Ride-Sharing Driver’s Assistant

• Chengkang Shen
• Peiyan Wang
• Kai Yan
• Chaoyue Zhao

Advisor: Vladimir Goncharoff, PhD

In today’s society, automobiles have become an indispensable part of life for both business and pleasure. Because of the many hours worked, fatigue presents a great danger to ride-sharing drivers. Owing to that, our group aims to design a device that provides useful feedback by evaluating driver status and surroundings. It also offers a digital record-keeping to assist the professional driver. In order to carry out these functions, there is a camera mounted on the rear-view mirror that continuously captures images of the driver’s face and sends them to a dedicated computer for analysis. We have applied the tools of deep learning, neural networks, and feature detection to estimate the driver’s current state of alertness. Additionally, we use another camera for road detection. To that end, we combine lane line detection and face detection to get a gradient judgment. When a dangerous condition is detected, the driver will be alerted by lively music and audio announcements with different degrees. Furthermore, our system can also keep a GPS log of driving times and locations for those professional drivers who need this service. Finally, we build a security system that if a stranger starts the car, a text message will be sent to the owner’s phone.

See supporting documentation in the team’s Box drive.