A New Method of Trajectory Restoration at Intersection
Abstract: 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. Butthere 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 builds an error recognition model and an
adjustment algorithm. Experiments showed that this method can improve accuracy
of trajectory restoration and its performance is better than existing method.
Thus, the proposed method is practical for further data mining.
Author: Zheng Ke
Journal Code: jptkomputergg150035
