Real Time Pedestrian Protection System: Pedestrian Environmental Awareness Detection and Augmented Reality Warning System

Environmental awareness;Pedestrian safety;Pedestrian protection;Warning system;Augmented reality;Heart rate variability;Industrial and operations engineering;Industrial and Systems Engineering, College of Engineering & Computer Science

Tong, YouruiKim, Sang-Hwan ;

University of Michigan

关键词: Environmental awareness;    Pedestrian safety;    Pedestrian protection;    Warning system;    Augmented reality;    Heart rate variability;    Industrial and operations engineering;    Industrial and Systems Engineering, College of Engineering & Computer Science;   

Others  :  https://deepblue.lib.umich.edu/bitstream/handle/2027.42/145590/thesis%20v6.pdf?sequence=1&isAllowed=y

瑞士|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

To improve the safety of the pedestrians via V2X communications, it is important to detect pedestrians;; environmental awareness and give warnings to those with low environmental awareness. Based on the characteristics of pedestrians, a real-time algorithm was developed to detect pedestrians;;environmental awareness, then an Augmented Reality (AR) warning system was developed to carry out the warning to the pedestrians who have low environmental awareness. In this study, the heart rate variability (HRV) analysis and phone position analysis were used to understand the mental state and distractions of pedestrians, the projection method was used to develop the AR warning system.The HRV analysis was used to detect the fatigue and alert states of the pedestrians, and the phone position was used to define the phone distractions of the pedestrians. Support Vector Machines (SVM) algorithms were used to classify the pedestrians;; mental state. After the user analysis, the AR warning system was developed based on the perspective projection method. After the data collection and experiment, the results show that the accuracy of the pedestrian state detection was about 85%for the mental state detection and 100% for the phone position detection. Also,the AR warning system works well for to carry out the warning to the pedestrian.