Yawn Detection for Driver's Drowsiness Prediction using Bi-Directional LSTM with CNN Features

Downloads

Downloads per month over past year

Saurav, S and Mathur, S and Sang, I and Prasad, SS and Singh, S (2019) Yawn Detection for Driver's Drowsiness Prediction using Bi-Directional LSTM with CNN Features. In: 11th International Conference on Intelligent Human Computer Interaction (IHCI-2019), December 12-14, 2019, IIT, Jodhpur, Rajasthan, India.

[img]
Preview
PDF
Download (5Mb) | Preview

Abstract

Drowsiness of drivers is a critical problem and has recently attracted a lot of attention from both academia and industry. A real-time driver's drowsiness detection system is often considered as a crucial component of the Advanced Driver Assistance System (ADAS). Although, there are a number of physical parameters associated with drowsiness like blink frequency, eye closure duration, pose, gaze, etc., yawing can also be used as an indicator of drowsiness. This work presents a novel deep learning-based framework for driver's drowsiness prediction based on yawn detection in a video stream. The proposed approach uses a combination of a convolutional neural network (CNN), 1D-CNN, and bi-directional LSTM (Bi-LSTM) network. In the first step, the pipeline extracts the mouth region from each frame of the video using a combination of face and landmark detector. In the subsequent step, spatial information from the mouth region is extracted using a pre-trained deep convolutional neural network (DCNN). Finally, sequential information which models the evaluation of yawn using the extracted mouth feature is learned using a blend of 1D-CNN and bi-directional LSTM (Bi-LSTM) network. Experiments were performed on manually extracted and annotated video clips obtained from two publically available drowsiness detection dataset namely YAWDD and NTHU-DD. Experimental results show the effectiveness of the pro-posed approach both in terms of recognition accuracy and computational efficiency. Thus, the proposed pipeline is a good candidate for real-time implementation on an embedded device.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Drowsiness detection; convolutional neural networks; long short-term memory (LSTM); bi-directional LSTM (Bi-LSTM).
Subjects: Electronic Systems > Digital Systems
Divisions: Electronic Systems
Depositing User: Mr. Jitendra Nath Bajpai
Date Deposited: 10 Sep 2021 11:31
Last Modified: 10 Sep 2021 11:31
URI: http://ceeri.csircentral.net/id/eprint/528

Actions (login required)

View Item View Item