背景:驾驶分心识别方法的现有选择是基于特定的研究角度,并且没有提供有关整个视野的全面信息。
方法:我们对以前的研究进行了系统回顾,旨在提出合适的研究方法来识别驾驶员的分心状态。首先,本文从五个数据库(WebofScience,ScienceDirect,SpringerLink,IEEE,和TRID),并确定了2000年至2020年的1,620份同行评审文件;这1,620份文件经过了书目分析和共现网络分析。从时间、国家,出版物,作者和关键词。第二,对发表的37篇论文进行了筛选,并对这37篇论文提出的驾驶分心识别方法进行了总结和分析。
结果:结果表明,该领域自2013年以来一直很普遍;美国等国家,英国,德国,澳大利亚,中国,加拿大在这一领域的研究处于前沿,相关国家之间的合作相对密切。作者之间的合作具有聚集性,而手机作为主关键词几乎与其他关键词节点相连;基于视频监控数据源的深度学习算法识别模型已成为主流热点干扰识别方法。基于车辆动力学数据的机器学习算法识别模型,驾驶员生理学,和眼动数据源具有特定的优点和缺点。
结论:结果可以帮助人们全面,系统地了解驾驶分心的现状,为研究者选择后续的驾驶分心识别模型提供更好的理论支持,为未来驾驶分心识别提供研究方向。
BACKGROUND: The existing selection of driving distraction recognition methods is based on a specific research perspective and does not provide comprehensive information on the entire field of view.
METHODS: We conducted a systematic
review of previous studies, aiming to come up with appropriate research methods to identify the driver\'s distraction state. First, this article selects four sets of search keywords related to driving distraction discrimination from five databases (Web of Science, ScienceDirect, Springer Link, IEEE, and TRID) and identifies 1,620 peer-reviewed documents from 2000 to 2020; these 1,620 documents underwent bibliographic analysis and co-occurrence network analysis. The co-occurrence coupling relationship is analyzed from the aspects of time, country, publication, author and keywords. Second, 37 papers published were screened, and the driving distraction recognition methods proposed by these 37 papers were summarized and analyzed.
RESULTS: The results show that this field has been prevalent since 2013; countries such as the United States, Britain, Germany, Australia, China, and Canada are in the forefront of research in this field, and the cooperation between related countries is relatively close. The cooperation between authors is characterized by aggregation, and the mobile phone as the main keyword is almost connected to other keyword nodes; the recognition model of deep learning algorithm based on video surveillance data sources has become the mainstream hot spot distraction recognition method. The recognition model of machine learning algorithm based on vehicle dynamics data, driver physiology, and eye movement data sources has specific advantages and disadvantages.
CONCLUSIONS: The results can help people to understand the current situation of driving distraction comprehensively and systematically, provide better theoretical support for researchers to choose the subsequent driving distraction recognition model, and provide research direction for driving distraction recognition in the future.