Drive-Net: Convolutional Network for Driver Distraction Detection

TL;DR

Drive-Net is a new supervised learning approach combining CNN and random decision forests for accurately detecting driver distraction from images, outperforming other machine learning methods.

Contribution

The paper introduces Drive-Net, a novel CNN and random forest based model for driver distraction detection, demonstrating superior accuracy on a public dataset.

Findings

Drive-Net achieves 95% detection accuracy.

Outperforms RNN and MLP methods by 2%.

Validated on a publicly available, annotated image dataset.

Abstract

To help prevent motor vehicle accidents, there has been significant interest in finding an automated method to recognize signs of driver distraction, such as talking to passengers, fixing hair and makeup, eating and drinking, and using a mobile phone. In this paper, we present an automated supervised learning method called Drive-Net for driver distraction detection. Drive-Net uses a combination of a convolutional neural network (CNN) and a random decision forest for classifying images of a driver. We compare the performance of our proposed Drive-Net to two other popular machine-learning approaches: a recurrent neural network (RNN), and a multi-layer perceptron (MLP). We test the methods on a publicly available database of images acquired under a controlled environment containing about 22425 images manually annotated by an expert. Results show that Drive-Net achieves a detection accuracy of 95%, which is 2% more than the best results obtained on the same database using other methods