2021, 13(3): 65-74. doi: 10.16670/j.cnki.cn11-5823/tu.2021.03.10
基于计算机视觉技术的施工机械操作员疲劳作业检测方法
1. | 天津大学 管理与经济学部,天津 300072 |
2. | 天津旭辉企业管理有限公司有限公司,天津 300041 |
A CV-Based Approach for Detecting Fatigue Operation of Construction Equipment Operators
1. | College of Management and Economics, Tianjin University, Tianjin 300072, China |
2. | CIFI Holdings (Group) Co., Ltd., Tianjin 300041, China |
引用本文:
崔兵, 张金月, 刘相池. 基于计算机视觉技术的施工机械操作员疲劳作业检测方法[J]. 土木建筑工程信息技术,
2021, 13(3): 65-74.
doi: 10.16670/j.cnki.cn11-5823/tu.2021.03.10
Citation:
Bing Cui, Jinyue Zhang, Xiangchi Liu. A CV-Based Approach for Detecting Fatigue Operation of Construction Equipment Operators[J]. Journal of Information Technologyin Civil Engineering and Architecture,
2021, 13(3): 65-74.
doi: 10.16670/j.cnki.cn11-5823/tu.2021.03.10
摘要:施工机械操作员的疲劳检测是工程安全管理中比较复杂棘手的问题。现有的疲劳检测方式存在着各种问题,疲劳问卷难以量化、时效性差,生理指标检测侵入性强、成本高昂。而计算机视觉技术为基于面部信息的疲劳检测提供了一个有价值的技术手段。本论文构建了一种基于计算机视觉技术的施工机械操作员疲劳作业检测方法。采用dlib(图像处理开源库)模型标注68个人脸特征点,计算实时的眼纵横比(EAR)和嘴纵横比(MAR)值,并取前30s视频作为样本计算出相应的阈值,进而计算出眨眼频率、平均眨眼时长、眼睑闭合时间百分比(PERCLOS)以及哈欠频率这四个指标值,利用归一化方法进行指标融合,依据综合疲劳指标的取值和持续时间采取不同的疲劳应对措施。最终通过实验验证该方法的准确性,结果表明本论文提出的综合疲劳指标能够反映不同情境下检测对象疲劳状态的变化趋势,其眨眼状态判定的正确率在95%左右。
Abstract: Fatigue detection of construction machinery operators is a complicated and difficult issue in construction safety management. There are various problems with the existing fatigue detection methods. Traditional fatigue questionnaire is difficult to quantify and poor timeliness. At the same time, the physiological based examination is highly invasive and costly. Computer Vision (CV) technology is a valuable technique for fatigue detection based on facial information collection and analysis. This paper proposes an approach for detecting fatigue operations of construction equipment operators based on CV. This approach uses the dlib model to mark 68 face feature points, and then calculates the real-time Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) values, and takes the first 30 seconds of video as a sample to calculate the corresponding threshold, and then calculates the four indicators of blink frequency, average blink duration, Percentage of Eyelid Closure over the Pupil (PERCLOS) and yawn frequency. After that, normalized methods are employed to integrate indicators, and different fatigue countermeasures can be taken according to the value and duration of the comprehensive fatigue index. Finally, the accuracy of the method is verified through experiments. The results show that the comprehensive fatigue index proposed in this paper can reflect the trend of the fatigue state of construction equipment operators under different situations, and the correct rate of blink judgment is about 95%.
[1] |
Dittner A J, Wessely S C, Brown R G. The assessment of fatigue-A practical guide for clinicians and researchers[J]. Journal of Psychosomatic Research, 2004, 56(2): 157-170.doi: 10.1016/S0022-3999(03)00371-4 |
[2] |
Zhang M, Sparer E H, Murphy L A, et al. Development and validation of a fatigue assessment scale for U.S. construction workers[J]. American Journal of Industrial Medicine, 2015, 58(2): 220-228.doi: 10.1002/ajim.22411 |
[3] |
Zhang M, Fang D. A continuous Behavior-Based Safety strategy for persistent safety improvement in construction industry[J]. Automation in Construction, 2013, 34: 101-107.doi: 10.1016/j.autcon.2012.10.019 |
[4] |
Aryal A, Ghahramani A, Becerik-Gerber B. Monitoring fatigue in construction workers using physiological measurements[J]. Automation in Construction, 2017, 82: 154-165.doi: 10.1016/j.autcon.2017.03.003 |
[5] |
曾友雯, 冯珍, 祝亚兵, 等. 基于脑电实验的眨眼次数与疲劳相关性研究[J]. 长春理工大学学报(自然科学版), 2017, 40(1): 123-126.doi: 10.3969/j.issn.1672-9870.2017.01.030 |
[6] |
Tsai M. Applying physiological status monitoring in improving construction safety management[J]. KSCE Journal of Civil Engineering, 2017, 21(6): 2061-2066.doi: 10.1007/s12205-016-0980-9 |
[7] |
卢章平, 尹传斌, 李瑞, 等. 基于生理信号的驾驶疲劳分级检测研究[J]. 重庆交通大学学报(自然科学版), 2017, 36(1): 77-81. |
[8] |
He J, Choi W, Yang Y, et al. Detection of driver drowsiness using wearable devices: A feasibility study of the proximity sensor[J]. Applied Ergonomics, 2017, 65: 473-480.doi: 10.1016/j.apergo.2017.02.016 |
[9] |
Nie B, Huang X, Chen Y, et al. Experimental study on visual detection for fatigue of fixed-position staff[J]. Applied Ergonomics, 2017, 65: 1-11.doi: 10.1016/j.apergo.2017.05.010 |
[10] |
Ishimaru S, Kunze K, Kise K, et al. In the blink of an eye: combining head motion and eye blink frequency for activity recognition with Google Glass[C]. Proceedings of the 5th Augmented Human International Conference, Kobe: ACM, 2014, 150-153. |
[11] | |
[12] | |
[13] |
Soukupová T, ech J. Real-Time Eye Blink Detection using Facial Landmarks[C]. 21st computer vision winter workshop, Rimske Toplice: 2016. |
[14] |
Wierwille W W, Wreggit S S, Kirn C L, et al. Research on vehicle-based driver status/performance monitoring; development, validation, and refinement of algorithms for detection of driver drowsiness, Final Report: DOT HS 808 247[R]. Washington DC: National Highway Traffic Safety Administration, 1994. |
[15] |
Jin H. Traffic Crash Epidemiology[M]. Beijing: Science Press, 2013, 24-30. |
[16] |
杨春宇, 胡皓, 向奕妍, 等. LED照明环境下照明参数对人眼视疲劳的影响[J]. 土木建筑与环境工程, 2018, 40(4): 88-93. |
[17] |
Nie B, Huang X, Chen Y, et al. Experimental study on visual detection for fatigue of fixed-position staff[J]. Applied Ergonomics, 2017, 65: 1-11. |
[18] |
计量
- PDF下载量(39)
- 文章访问量(2209)
- HTML全文浏览量(1260)