D-Cubed: detection of driver drowsiness for cognivue based system

美国国家公路交通安全管理局（NHTSA）指出，在昏睡状态下驾驶是导致22%至24%的车祸的原因，与在清醒状态下驾驶相比，其导致的近碰撞/碰撞风险高出4至6倍。这种高事故率是由于昏昏欲睡的司机在碰撞前没有采取正确的行动。因此，使用辅助系统监测驾驶员的警觉水平，并在驾驶员困倦或注意力不集中的情况下提醒驾驶员，对预防事故具有重要意义。这项提案的目标是与我们的行业合作伙伴Cognivue Corp.合作，研究、设计和实现一个系统的原型，该系统通过监测驾驶员并根据嘴的几何形状和运动识别打哈欠来检测驾驶员的睡意。Cognivue在汽车摄像头系统方面有产品线，Cognivue APEXTM，这是一个可编程的嵌入式平台，提供多摄像头解决方案

The U.S. National Highway Traffic Safety Administration (NHTSA) has indicated that driving while drowsy is the cause of 22 to 24 percent of car crashes, and results in a four- to six-times higher near-crash/crash risk compared to driving while alert. This high accident rate is due to the fact that sleepy drivers fail to take correct actions prior to a collision. Therefore, the use of assisting systems that monitor a driver's level of vigilance and alert the driver in the case of drowsiness or inattention can be of significant importance in the prevention of accidents. The goal of this proposal is to team up with our industry partner, Cognivue Corp., to study, design, and implement the prototype of a system to detect driver drowsiness by monitoring the driver and recognizing yawning based on mouth geometry and movements. Cognivue has a product line in Automotive Camera systems, CogniVue APEXTM, which is a programmable embedded platform offering multi-camera solutions