Multi-Sensor Soft-Computing System for Driver Drowsiness Detection
Advanced sensing systems, sophisticated algorithms and increasing computational resources continuously enhance active safety technology for vehicles. Driver status monitoring belongs to the key components of advanced driver assistance system which is capa
- PDF / 636,970 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 8 Downloads / 233 Views
Abstract Advanced sensing systems, sophisticated algorithms and increasing computational resources continuously enhance active safety technology for vehicles. Driver status monitoring belongs to the key components of advanced driver assistance system which is capable of improving car and road safety without compromising driving experience. This paper presents a novel approach to driver status monitoring aimed at drowsiness detection based on depth camera, pulse rate sensor and steering angle sensor. Due to NIR active illumination depth camera can provide reliable head movement information in 3D alongside eye gaze estimation and blink detection in a non-intrusive manner. Multi-sensor data fusion on feature level and multilayer neural network facilitate the classification of driver drowsiness level based on which a warning can be issued to prevent traffic accidents. The presented approach is implemented on an integrated soft-computing system for
L. Li (&) K. Werber C. F. Calvillo K. D. Dinh A. König TU Kaiserslautern, Department of Electrical and Computer Engineering, Institute of Integrated Sensor Systems, Erwin-Schrödinger-Str. Gebäude 12, 67663 Kaiserslautern, Germany e-mail: [email protected] K. Werber e-mail: [email protected] C. F. Calvillo e-mail: [email protected] K. D. Dinh e-mail: [email protected] A. König e-mail: [email protected] A. Guarde Faculty of Engineering of Bilbao, University of the Basque Country, Bilbao, Spain e-mail: [email protected]
V. Snášel et al. (eds.), Soft Computing in Industrial Applications, Advances in Intelligent Systems and Computing 223, DOI: 10.1007/978-3-319-00930-8_12, Springer International Publishing Switzerland 2014
129
130
L. Li et al.
driving simulation (DeCaDrive) with multi-sensing interfaces. The classification accuracy of 98:9 % for up to three drowsiness levels has been achieved based on data sets of five test subjects with 588-min driving sequence.
1 Introduction Drowsy driving is a serious problem that can affect anyone on the road. It was a major factor in 20 % of all accidents in the United States in 2006 according to the report of National Highway Traffic Safety Administration (NHTSA). A study by the Federal Highway Research Institute (BASt) in Germany showed that drowsy driving was the second most frequent cause of serious truck accidents on German highways. Due to severe damage caused by drowsy truck or bus drivers it is urgent to extend active safety to cope with driver drowsiness in commercial vehicles. Driver Assistance Systems, in general, have been on the agenda of automotive and related industry for nearly two decades now. For instance, in the Electronic Eye [1] research program of the German Federal Ministry of Education and Research (BMBF), the topic had been pursued in the mid nineties, focusing both on CMOS sensing with high-dynamic range and high-speed as well as dedicated massively parallel digital computation platforms for applications, such as SleepEye-Detectors or Overtake-Monitors (OTM) [2]. Advanced Dri
Data Loading...
