Vision-based approach for predicting the probability of vehicle–pedestrian collisions at intersections

Abstract The increase in public transportation in the last decade has resulted in a larger pedestrian population and hence a larger number of pedestrian collisions. In the past, car-pedestrian accident prevention had been a challenge for automotive and transport safety members. Recent reports in car-pedestrian accidents have influenced many improvements to prioritize pedestrian protection for automotive industries. The number of pedestrian fatalities in U.S has raised in last decade proportionally, Car manufacturers, and transport investigation teams are implementing new product designs and adding new development methods to reduce the risk of pedestrian collisions. In this study, adult headform and upper legform is tested with a finite element vehicle model to examine the simulation results and injury behavior during impact. All finite element simulation tests are produced under Euro-NCAP Committee regulations. Finite element models are configured as per the regulation’s and testing criteria. Both upper legform impactor and adult headform finite simulation results are tested with assessing criteria limits. Finite simulation tests are carried on the LS-DYNA – Code platform. This comparative study between sedan and pickup finite vehicle models gives an injury risk prediction of pedestrian safety and assesses design parameters of automotive industries.

Download Full-text

The system analysis and mathematical modeling road accidents in the metropolis

«System analysis and applied information science» ◽

10.21122/2309-4923-2019-1-4-8 ◽

2019 ◽

pp. 4-8

Author(s):

A. G. Davidovsky ◽

A. M. Linnik

Keyword(s):

Mathematical Modeling ◽

Traffic Safety ◽

System Analysis ◽

Safety Management ◽

Road Traffic ◽

Time Of Day ◽

Road Accidents ◽

Traffic Incidents ◽

Day Of The Week ◽

Pedestrian Collisions

The article presents the results of correlation analysis of the causes of road accidents in such a modern metropolis as Minsk. Has been identified the most frequent causes of road accidents, including pedestrian collisions caused by drivers, collisions at intersections, incidents at controlled and unregulated pedestrian crossings, as well as on the roadway. The dependence of transport incidents on the time of day, day of the week and month of the year was investigated. Shows the periods when road traffic incidents occur from 3.00 to 6.00 h, from 15.00 to 18.00 and from 21.00 to 24.00 on Monday, Friday and Sunday in January, March, June, September, October and November. Methods of correlation and multiple regression analysis can be the basis of preventive traffic safety management in a modern metropolis.

Download Full-text