Smartphone based fuzzy vehicle to pedestrian collision warning system

Nearly one third of accident casualties is related to pedestrians. Therefore pedestrian safety is one of the important transportation issues. For this purpose collision warning systems are mainly used. In this research, the necessary warnings are provided by computing and sending the vehicle and pedestrian smartphone positions, vehicle and pedestrian speeds, vehicle and pedestrian directions and vehicle acceleration to new fuzzy system. The proposed system includes three phases. In activation phase, the system according to position and trajectory of the vehicle and the pedestrians around the vehicle, is activated for the pedestrians in the activation area. In the second phase, detected pedestrians are monitored momentary to extract the effective collision parameters. And in the third phase, red level warning or yellow level warning is provided by fuzzification of effective parameters and accident risk analysis. The results show that activation of the system has 86 percent accuracy and warning or no warning situations are correctly detected in 95 percent of the cases. Also yellow warning and red warning accuracy was 62 and 100 percent.