Fatigue Driving Recognition Algorithm Using Random Forest with Multi-feature Fusion

doi:10.3778/j.issn.1002-8331.1907-0392

Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (20): 212-219.DOI: 10.3778/j.issn.1002-8331.1907-0392

Previous Articles Next Articles

Fatigue Driving Recognition Algorithm Using Random Forest with Multi-feature Fusion

WU Shili, TANG Zhenmin, LIU Yong

1.School of Computer Science and Engineering, Nanjing University of Technology, Nanjing 210094, China
2.Laboratory of Chang’an Ford, Department of Automobile Engineering, Nanjing Vocational Institute of Transport Technology, Nanjing 211188, China

Online:2020-10-15 Published:2020-10-13

多特征融合的随机森林疲劳驾驶识别算法

吴士力，唐振民，刘永

1.南京理工大学计算机科学与工程学院，南京 210094
2.南京交通职业技术学院汽车工程学院长安福特实验室，南京 211188

Abstract

Abstract:

Complex traffic environment, personal and social factors restrict the application effect of fatigue driving recognition technology. This paper presents a fatigue driving recognition algorithm based on the fusion analysis of driver’s face state in video and vehicle driving state data. The algorithm calculates the aspect ratio of eyes and mouth based on the extracted face contour points using Dlib database, and then generates the orbital and yawn features. At the same time, the vehicle manipulation activity features based on the linear fitting trend extraction method are obtained. The improved random forest model is used to identify the fatigue state. The model evaluates the importance of features based on weight, improves the validity of tree nodes splitting, and gives the method of regulating the number of trees in forest. The experimental results show that the average accuracy of fatigue driving recognition of the proposed algorithm reaches 92.06%, and it has good computational efficiency meanwhile, which verifies its effectiveness.

Key words: random forest, face contour points, vehicle manipulation activity, fatigue driving

摘要：

复杂的交通环境、个人和社会因素制约了疲劳驾驶识别技术的应用效果，提出一种对视频中驾驶员脸部状态和车辆驾驶状态数据进行融合分析的疲劳驾驶识别算法。该算法基于Dlib库提取的人脸轮廓点计算眼和嘴的纵横比值，生成眯眼和哈欠特征，基于线性拟合趋势提取法生成车辆操控活跃度特征，然后采用改进后的随机森林模型对疲劳状态进行识别。该模型基于权重对特征的重要性进行评估，提高了树节点分裂的有效性，并给出了森林中树的数量的调控方法。实验结果表明所提算法的疲劳驾驶识别准确率均值达到了92.06%，并具有较好的计算效率，验证了其有效性。

关键词: 随机森林, 人脸轮廓点, 车辆操控活跃度, 疲劳驾驶

WU Shili, TANG Zhenmin, LIU Yong. Fatigue Driving Recognition Algorithm Using Random Forest with Multi-feature Fusion[J]. Computer Engineering and Applications, 2020, 56(20): 212-219.

吴士力，唐振民，刘永. 多特征融合的随机森林疲劳驾驶识别算法[J]. 计算机工程与应用, 2020, 56(20): 212-219.

[1]	YANG Yemin, ZHANG Huijun, ZHANG Xiaolong. Research on Interpretable Visual Analysis Method of Random Forest [J]. Computer Engineering and Applications, 2021, 57(6): 168-175.
[2]	XIONG Jian, QIN Renchao, HE Mengyi, LIU Jianlan, TANG Fengyang. Application of Improved Random Forest Algorithm in Android Malware Detection [J]. Computer Engineering and Applications, 2021, 57(3): 130-136.
[3]	AN Lei, HAN Zhonghua, LIN Shuo, SHANG Wenli. Research on GAN-SDAE-RF Model for Network Intrusion Detection [J]. Computer Engineering and Applications, 2021, 57(21): 155-164.
[4]	WU Weijie, ZHANG Jingxiang. Random Forest Feature Selection Algorithm Based on Categorization Information and Application [J]. Computer Engineering and Applications, 2021, 57(17): 147-156.
[5]	YAN Zhengxu, QIN Chao, SONG Gang. Random Forest Model Stock Price Prediction Based on Pearson Feature Selection [J]. Computer Engineering and Applications, 2021, 57(15): 286-296.
[6]	ZHU Di, CHEN Danwei. Technology of Mobile Application Identification Based on Density-Based Clustering and Random Forest [J]. Computer Engineering and Applications, 2020, 56(4): 63-68.
[7]	HU Qingyu, LIU Guangchen. Application of Deep Belief Network in Recognition of Protein Coding Regions [J]. Computer Engineering and Applications, 2020, 56(4): 247-255.
[8]	LI Ling, GU Xiaomei, LIU Zihao. Application Research of Multi-subdomain Random Forest in Context-Aware Recommendation [J]. Computer Engineering and Applications, 2020, 56(22): 132-141.
[9]	LUO Jigen, DU Jianqiang, NIE Bin, LI Huan, NIE Jianhua, CHEN Yufeng. Random Forest Optimization Method Based on Cluster Undersampling Strategy [J]. Computer Engineering and Applications, 2020, 56(22): 166-172.
[10]	LI Jieqi, HU Liangbing. Review of Machine Learning for Predictive Maintenance [J]. Computer Engineering and Applications, 2020, 56(21): 11-19.
[11]	CHENG Zhenjing, CHENG Yaodong, CHEN Gang, WANG Lu, LI Haibo, HU Qingbao. High Energy Physics Data Placement Strategy Based on Random Forest [J]. Computer Engineering and Applications, 2020, 56(21): 60-64.
[12]	GOU Jijun, LI Junhua, CHEN Chen, CHEN Yiming, LV Yida. Network Intrusion Detection Method Based on Random Forest [J]. Computer Engineering and Applications, 2020, 56(2): 82-88.
[13]	SUN Fuxiong, LIU Guangming, ZENG Zixuan, PENG Mengqi. Research on Stock Suspension Prediction Based on Combination Model [J]. Computer Engineering and Applications, 2020, 56(18): 272-278.
[14]	GUO Yuhan, HU Dejia. Vehicle Multiplication Solution Based on Random Forest and Variable Neighborhood Decline [J]. Computer Engineering and Applications, 2020, 56(13): 243-253.
[15]	ZHANG Jiawei, GUO Linming, YANG Xiaomei. Improved Oversampling and Random Forest Algorithm for Imbalanced Data [J]. Computer Engineering and Applications, 2020, 56(11): 39-45.

Fatigue Driving Recognition Algorithm Using Random Forest with Multi-feature Fusion

多特征融合的随机森林疲劳驾驶识别算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics