Lightweight Driver Monitoring System Based on Multi-Task Mobilenets

Abstract

Research on driver status recognition has been actively conducted to reduce fatal crashes caused by the driver’s distraction and drowsiness. As in many other research areas, deep-learning-based algorithms are showing excellent performance for driver status recognition. However, despite decades of research in the driver status recognition area, the visual image-based driver monitoring system has not been widely used in the automobile industry. This is because the system requires high-performance processors, as well as has a hierarchical structure in which each procedure is affected by an inaccuracy from the previous procedure. To avoid using a hierarchical structure, we propose a method using Mobilenets without the functions of face detection and tracking and show this method is enabled to recognize facial behaviors that indicate the driver’s distraction. However, frames per second processed by Mobilenets with a Raspberry pi, one of the single-board computers, is not enough to recognize the driver status. To alleviate this problem, we propose a lightweight driver monitoring system using a resource sharing device in a vehicle (e.g., a driver’s mobile phone). The proposed system is based on Multi-Task Mobilenets (MT-Mobilenets), which consists of the Mobilenets’ base and multi-task classifier. The three Softmax regressions of the multi-task classifier help one Mobilenets base recognize facial behaviors related to the driver status, such as distraction, fatigue, and drowsiness. The proposed system based on MT-Mobilenets improved the accuracy of the driver status recognition with Raspberry Pi by using one additional device.

Lightweight Driver Behavior Identification Model with Sparse Learning on In-Vehicle CAN-BUS Sensor Data

“…for learning driver behavior [ 18 , 19 , 20 ] under complex situations such as those entailing goal-oriented action, stimulus-driven action, and cause-attention (e.g., stop a vehicle to let a pedestrian pass (cause) and analyze how the driver attends the situation (attention)). For the driver monitoring applications, several researchers have utilized camera video/image only [ 21 , 22 ]. Some other works employed physiological sensor data from bio-signals to identify a distracted driver [ 23 ].…”

Wind turbine tower detection using feature descriptors and deep learning

“…As indicated in Fig. 4, MobileNets are based on an architecture that uses depth wise separable convolutions to build lightweight deep neural networks [17,[39][40][41]. In [17], the authors introduced two simple global hyper-parameters that effectively compensate for latency and accuracy.…”

Gaze and Eye Tracking: Techniques and Applications in ADAS

“…It corresponds to the percentage of time during a one-minute period for which the eyes remain at least 70% or 80% closed. A driver's physical activities such as head movements are captured and processed in the ADAS applications [176][177][178][179]. The video cameras are installed inside the vehicle at suitable locations to record the driver's physical movements and gaze data.…”