Moving object trajectory simplification algorithm based on feature selection

Abstract

The invention discloses a moving object trajectory simplification algorithm based on feature selection. The algorithm comprises the following steps of processing the trajectory data of a moving object by adopting a DBSCAN density clustering algorithm to obtain a velocity interval of a trajectory; dividing the trajectory of the moving object according to the speed interval to obtain a trajectory segment corresponding to the speed interval; performing feature analysis on each trajectory section, selecting a simplified algorithm, and performing simplified processing on the trajectory data of the trajectory section; and combining the simplification results of each trajectory segment to obtain a trajectory simplification result of the moving object. According to the moving object trajectory simplification algorithm based on feature selection provided by the invention, the trajectory segments are divided according to the speed features, and then the direction feature judgment or the distance feature judgment is performed in the trajectory segments, so that the simplification algorithm suitable for each trajectory segment is selected, the optimization of execution time and error measurement is realized, and the simplification effect is improved.

Description

technical field [0001] The invention belongs to the technical field of computer application and specifically designs a feature selection-based moving object track simplification algorithm. Background technique [0002] The research on the simplification algorithm of moving object trajectory is an important part of the research field of moving object database. It is gradually produced and developed along with the upgrading and popularization of mobile electronic products. Monitoring and traffic management, location-based social network (LBSN), route navigation trajectory recommendation, destination prediction and user behavior analysis and many other fields. [0003] GPS sensors in smartphones, in-vehicle navigation systems, and wearable devices usually generate a large amount of raw trajectories, increasing the cost of data storage, transmission, and data analysis. Trajectory data simplification and compression is a method to improve data transmission, storage and processin...

AI Technical Summary

Problems solved by technology

Most of the previous simplification algorithms relied on the geometric characteristics of the trajectory (such as the relationship between the position of the trajectory points, the relationship between the direction and angle of the trajectory points), these geometric characteristics can be displayed by the relative position of the trajectory points, and for the moving object Speed, an important characteristic, is not well studied

Images