Automatic Traffic Accident Detection and Notification with Smartphones,
- JulesWhite, Chris Thompson, Hamilton Turner, Brian Dougherty, Douglas C. Schmidt, WreckWatch
- Mobile Netw Appl,
Traffic accidents negatively affect the lives of human beings. Accidents may result in deaths, severe injuries, and loss of income to the impacted families. Accident detection and prevention is a keystone in improving road safety. In this paper, a system for detecting vehicle collision and rollover is presented. The proposed system includes three key phases. Data acquisition where accelerometer and gyroscope, integrated into MPU-6050 motion sensor are used to acquire 3-axis acceleration forces and rotation angles respectively. The complementary filter is used to enable the use of the gyroscope data on the short term because it is very precise and not susceptible to external forces. On the long term, the accelerometer data is used because it does not drift. An algorithm for acquiring data using sensors, filtering and analyzing data, detecting collision and rollover is developed. Experiments are conducted to test the proposed system. Experiments show promising results.