Map matching refers to the correct matching of GPS positioning coordinates onto the roads of a digital map.Offline map matching is to find the real path of vehicle traveling from recorded and stored trajectory data.Sampling frequency and complex road network are the two most important factors affecting the correctness of map matching.In order to improve the correctness of existing hidden Markov model map matching algorithms on complex road networks,this paper proposes a segment verification matching method(SV algorithm).Considering that there will be k candidate paths for each sub-trajectory,a fitness degree is introduced to judge the degree of match between the candidate path and the trajectory,and the candidate path with the highest fitness degree is selected as the local best matching path.Furthermore,the proposed algorithm also takes into account the angle difference between the direction of the road segment and the direction of vehicle travel,as well as the speed limitations of the road segment,and filters candidate road segments and points through these constraints to improve efficiency of algorithm.
国家科技期刊平台
NSTL
万方数据
