A trajectory data processing method, device and computer-readable storage medium

Abstract

The present application discloses a track data processing method, device and computer-readable storage medium. The method relates to data transmission-related technologies in cloud technology. The method includes: acquiring face tracks and human body tracks in the detection area; The track correlation between the face track and the human body track in the area, bind the face track and the human body track in the detection area, and obtain the track binding pair; determine the human track that failed to be bound as the human track to be matched , according to the trajectory similarity between the human trajectory of the trajectory binding pair and the human trajectory to be matched, determine the user attributes that match the human trajectory to be matched; bind the user attributes that match the human trajectory to be matched with the human trajectory to be matched, The attribute binding pair is obtained; according to the attribute binding pair and the trajectory binding pair, the user traffic and user attributes in the detection area are determined. By adopting the present application, the accuracy of the acquired user traffic and user attributes in the detection area can be improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a trajectory data processing method, device, and computer-readable storage medium. Background technique [0002] In some large-scale shopping malls, it is often necessary to count the passenger flow in a certain monitoring area of ​​the mall and the corresponding passenger flow attribute of the passenger flow. The passenger flow attribute may be the age attribute or gender attribute of the passenger flow. [0003] In the prior art, the face images in the monitoring area are often captured, and the passenger flow in the monitoring area is determined by counting the captured face images, and can be determined by identifying the facial features in the face images. Obtain the passenger flow attribute corresponding to the passenger flow. [0004] However, in many cases, the captured face images in the monitoring area may be obtained by shooting the occasional fa...

AI Technical Summary

Problems solved by technology

[0004] However, in many cases, the captured face images in the monitoring area may be obtained by shooting the occasional faces of some guests who are far away from the monitoring area, and if the faces of distant guests are The face images in the monitoring area also participate in the calculation of the passenger flow and passenger flow attributes in the monitoring area, which will lead to inaccurate statistics of the passenger flow and passenger flow attributes in the monitoring area

Images