Construction Area Identification Method Based on Spatial-Temporal Trajectory of Slag Truck

Abstract

The enclosure construction is easy to cause traffic congestion in the process, so timely determination of it is crucial to alleviate traffic congestion. At present, most existing methods are either susceptible to obstacles such as clouds and fog, or only suitable for small-scale areas. To address these problems, this paper proposes an effective automatic identification method, which mines the spatial-temporal trajectory data of common engineering vehicles such as slag trucks to automatically determine the construction area. To reduce the memory consumption and the influence of the two parameters e (field radius) and MinPts (domain density threshold) on the clustering results, we first divide the trajectory points, match them to the grid and generate cluster candidate sets by extracting High-density grid base on the preset density threshold. Then, the DBSCAN algorithm is used to identify the construction areas, which greatly shorten the running time. The experimental results show that the method is effective through the verification of ArcGIS & Google Earth.