Analysis of Rear-End Collision Accident of Urban Traffic Based on Safety Pre-Warning Algorithm

Abstract

With the increase of per capita car ownership, traffic accidents frequently occur, in which rear-end collision accounts for 30% to 40% of the total accidents; thus, rear-end collision has become the primary factor of traffic environment deterioration. Therefore, how to improve road traffic safety and reduce the probability of rear-end collision has become a major social concern. In this study, based on the safety pre-warning algorithm, a vehicle collision model was built, and a vehicle anti-collision warning system was established. The calculation was performed based on the sample data to obtain the prediction value of vehicle collision time under different driving speeds, so as to provide drivers with effective response time and reduce the casualties and property losses caused by a vehicle collision. The experimental results showed that the accuracy rate of the pre-warning reached 80% when the speed was regarded as a variable, and the simulation results showed that the early pre-warning or delayed pre-warning rate was very low, and the timeliness rate reached 89%, which enables drivers to react quickly in the appropriate time and effectively reduces the risk of vehicle rear-end collision.

Accident Detection and Flow Prediction for Connected and Automated Transport Systems

“…As shown in Figure 1, we divide a lane into a number of overlapping grids with a unit length of L grid and adjacent interval of dg. According to the analysis result of the density of queued vehicles under diferent trafc conditions, the length of the unit L grid is determined to be the sum of the body length of fve vehicles and the minimum safety car-following distance d min in free fow, which in the urban road condition is 22.8 m [19], while in the highway condition is 127.2 m [20]. Considering that the vehicle length is generally less than 5.0 m, the length of the state detection unit L grid for urban road and the highway conditions is set to be 139.0 m and 661.0 m, respectively.…”

Research on optimization of subway operating schedule based on case database

“…In recent years, with the development of case-based reasoning technology, it has been widely used in the field of transportation [6]. Through case reasoning, the existing case data of subway operation energy consumption schedule is analyzed, and the subway operation energy consumption model is formed.…”