Object density acquisition method and device

Abstract

The invention discloses an object density acquisition method and device and belongs to the image analysis technology field. The method comprises steps that n monitoring images of a target area collected at n different times in the target time period are acquired, and the n is an integer greater than 1; objects contained by each monitoring image are identified; the distance difference information corresponding to each monitoring image is acquired, and the distance difference information is used for indicating the degree of difference in the distances among the objects contained in the monitoring images; according to the respective distance difference information of the n monitoring images, the object density of the target area in the target time period is determined. The method is advantaged in that constructing and training a model are not needed in the scheme realization process, and scheme realization complexity and enforcement requirements are reduced.

Description

technical field

[0001] Embodiments of the present invention relate to the technical field of image analysis, and in particular to a method and device for acquiring object density. Background technique

[0002] With the rapid increase of urban population density, many public infrastructures often usher in short-term peak flow of people, and the high degree of crowding can easily lead to various emergencies. Therefore, it is very necessary to measure the crowd density in public infrastructure and other places, and then carry out subsequent management and coordination.

[0003] Driven by the construction of a safe city, cameras have been installed in many places. By analyzing the surveillance video collected by the cameras, the crowd density of the corresponding places can be determined. In the related art, a method for obtaining crowd density based on video analysis is provided, which mainly includes the following two steps: (1) training the crowd density estimation model, (2...

Images