Spiking-DD: Neuromorphic Event Camera based Driver Distraction Detection with Spiking Neural Network

TL;DR

This paper introduces Spiking-DD, a novel driver distraction detection system using event camera data and spiking neural networks, achieving state-of-the-art accuracy with fewer parameters and enhanced efficiency.

Contribution

First to utilize event camera data with spiking neural networks for driver distraction detection, demonstrating improved performance and efficiency.

Findings

Achieves state-of-the-art accuracy in driver distraction detection.

Uses fewer parameters than existing event-based methods.

Provides rapid, low-latency, and power-efficient detection.

Abstract

Event camera-based driver monitoring is emerging as a pivotal area of research, driven by its significant advantages such as rapid response, low latency, power efficiency, enhanced privacy, and prevention of undersampling. Effective detection of driver distraction is crucial in driver monitoring systems to enhance road safety and reduce accident rates. The integration of an optimized sensor such as Event Camera with an optimized network is essential for maximizing these benefits. This paper introduces the innovative concept of sensing without seeing to detect driver distraction, leveraging computationally efficient spiking neural networks (SNN). To the best of our knowledge, this study is the first to utilize event camera data with spiking neural networks for driver distraction. The proposed Spiking-DD network not only achieve state of the art performance but also exhibit fewer parameters and provides greater accuracy than current event-based methodologies.