驾驶分心检测方法综述

doi:10.16638/j.cnki.1671-7988.2025.007.008

摘要/Abstract

摘要： 随着车辆自动化和信息娱乐系统的发展，与驾驶分心相关的事故比例上升，因此，驾驶分心已经成为重要且日益严重的安全问题。为了探究驾驶分心检测方法的研究进展，文章将驾驶分心检测方法总结为单类参数方法和多类参数融合方法，并进一步细分为侵入式检测法、半侵入式检测法、非侵入式检测法，梳理了国内外检测方法的研究现状，探讨了驾驶分心检测方法的适用范围和优劣，预测了驾驶分心检测的未来研究趋势。结果表明，单类参数方法的侵入式检测法的识别准确率高，对驾驶员侵入性大，更适用于模拟驾驶环境；半侵入式检测法对驾驶员有一定侵入，影响较小、准确率较高，但具有事后性；多类参数融合方法的侵入式检测法对驾驶员侵入性大，半侵入式检测识别准确率高、侵入性小，但具有事后性。未来可能重点使用多类参数融合方法的半侵入式检测法识别分心，侧重复合分心识别研究，开展精准识别分心类型的研究，建立不同分心程度的识别模型，确定识别指标的重要度，完善识别模型的评价体系。

关键词: 驾驶分心；分心检测；生理特征；眼动仪；驾驶绩效

Abstract: With the development of vehicle automation and infotainment systems, the proportion of accidents associated with driving distraction has increased, therefore driving distraction has become an important and increasingly serious safety issue. In order to explore the research progress of driving distraction detection methods, this paper summarizes the driving distraction detection methods into single-class parameter method and multi-class parameter fusion method, and further subdivides them into invasive detection method, semi-invasive detection method, non-invasive detection method. And reviews the research status of detection methods at home and abroad, discusses the scope of application and advantages and disadvantages of driving distraction detection methods, and predicts the future research trend of driving distraction detection. The results show that the invasive detection method of the single-class parameter method has high recognition accuracy and is highly invasive to the driver, and is more suitable for simulated driving environment. The semi-invasive detection method has a certain degree of intrusion on driving, with little impact and high accuracy, but is ex-post. The invasive detection method of multi-parameter fusion method is highly invasive to the driver. Semi-invasive detection has high recognition accuracy and low invasiveness, but is ex-post. In the future, it is possible to focus on the use of semi-invasive detection of multi-parameter fusion method to identify distractions, focus on the research on compound distraction recognition, carry out research on accurate identification of distraction types, establish recognition models with different degrees of distraction, determine the importance of identification indicators, and improve the evaluation system of recognition models.

Key words: distracted driving; distraction detection; physiological characteristics; eye movement instrument; driving performance

崔同川，王晓庆，李永，李育隆，孙伟程. 驾驶分心检测方法综述[J]. 汽车实用技术, 2025, 50(7): 41-45,52.

CUI Tongchuan, WANG Xiaoqing, LI Yong, LI Yulong, SUN Weicheng. Review of Distracted Driving Detection Methods[J]. Automobile Applied Technology, 2025, 50(7): 41-45,52.

参考文献

[ 1 ] 华强,金立生,郭柏苍,等.一种混行环境下驾驶人认知分心识别方法[J].吉林大学学报(工学版),2022,52 (8):1800-1807. [ 2 ] 徐文翔,赵晓华,杜洪吉.基于样本熵的分心驾驶心理反应研究[J].交通工程,2019,19(S1):59-64. [ 3 ] DEHZANGI O,TAHERISADR M.Driver Distraction Detection Using MEL Cepstrum Representation of Galvanic Skin Responses and Convolutional Neural Networks[C]//2018 24th International Conference on Pattern Recognition.Piscataway:IEEE,2018:1481-1486. [ 4 ] CEGOVNIK T,STOJMENOVA K,JAKUS G,et al.An Analysis of the Suitability of a Low-cost Eye Tracker for Assessing the Cognitive Load of Drivers[J].Applied Ergonomics,2018,68:1-11. [ 5 ] SUN W C,SI Y H,GUO M Z,et al.Driver Distraction Recognition Using Wearable IMU Sensor Data[J].Sustainability,2021,13(3):3390. [ 6 ] YANG S Y,KUO J,LENNE M G.Patterns of Sequential Off-road Glances Indicate Levels of Distraction in Automated Driving[J].Proceedings of the Human Factors and Ergonomics Society Annual Meeting,2019, 63(1):2056-2060. [ 7 ] 米奇,吉柯.分心行为对驾驶员视觉的影响研究[C]// 世界交通运输工程技术论坛(WTC2021)论文集(上). 北京:人民交通出版社,2021:1757-1764. [ 8 ] 王冠,李振龙.基于反向双目识别的驾驶员分心检测 [J].科学技术与工程,2018,18(17):82-88. [ 9 ] ALAM L,HOQUE M M.Real-time Distraction Detection Based on Driver's Visual Features[C]//2019 International Conference on Electrical,Computer and Communication Engineering.Piscataway:IEEE,2019:1-6. [10] 陈仁祥,胡超超,胡小林,等.基于改进 YOLOv5的驾驶员分心驾驶检测[J].吉林大学学报(工学版),2024,54 (4):959-968. [11] ZHAO Z P,XIA S L,XU X Z,et at.Driver Distraction Detection Method Based on Continuous Head Pose Estimation[J].Computational Intelligence and Neuros-cience,2020,10:1155. [12] 秦斌斌,彭良康,卢向明,等.司机分心驾驶检测研究进展[J].计算机应用,2021,41(8):2330-2337. [13] 罗毅,高岩,尤志栋.基于换道行为的驾驶分心识别方法[J].中国安全科学学报,2018,28(10):25-30. [14] ZHANG W H,ZHANG H Y.Research on Distracted Driving Identification of Truck Drivers Based on Simulated Driving Experiment[J].IOP Conference Series:Earth and Environmental Science,2021,638(1): 012039. [15] 孙剑,张一豪,王俊骅.基于自然驾驶数据的分心驾驶行为识别方法[J].中国公路学报,2020,33(9):225-235. [16] SAHAYADHAS A,SUNDARAJ K, MURUGAPPAN M,et al.Physiological Signal Based Detection of Driver Hypovigilance Using Higher Order Spectra[J]. Expert Systems with Applications,2015,42(22):8669- 8677. [17] 王星月.基于多数据源的驾驶分心状态判别及安全风险预测[D].北京:北方工业大学,2023. [18] 莫端.多模态数据融合的驾驶员分心行为识别研究 [D].重庆:重庆理工大学,2024. [19] 陈军,张黎,周博,等.基于级联卷积神经网络的驾驶员分心驾驶行为检测[J].科学技术与工程,2020,20(14): 5702-5708.