Warwick-JLR Driver Monitoring Dataset (DMD): A public Dataset for Driver Monitoring Research

Driving is a safety critical task that requires the full attention of the driver. Despite this, there are many distractions throughout a vehicle that can impose extra workload on the driver, diverting attention from the primary task of driving safely. If a vehicle is aware that the driver is currently under high workload, the vehicle functionality can be changed in order to minimize any further demand. Traditionally, workload measurements have been performed using intrusive means such as physiological sensors. We propose to monitor workload online using readily available and robust sensors accessible via the vehicle’s Controller Area Network (CAN). The purpose of this paper is to outline a protocol to collect driver monitoring data and to announce the publication of a database for driver monitoring research. We propose five ground truths, namely, timings, Heart Rate (HR), Heart Rate Variability (HRV), Skin Conductance Level (SCL), and frequency of Electrodermal Responses (EDR). The dataset will be released for public use in both driver monitoring and data mining research.