Driver Identity Recognition Based on Curved Handprints on Steering Wheel

Identity recognition of drivers is important for improving vehicle security and driving safety, especially in truck transportation. Continuous tracking of driver identity can prevent unauthorized drivers to take over the control of the truck, as well as detect whether drivers have changed shifts within their maximum allowed driving duration. The identification method also needs to be non-intrusive to reduce distractions for the driver. In this paper, we propose a system that analyzes real-time handprints on the steering wheel to recognize a driver’s identity. We present a novel mapping algorithm that matches planar handprints to curved ones. Then we use the matching result to perform identity recognition. We demonstrate this system using handprint data collected from 47 subjects. In addition, we analyze how feature matching of curved handprints are affected by the diameter of the steering wheel.