Driver Image Collection Protocol and Database for Driver Monitoring Systems

用于驾驶员监控系统的驾驶员图像收集协议和数据库

• 批准号: 520964-2017
• 负责人: Cao, Shi
• 金额: $ 0.91万
• 依托单位: University of Waterloo
• 依托单位国家: 加拿大
• 项目类别: Engage Plus Grants Program
• 财政年份: 2017
• 资助国家: 加拿大
• 起止时间: 2017-01-01 至 2018-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=639888
• 关键词: Driver; Image; Collection; Protocol; Database

Computer vision technologies have been developed to monitor drivers' behaviours, detecting unsafe eventssuch as fatigue and distraction. Before the technology is released to the public, its accuracy and robustnessmust be tested with human data collected from a wide range of driver populations and driver conditions. In arecently completed research collaboration (NSERC ENGAGE) between the PI and the company (Omron), ahuman data collection protocol has been developed and pilot-tested. As a follow-up step, the current projectaims to further validate the research protocol with a larger sample size of Canadian drivers. The resultingimage database will support the validation of image recognition and driver monitoring systems for theCanadian population. The research will also help address research questions related to driving safety. Forexample, how to determine the impact of critical driver behaviours on driving safety?

计算机视觉技术已被开发用于监控驾驶员的行为，检测疲劳和分心等不安全事件。在向公众发布该技术之前，必须使用从广泛的驾驶员人群和驾驶员条件中收集的人类数据对其准确性和鲁棒性进行测试。在PI和公司（Omron）之间最近完成的研究合作（NSERC ENGAGE）中，已开发并进行了试点测试的人体数据收集协议。作为后续步骤，目前的项目是进一步验证研究协议与更大的样本量的加拿大司机。由此产生的图像数据库将支持加拿大人口的图像识别和驾驶员监控系统的验证。该研究还将有助于解决与驾驶安全相关的研究问题。例如，如何确定关键驾驶员行为对驾驶安全的影响？