# Enhancing Driver Monitoring Systems Based on Novel Multi-Task Fusion Algorithm

## TL;DR

This paper introduces a new driver monitoring system that uses a multi-task fusion algorithm to better detect driver distraction and improve road safety.

## Contribution

A novel multi-task fusion algorithm is proposed to enhance driver attention assessment using multi-perspective data.

## Key findings

- The multi-perspective monitoring approach improves distraction detection accuracy compared to single-perspective systems.
- The multi-task fusion algorithm enables stable and adaptive classification of driver distraction with fewer false positives.

## Abstract

What are the main findings?
A multi-perceptive and multi-task driver monitoring model is developed.A multi-task fusion algorithm for determining if the driver is attentive enough to drive safely is developed.

A multi-perceptive and multi-task driver monitoring model is developed.

A multi-task fusion algorithm for determining if the driver is attentive enough to drive safely is developed.

What are the implications of the main findings?
Improved distraction detection accuracy: The multi-perspective monitoring approach outperforms traditional single-perspective systems, providing a more comprehensive and accurate assessment of driver tasks being performed and attention level.Real-time aggregation and decision-making: The multi-task fusion algorithm allows for stable and adaptive driver distraction classification, reducing false positives and improving response accuracy.

Improved distraction detection accuracy: The multi-perspective monitoring approach outperforms traditional single-perspective systems, providing a more comprehensive and accurate assessment of driver tasks being performed and attention level.

Real-time aggregation and decision-making: The multi-task fusion algorithm allows for stable and adaptive driver distraction classification, reducing false positives and improving response accuracy.

Distracted driving continues to be a major contributor to road accidents, highlighting the growing research interest in advanced driver monitoring systems for enhanced safety. This paper seeks to improve the overall performance and effectiveness of such systems by highlighting the importance of recognizing the driver’s activity. This paper introduces a novel methodology for assessing driver attention by using multi-perspective information using videos that capture the full driver body, hands, and face and focusing on three driver tasks: distracted actions, gaze direction, and hands-on-wheel monitoring. The experimental evaluation was conducted in two phases: first, assessing driver distracted activities, gaze direction, and hands-on-wheel using a CNN-based model and videos from three cameras that were placed inside the vehicle, and second, evaluating the multi-task fusion algorithm, considering the aggregated danger score, which was introduced in this paper, as a representation of the driver’s attentiveness based on the multi-task data fusion algorithm. The proposed methodology was built and evaluated using a DMD dataset; additionally, model robustness was tested on the AUC_V2 and SAMDD driver distraction datasets. The proposed algorithm effectively combines multi-task information from different perspectives and evaluates the attention level of the driver.