Chapter 6 - Application of Deep Learning Methods in Driver Behavior Recognition

Abstract

Driver decisions and behaviors are essential factors that can affect driving safety. To understand the driver behaviors, a driver activities recognition system is designed based on the deep convolutional neural networks (CNNs) in this section different from the driver behavior recognition system designed in the last chapter. The driver behavior recognition models are end-to-end trainable without hand-crafted feature extraction. specifically, seven common driving activities are identified, which are the normal driving, right mirror checking, rear mirror checking, left mirror checking, using in-vehicle radio devices, texting, and answering the mobile phone, respectively. Among these activities, the first four are regarded as normal driving tasks, while the remaining three are classified as the distraction group. The experimental images are collected using a low-cost camera, and 10 drivers are involved in the naturalistic data collection. The raw images are segmented using the Gaussian mixture model to extract the driver's body from the background before training the behavior recognition CNN model. To reduce the training cost, the transfer learning method is applied to fine-tune the pretrained CNN models. Three different pretrained CNN models, namely AlexNet, GoogLeNet, and ResNet50, are adopted and evaluated. The detection results for the seven tasks achieved an average of 81.6% accuracy using the AlexNet, and 78.6% and 74.9% accuracy using the GoogLeNet and ResNet50, respectively. Then, the CNN models are trained for the binary classification task and identify whether the driver is being distracted or not. The binary detection rate achieved 91.4% accuracy, which shows the advantages of using the proposed deep learning approach. Finally, the real-world application is analyzed and discussed.