A Method for Identifying Fatigue State of Driver's Face Based on Improved AAM Algorithm

A Method for Identifying Fatigue State of Driver's Face Based on Improved AAM Algorithm

Zuojin Li, Jun Peng, Liukui Chen, Ying Wu, Jinliang Shi
DOI: 10.4018/978-1-7998-0414-7.ch070
(Individual Chapters)
No Current Special Offers


The change of lighting conditions and facial pose often affects the driver's face's video registration greatly, which affects the recognition accuracy of the driver's fatigue state. In this paper, the authors first analyze the reasons for the failure of the driver's face registration in the light conditions and the changes of facial gestures, and propose an adaptive AAM (Active Appearance Model) algorithm of adaptive illumination and attitude change. Then, the SURF (speeded up robust feature) feature extraction is performed on the registered driver's face video images, and finally the authors input the extracted SURF feature into the designed artificial neural network to realize the recognition of driver's fatigue state. The experimental results show that the improved AAM method can better adapt to the driver's face under the illumination and attitude changes, and the driver's facial image's SURF feature is more obvious. The average correct recognition rate of the driver's fatigue states is 92.43%.
Chapter Preview

2. Method

2.1. Overview

This method describes the whole process of driver facial fatigue recognition based on video images. In the real vehicle driving condition, the intensity of the driver's facial image is greatly affected by the change of lighting and its position, which makes the face registration of the driver's video image poorly robust. The Active Aesthetic Model (AAM) is one of the classical algorithms for the feature extraction of facial features (Iain & Simon, 2004; Suo, Zhang & Sun, 2013). In this paper, the popular method of facial feature localization, AAM, is applied to the facial registration of drivers and the reasons for the influence of illumination variation on AAM algorithm are analyzed, and an improved AAM algorithm is proposed. Then, the SIFT feature extraction is performed on the registered face video images. As when the driver is in the fatigue state, the driver's eyes are often closed, based on this fatigue characteristic, the driver's fatigue state identification is realized with the designed artificial neural network. The whole process of the method is as shown in Figure 1.

Figure 1.

The flowchart of proposed method based on improved AAM


Complete Chapter List

Search this Book: