Masahiro Miyaji

Driver's cognitive distraction detection using physiological features by the adaboost

Effects of drivers states adaptive driving support systems is highly expected for the prevention of traffic accidents. In order to create this constituent technology, detecting drivers psychosomatic states which occurs just before a traffic accident is essential. Therefore drivers distraction is thought as one of important factors. This study focused on detecting drivers cognitive distraction, a state which can easily lead to a traffic accident. We reproduced the cognitive distraction by imposing conversation or arithmetic loads to the subjects on a driving simulator. A stereo camera system were used as the means to track a subjects eyes, and head movements, which were set as classification features for pattern recognition on the Support Vector Machine (hereafter, SVM) basis used in the previous study of the AIDE project, a part of EU 6th Framework Programme. Diameter of pupil as well as the interval between heart R-waves (hereafter, heart rate RRI) from an ECG (electrocardiogram) were added for classification features to further improve the accuracy of drivers cognitive distraction detection. Based on this study, we established the methodology for more precise and faster drivers cognitive detection by using the AdaBoost.

Driver’s cognitive distraction detection using AdaBoost on pattern recognition basis

Detecting the mental and physical states which occur in a driver immediately before a traffic accident and then providing information to or warning the driver is an effective means of reducing traffic accidents. This study is focused on driver distraction, a state which can easily lead to traffic accidents, and reproduced this distraction in a driving simulator by providing conversation or arithmetic tasks to the subjects. Stereo cameras were used as the means to track subjectspsila eye and head movements. These movements were tracked and their standard deviations were set as classification features of pattern recognition, and the AdaBoost method was used to detect subject distraction. The interval between heart R-waves was also added as a classifier feature, in order to improve cognitive distraction detection performance. The results were then compared with the SVM method from the AIDE Project, which was carried out as part of the EU 6th Framework Programme.

Effect of pattern recognition features on detection for driver's cognitive distraction

Constituent technology of a driver monitor system using information of a drivers psychosomatic states is expected to create drivers states adaptive drive supporting system for the reduction of traffic accidents. In this study we identified a drivers distraction as one of major psychosomatic states which may result in a traffic accident by using Internet based survey on a questionnaire basis. Then we aimed at creating a methodology in use for detecting drivers cognitive distraction by means of using the AdaBoost which is capable of rapid and accurate classification. Furthermore we verified an effect of pattern recognition features such as interval between heart R-waves (hereafter, heart rate RRI) from an ECG (electrocardiogram), pupil diameter, and, gaze angle and head rotation angle.

Study on the reduction effect of traffic accident by using analysis of Internet survey

Traffic fatalities and injuries in Japan have declined for twelve years by the comprehensive counter-measure for the reduction of traffic accidents. The efforts include enhancement of vehicle safety performance in both passive and preventive safety area. With regard to passive safety, major reduction effect was brought by airbag system, seat belt and crashworthiness of vehicle. For further reduction of the traffic accident, preventive safety may play more important role. Recently drivers psychosomatic state adaptive driving support safety system has been highlighted to reduce the traffic accident. For that reason reduction effect of psychosomatic adaptive safety function should be clarified to foster its penetration into the market. Statistical analysis of the traffic incident is highly expected to evaluate the reduction effect of the traffic accident of psychosomatic adaptive safety function. To execute the challenge, this study introduced Internet survey by delivering questionnaires to respondents. From the analysis of the collected answer, major psychosomatic state of driver is hasty and distraction. As a first step this study focused drivers distraction, which may cause severe traffic accidents. By using pattern recognition, the detection accuracy of drivers distraction was acquired. The reduction effect of the drivers distraction in the traffic accident was estimated by referring the reduction rate of both ASV (Advanced Safety Vehicle) and Intelligent Transportation Systems.

Data mining for safety transportation by means of using Internet survey

Internet survey may be one of the effective means to collect big data from the real world. Collected data may realize meaningful analysis of targeted field. Intelligent Transportation (hereinafter: ITS) is one of smart city applications which bring us safety driving as well as comfortable driving by mitigation of the traffic congestion. This study proposes an example of vehicle-infrastructure cooperative function which would be incorporate into vehicle safety system for smart city application. Drivers state adaptive driving support safety function may be one of key functions that can bring road traffic safety in combination with road infrastructure interactively. Consequently this study clarified root cause of traffic accidents by analysing data of experiences on traffic incidents. Data was collected by two methods, one was collected through direct interview, and the other was collected through Internet. From the analysis, haste, distraction were major factor of a drivers psychosomatic states just before traffic incidents. As an alternative characteristic of drivers cognitive distraction, this study acquired physiological information, which were movements of eyes and head, and heart rate. A method of detecting drivers cognitive distraction was established by using pattern recognition, which were AdaBoost and Error-Correcting Output Coding (ECOC). This study proposes drivers psychosomatic adaptive driving support safety function in combination with ITS service for smart city applications.

Study on psychosomatic features of driver's distraction based on pattern recognition

Drivers distraction is said as one of major psychosomatic factors which may prone to be involved in traffic accidents. Therefore it is much expected to prevent traffic accidents by means of incorporating a function of driver state monitoring into a driving support system. In our previous study, we identified the methodology for detecting drivers cognitive distraction in higher degree of accuracy by means of using the AdaBoost as pattern recognition algorithm. We used visual features such as gaze direction and head rotation angle, pupil diameter and heart rate RRI as physiological features. In this study we aimed at clarifying the degree of influence for detecting drivers distraction by four recognition features, which are gaze angle and head rotation angle (hereinafter; vision information), pupil diameter and the interval between heart R-waves (hereinafter; heart rate RRI) in order to create a drivers state monitoring function.

Reduction effect of traffic accidents by driver's psychosomatic state monitoring function

Traffic fatalities and injuries in Japan have declined for fourteen years by comprehensive counter-measures. One of efforts has included enhancement of vehicle safety performance in passive and preventive safety. Pertaining to passive safety, major reduction effect has been brought by airbag systems, seat belts and crashworthiness of vehicles. To further reduce the traffic accident, preventive safety may play more important role. Recently drivers psychosomatic state adaptive driving support safety function has been highlighted to further reduce the number of traffic accident. Accordingly reduction effect of psychosomatic adaptive driving support safety function should be clarified to foster its penetration into the market. Statistical analysis of the traffic incident is highly expected to evaluate reduction effect of the traffic accident. In this study experiences of traffic incidents was analyzed by using the data collected through Internet. From the results this study focused drivers distraction, which may cause severe traffic accidents. By using pattern recognition, detection accuracy of drivers cognitive distraction was acquired. Reduction rate by using function of drivers distraction detection was estimated by referring the reduction rate of both Advanced Safety Vehicle and Intelligent Transportation Systems.

Method of Driver State Detection for Safety Vehicle by Means of Using Pattern Recognition

Evolution of preventive safety devices for vehicles is highly expected to reduce the number of traffic accidents. Driver’s state adaptive driving support safety function may be one of solutions of the challenges to lower the risk of being involved in the traffic accident. In the previous study, distraction was identified as one of anormal states of a driver by introducing the Internet survey. This study reproduced driver’s cognitive distraction on a driving simulator by imposing cognitive loads, which were arithmetic and conversation. For classification of a driver’s distraction state, visual features such as gaze direction and head orientation, pupil diameter and heart rate from ECG were employed as recognition features. This study focused to acquire the best classification performance of driver’s distraction by using the AdaBoost, the SVM and Loss-based Error-Correcting Output Coding (LD-ECOC) as classification algorithm. LD-ECOC has potential to further enhance the classification capability of the driver’s psychosomatic states. Finally this study proposed next generation driver’s state adaptive driving support safety function to be extendable to Vehicle-Infrastructure cooperative safety function.

Effect on hasty state for driver's visual perception

Drivers hasty state is one of major psychosomatic states which may result in traffic accidents. This paper describes an effect on hasty state as to drivers perception by means of detecting the change of drivers useful view of field and time to perception of a moving object. Hasty state was reproduced by means of using a scenario of traffic incidents in rush operation on a driving simulator basis. A stereo camera based tracking unit was used for measurement of movement of drivers eyes and head while driving ahead in traffic incidents occurring situation. It was clarified that drivers useful field of view had decreasing tendency, meanwhile time to percept to the moving object was prolonged when subjects operated rush driving to a destination. Finally we propose a concept to provide information on psychosomatic states to a driver was in order to lower a potential risk to be involved in a traffic accident.

Study for the effect of hasty state while driving on potential risks

Drivers hasty state is one of psychosomatic states which may result in traffic accidents. This paper describes analytical effects on hasty state for drivers perception by means of detecting the change of drivers useful view of field and time to perception of moving objects. Then we proposed a concept of a function for detecting drivers hasty states for an intelligent driving support system. The function may become one of the content of the next generation Vehicle - Infrastructure cooperative safety system by means of using ultra high speed communication technology in the next stage.