DarNet: A Deep Learning Solution for Distracted Driving Detection

Abstract Distracted driving is known to be the leading cause of motor vehicle accidents. With the increase in the number of IoT devices available within vehicles, there exists an abundance of data for monitoring driver behavior. However, designing a system around this goal presents two key challenges - how to concurrently collect data spanning multiple IoT devices, and how to jointly analyze this multimodal input. To that end, we present a uniied data collection and analysis framework, DarNet, capable of detecting and classifying distracted driving behavior. DarNet consists of two primary components: a data collection system and an analytics engine. Our system takes advantage of advances in machine learning (ML) to classify driving behavior based on input sensor data. In our system implementation, we collect image data from an inward facing camera, and Inertial Measurement Unit (IMU) data from a mobile device, both located within the vehicle. Using deep learning techniques, we show that DarNet achieves a Top-1 classiication percentage of 87.02% on our collected dataset, signiicantly outperforming our baseline model of 73.88%. Additionally, we address the privacy concerns associated with collecting image data by presenting an alternative framework designed to operate on down-sampled data which produces a Top-1 classiication percentage of 80.00%.
  • Christopher Streifer
  • Ramya Raghavendra (IBM US)
  • Mudhakar Srivatsa (IBM US)
  • Theophilus Benson
Date Dec-2017
Venue ACM/IFIP/USENIX Middleware 2017