 704-711.doi: 10.13229/j.cnki.jdxbgxb20200767

Previous Articles    

Classification of drivers' head status based on improved ResNeSt

Qian-yi XU1,2(),Gui-he QIN1,2,Ming-hui SUN1,2(),Cheng-xun MENG3   

  1. 1.College of Computer Science and Technology，Jilin University，Changchun 130012，China
    2.Key Laboratory of Symbolic Computing and Knowledge Engineering，Ministry of Education，Jilin University，Changchun 130012，China
    3.Jilin Hangsheng Electronics Co. ，Jilin 132013，China
  • Received:2020-10-19 Online:2021-03-01 Published:2021-02-09
  • Contact: Ming-hui SUN E-mail:xuqynina@163.com;smh@jlu.edu.cn

RICH HTML

 13   

PDF (PC)

440

Abstract:

In order to quickly and accurately obtain the driver's head status during the driving schedule to identify drivers' status， an improved ResNeSt classification algorithm is proposed in this paper. Yolov4 is used as an algorithm to detect the drivers' head to obtain head images. To solve the problem of imbalance classification of the dataset， the method named PULSE is applied to recover the focus failed image to complete the dataset. Experimental results show that the classification accuracy can reach to 80.51%， indicating that the proposed algorithm has certain validity and accuracy.

Key words: computer application technology, driver's head status detection, image classification, ResNeSt

CLC Number: 

  • TP391.9

Fig.1

Image using PULSE method"

Fig.2

Reorganized dataset"

Fig.3

ResNeSt block structure diagram"

Fig.4

Split-Attention within a cardinal group"

Fig.5

Improved ResNeSt block structure diagram"

Fig.6

Self-Calibrated Conv module structure diagram"

Table 1

Classification algorithm comparison"

算法参数量MTop-1准确率/%

ResNet-50

ResNet-101

ResNext-50

ResNext-101

SENet-50

SENet-101

SKNet-50

SKNet-101

SCNet-50

SCNet-101

ResNeSt-50

ResNeSt-101

25.6

44.5

25.0

44.2

27.9

49.3

27.5

48.4

25.6

44.5

27.5

48.2

76.23

77.42

77.53

78.61

78.04

79.37

79.18

78.91

77.78

78.26

79.93

80.04

改进的ResNest-10148.180.51

Table 1

Comparison of data classification accuracy"

数据准确率/%

原始数据（10分类）

原始数据（13分类）

PULSE数据（单分类）

最终数据（13分类）

77.27

78.42

90.15

80.51

1 Li L, Song J Y, Wang F Y, et al. IVS 05: new developments and research trends for intelligent vehicles[J]. IEEE Intelligent Systems, 2005, 20(4): 10-14.
2 Li L, Wang F Y. Advanced Motion Control and Sensing for Intelligent Vehicles[M]. Springer Science & Business Media, 2007.
3 Jain A, Singh A, Koppula H S, et al. Recurrent neural networks for driver activity anticipation via sensory-fusion architecture[C]∥IEEE International Conference on Robotics and Automation, Stockholm, Sweden, 2016: 3118-3125.
4 Agustina G, Correa L, Orosco E, et al. Automatic detection of drowsiness in EEG records based on multimodal analysis[J]. Medical Engineering & Physics, 2013, 36(2): 244-249.
5 Patrick K C A, Imtiaz S A, Bowyer S, et al. An algorithm for automatic detection of drowsiness for use in werable EEG systems[C]∥Proceedings of the 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, FL, 2016: 3523-3526.
6 Zhao S, Xu G, Tao T. Detecting of driver's drowsiness using multiwavelet packet energy spectrum[C]∥Proceedings of the 2nd International Congress on Image and Signal, Tianjin, China, 2009: 1-5.
7 He Q, Li W, Fan X. Estimation of driver's fatigue based on steering wheel angle[C]∥Proceedings of the International Conference of Engineering Psychology and Cognitive Ergonomics, Berlin, Heidelberg, 2011: 145-155.
8 Zhang X B, Cheng B, Feng J J. Real-time detection method of driver fatigue state based on steering wheel operation[J]. Journal of Tsinghua University Science and Technology, 2010, 7(1): 1072-1076.
9 Tawari A, Trivedi M M. Robust and continuous estimation of driver gaze zone by dynamic analysis of multiple face videos[C]∥IEEE Intelligent Vehicles Symposium Proceedings, Dearborn, MI, 2014: 344-349.
10 Choi I H, Kim Y G. Head pose and gaze direction tracking for detecting a drowsy driver[C]∥Proceedings of the International Conference on Big Data and Smart Computing, Berlin, Heidelberg, 2014: 807-814.
11 Zhao L, Wang Z, Wang X, et al. Human fatigue expression and bimodal deep learning[J]. Journal of Electronic Imaging, 2016, 25(5): 53024-53034.
12 Halim Z, Kalsoom R, Baig A R. Profiling drivers based on driver dependent vehicle driving features[J]. Applied Intelligence, 2016, 44: 645-664.
13 Jabon M, Bailenson J, Pontikakis E, et al. Facial expression analysis for predicting unsafe driving behavior[J]. IEEE Pervasive Computing, 2011, 10(4): 84-95.
14 Papageorgiou C P, Oren M, Poggio T. A general framework for object detection[C]∥6th International Conference on Computer Vision, Bombay, India, 1998: 555-562.
15 Lowe D G. Object recognition from local scale-invariant features[C]∥Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 1999: 1150-1157.
16 Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]∥Proceedings of Computer Vision and Pattern Recognition, San Diego, California, 2005: 886-893.
17 Donahue J, Jia Y, Vinyals O, et al. DeCAF: a deep convolutional activation feature for generic visual recognition[J]. Computer Vision and Pattern Recognition, arXiv: 1310.1531.
18 Lienhart R, Maydt J. An extended set of haar-like features for rapid object detection[C]∥Proceedings of International Conference on Image Processing, Rochester, NY, USA, 2002: 900-903.
19 Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥Proceedings of Computer Vision and Pattern Recognition, Columbus, Ohio, 2014: 580-587.
20 Blaschko M B, Lampert C H. Learning to localize objects with structured output regression[C]∥Proceedings of European Conference on Computer Vision, Berlin, Heidelber, 2008: 2-15.
21 Sermanet P, Eigen D, Zhang X, et al. Overfeat: integrated recognition, localization and detection using convolutional networks[J]. Computer Vision and Pattern Recognition, arXiv: 1312.6229.
22 Uijlings J R, van de Sande K E, Gevers T, et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2): 154-171.
23 Zitnick C L, Dollar P. Edge boxes: locating object proposals from edges[C]∥Proceedings of European Conference on Computer Vision, Zurich, Switzerland, 2014: 391-405.
24 Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. Computer Vision and Pattern Recognition, arXiv:2004.10934.
25 李志军, 杨楚皙, 刘丹, 等. 基于深度卷积神经网络的信息流增强图像压缩方法[J]. 吉林大学学报: 工学版, 2020, 50(5): 1788-1795.
Li Zhi-jun, Yang Chu-xi, Liu Dan, et al. Deep convolutional networks based image compression with enhancement of information flow[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(5): 1788-1795.
26 刘国华, 周文斌. 基于卷积神经网络的脉搏波时频域特征混叠分类[J]. 吉林大学学报: 工学版, 2020, 50(5): 1818-1825.
Liu Guo-hua, Zhou Wen-bin. Pulse wave signal classification algorithm based on time⁃frequency domain feature aliasing using convolutional neural network[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(5): 1818-1825.
27 He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),Las Vegas, USA, 2016:770-778.
28 Xie S, Girshick R, Dollár P, et al. Aggregated residual transformations for deep neural networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA, 2017: 1492-1500.
29 Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 7132-7141.
30 Zhang H, Wu C R, Zhang Z Y, et al. ResNeSt: split-attention networks[J]. Computer Vision and Pattern Recognition, arXiv:2004.08955.
31 Competition Kaggle. State Farm Distracted Driver Detection[DB/OL]. [2019-10-12].
32 Redmon J, Farhadi A. Yolov3: an incremental improvement[J]. Computer Vision and Pattern Recognition, arXiv:1804.02767.
33 Huang G, Liu Z, van der Maaten L, et al. Densely connected convolutional networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Hawaii, USA, 2017: 4700-4708.
34 Li X, Wang W, Hu X, et al. Selective kernel networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Los Angeles, USA, 2019: 510-519.
35 Liu J J, Hou Q, Cheng M M, et al. Improving convolutional networks with self-calibrated convolutions[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 10096-10105.
[1] Yuan SONG,Dan-yuan ZHOU,Wen-chang SHI. Method to enhance security function of OpenStack Swift cloud storage system [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 314-322.
[2] Xiang-jiu CHE,You-zheng DONG. Improved image recognition algorithm based on multi⁃scale information fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(5): 1747-1754.
[3] Xiang-jiu CHE,Hua-luo LIU,Qing-bin SHAO. Fabric defect recognition algorithm based onimproved Fast RCNN [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 2038-2044.
[4] CHEN Mian-shu, SU Yue, SANG Ai-jun, LI Pei-peng. Image classification methods based on space vector model [J]. 吉林大学学报(工学版), 2018, 48(3): 943-951.
[5] HU Guan-yu, QIAO Pei-li. High dimensional differential evolutionary algorithm based on cloud population for network security prediction [J]. 吉林大学学报(工学版), 2016, 46(2): 568-577.
[6] CHEN Zai-qing, SHI Jun-sheng, BAI Feng-xiang. Automatic image classification based on fuzzy-rough set [J]. 吉林大学学报(工学版), 2013, 43(增刊1): 209-212.
[7] TONG Jin, WANG Ya-hui, FAN Xue-mei, ZHANG Shu-jun, CHEN Dong-hui. Monitoring system of cold chain logistics for farm fresh produce [J]. 吉林大学学报(工学版), 2013, 43(06): 1707-1711.
[8] WANG Ying, GUO Lei, LIANG Nan. Classification algorithm of hyperspectral images based on kernel entropy analysis [J]. , 2012, (06): 1597-1601.
[9] LIU Ping-ping, ZHAO Hong-wei, GENG Qing-tian, DAI Jin-bo. Image classification method based on local feature and visual cortex recognition mechanism [J]. 吉林大学学报(工学版), 2011, 41(05): 1401-1406.
[10] Cao Chun-hong Zhang Bin,Li Xiao-lin . Medical image classification technology based on fuzzy support vector machine [J]. 吉林大学学报(工学版), 2007, 37(03): 630-0633.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd