Design of Fatigue Driving Detection Algorithm Based on Image Processing
One of the primary causes of traffic accidents is drowsy of the drivers involved. A warning system about drowsy status (fatigue or drowsiness) of the driver, helping to limit the traffic accidents caused by falling asleep behind the wheel by determining t
- PDF / 1,323,587 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 34 Downloads / 296 Views
2
Nanyang Institute of Technology, Nanyang 473004, Henan Province, People’s Republic of China [email protected] School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo 454000, Henan Province, People’s Republic of China [email protected]
Abstract. One of the primary causes of traffic accidents is drowsy of the drivers involved. A warning system about drowsy status (fatigue or drowsiness) of the driver, helping to limit the traffic accidents caused by falling asleep behind the wheel by determining the status of the eyes combined with the status of mouth. In this paper, we present a novel approach for determining the facial landmarks. Besides, we proposed an algorithm to detect and identify the status of eye and mouth. Testing results confirms the effectiveness and feasibility of the proposed algorithm.
Keywords: Fatigue detection
1
· Fatigue driving · Image processing
Introduction
Driving safety is influenced by two key factors: 1) the mental states of the driver 2) the external environment. Various psychological conditions, e.g., fatigue, distraction and motion sickness can affect driving safety. Fatigue driving has a close relation with traffic accidents such as collision, personal injury and so on. Investigations show that up to 37% of all vehicle fatalities involve a fatigue driving or drowsy driving in the United States [1,2]. In Europe, drowsy driving contributes to one fourth to one third of road accidents [3]. Some researchers found that fatigue driving has been estimated to be involved in 2% to 23% of all crashes [4]. The degradation in driving performance because of fatigue accounts for a small, but significant, percent of highway accidents [5,6]. The growing number of accidents caused by fatigue driving has been becoming a serious societal problem in recent years. Therefore, it is of great significance to detect fatigue driving and to develop an efficient intervention for driving mental fatigue not only to reduce the social cost of traffic safety but also to improve the health of drivers and passengers. c The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021 Y. Jia et al. (Eds.): CISC 2020, LNEE 706, pp. 602–610, 2021. https://doi.org/10.1007/978-981-15-8458-9_64
Fatigue Driving Detection Algorithm
603
Fatigue driving detection measures include subjective evaluation method and objective evaluation method. The objective method can be categorized into: 1) evaluation of biomedical signals including pulse rate, EEG, changes of head position, eye-closure rate, and eyelid movement; 2) evaluation of driver–vehicle data, including steering angle, throttle/brake input, and speed. The major drawback of the techniques based on biomedical signals is that they require directly placing sensors on the driver’s body. This will make the driver feel uncomfortable. Methods based on driver-vehicle data are prone to be affected by driving habits of drivers as well as size and shape of vehicles.
2 2.1
Face Landmark Detection Based on Classi
Data Loading...
