Driver Image Collection Protocol and Database for Driver Monitoring Systems

计算机视觉技术已被用于监控驾驶员的行为，检测疲劳和分心等不安全事件。在向公众发布这项技术之前，必须使用从广泛的驾驶员人群和驾驶员状况中收集的人类数据来测试其准确性和稳健性。在PI和公司（欧姆龙）最近完成的一项研究合作（NSERC ENGAGE）中，已经开发了一种人体数据收集协议并进行了试点测试。作为后续步骤，目前的项目将进一步验证研究协议与更大的加拿大司机样本。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。这项研究还将有助于解决与驾驶安全有关的研究问题。例如，如何确定驾驶员的关键行为对驾驶安全的影响？

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?