Embedded System for Inattention Detection in Driving Task

Abstract

A common factor in road accidents is due to inattention in the driving task (drowsiness, distraction, etc.). Therefore, areas such as intelligent transportation systems are in continuous development to provide greater security. An example are the assistance systems that focus on improving occupant safety by merging information from sensors that recognize the environment, processing with methods and algorithms that detect risk situations that are addressed with the activation of actuators and/or recommendations to the driver. This article proposes an assistance system that detects the driver's inattention level and displays a series of alerts. The system obtains information through computer vision and performs the inference with fuzzy logic, the system is implemented on the embedded NVIDIA Jetson TX2 platform. Real-time experiments show that the proposed system is highly efficient to find drowsiness and alert the driver, obtaining a detection rate > 0.90 and a precision > 0.88.