基于车载机器视觉的汽车安全技术  

Automobile Safety Technology Based on the Vision of On-board Machines

作　　者：初秀民[1] 万剑[1] 严新平[1] 毛喆[1] 

机构地区：[1]水路公路交通安全控制与装备教育部工程研究中心

出　　处：《中国安全科学学报》2008年第5期154-161,共8页China Safety Science Journal

基　　金：国家自然科学基金资助(50578128);"863"计划(2006AA11Z215)

摘　　要：在描述汽车驾驶操作过程基础上,根据信息获取范围将汽车安全辅助驾驶的机器视觉分为外部信息的机器视觉与内部信息的机器视觉技术,包括视觉增强、视野扩展、道路环境理解、视线跟踪与驾驶疲劳监测;逐个阐述其作用机理,综述其国内外研究现状,并归纳出研究重点;分析了汽车安全辅助驾驶系统中机器视觉技术当前研究不足。笔者认为,低能见度驾驶员视觉增强方法、道路环境理解信息融合以及驾驶疲劳检测等技术需进一步开展研究。According to the operation process of driving vehicle and the vision scope of information acquisition, the machine vision of safety assistant driving system was divided into external information machine vision and internal information machine vision technology, which included drivers＇ vision enhancement, drivers＇vision enlargement, understanding of road environment, sightline tracking and fatigue-driving monitoring. The impact mechanism of the machine vision on drivers was respectively analyzed ; the research situation in this field at home and abroad was reviewed and the major research field was summarized. Meanwhile, the weakness of machine vision technology in automobile safety assistant driving system was analyzed. It was considered that such technologies about drivers＇vision enhancement in low visibility, information fusion of road environment and fatigue-driving monitoring should be further studied.

关 键 词：道路安全 驾驶员视觉 汽车安全辅助驾驶 机器视觉 

分 类 号：X924.2[环境科学与工程—安全科学]