Research and Application of Video Feature Reference Layout for Road Traffic Accident Reconstruction
Objective In order to solve the problem of feature reference selection and placement caused by changes in the position of surveillance cameras in video speed identification,a feature reference layout method for road traffic accident reconstruction is proposed using image homography.Methods Firstly,we examined the road surveillance video cameras and roughly determined the location of feature placement.Secondly,we set up feature references on site and use drones/cameras to obtain on-site photos containing feature references.Thirdly,we solved the homography matrix and converted on-site photos into surveillance visual angles.Finally,we completed the fusion and matching of on-site photos and surveillance videos.Results The deployment of feature reference in surveillance videos was realized,and the effectiveness of the video feature reference layout for road traffic accident reconstruction was verified.Conclusion This method can be used in the forensic identification of vehicle driving speed and determining the driving boundary with position changed surveillance cameras,and can effectively serve the road traffic accident investigation and identification work using video images.