A method of Trajectory Restoration at Intersection

Ke Zheng (School of Computer and Information Engineering, Nanyang Institute of Technology)
Xiangbo Song (Wuhan KOTEI Informatics Co., LTD.)
Dunyao Zhu (Wuhan KOTEI Informatics Co., LTD.)

TELKOMNIKA (Telecommunication Computing Electronics and Control)
Vol 13, No 2: June 2015

Floating car data (FCD) is vechiel’s position trace that is comes from Global Positioning System receivers.collected at the discrete time. FCD contains much information of traffic and road-network. But there are different level of trajectory shape damages because of the affection of sample frequency and running speed. So before the FCD mining, the first thing should be done is to restore track to make up for the loss. This paper analyzes the spatial-temporal characteristics of floating car trajectory at intersection, and build an error recognition model and a adjust algorithm. Experiments showed that this method can improve accuracy of trajectory restoration, and set a solid foundation for further data mining.