Object flow data monitoring method and device and readable storage medium

Abstract

The embodiment of the invention discloses an object flow data monitoring method and device and a readable storage medium. The object flow data monitoring method comprises the steps of obtaining an original boundary line in a monitoring video for a target environment; determining a track buffer area in the monitoring video according to the original boundary line, wherein the track buffer area comprises a virtual boundary line constructed based on the original boundary line, wherein the monitoring video further comprises a behavior prediction area constructed based on the virtual boundary line;obtaining a behavior track corresponding to a moving object in the monitoring video; determining a behavior attribute corresponding to the moving object according to a position relationship among thebehavior track, the behavior prediction area and the virtual boundary line; and determining object flow data in the target environment according to the behavior attribute. By adopting the embodiment of the invention, accurate statistics of object flow data can be realized, and particularly the method plays an important role in passenger flow big data mining in a supermarket scene.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method, device and readable storage medium for monitoring object flow data. Background technique [0002] With the continuous development of Internet technology, more and more traditional industries have begun to deeply integrate with Internet technology, thus building a new development ecology. In order to provide better services, service providers in traditional industries need to collect and analyze relevant data in the service area to judge the behavior of moving objects entering and leaving the service area and other behaviors in the service area, and to conduct traffic statistics. [0003] In the existing object traffic data analysis and statistical methods, the video data is mainly collected through the monitoring camera installed in the service area, and then some features of the moving object are captured, and the behavior of the moving object is analyzed and judged ...

AI Technical Summary

Problems solved by technology

For example, when counting the flow of people entering and leaving a building, because the feature capture method is angle-sensitive and greatly affected by occlusion, it is easy to miss the judgment due to the failure of feature recognition, and cannot obtain more sufficient behavior information, resulting in object flow. The accuracy of the statistical results of the data is low

Images