Trajectory processing method, device, electronic equipment and medium

Abstract

The embodiment of the present application discloses a trajectory processing method, device, electronic equipment and medium, which are applied in the technical field of computer vision. The methods include: obtaining the track to be processed, dividing the track to be processed into multiple track segments to be processed, dividing the track segments to be processed into one or more track groups according to the target grouping rules, and obtaining the exceptions in each track group According to the deletion loss value of the trajectory segment and the abnormal trajectory segment, target management is performed on the abnormal trajectory segment in each trajectory group according to the deletion loss value, and at least one target trajectory group is obtained. By adopting the embodiment of the present application, abnormal trajectory segments can be effectively processed during the trajectory segmentation process.

Description

technical field

[0001] The present application relates to the technical field of computer vision, and in particular to a trajectory processing method, device, electronic equipment and media. Background technique

[0002] At present, when using smart devices to collect GPS trajectories for road update, or when using trajectory data to mine real-world laws, the trajectories need to be processed first, and an important step in the processing is to segment the trajectories. The existing trajectory segmentation methods are mainly divided into: segmentation methods based on supervised classification, segmentation methods based on unsupervised classification, segmentation methods based on semantics, and segmentation methods based on time segments. However, the inventors have found in practice that the existing trajectory segmentation methods cannot handle abnormal trajectory segments well after segmenting the trajectory, which in turn affects the efficiency and quality of the segme...

Images