An image-based object statistics method and system

Abstract

The invention provides an object statistical method and system based on images. The object statistical method comprises the steps of counting objects to be counted moving in a monitoring region, respectively monitoring part of regions in the monitoring region and the objects to be counted in part of the regions through a plurality of camera devices for monitoring the monitoring region, acquiring images, synchronizing the images in all the regions and splicing the images into a global image corresponding to the monitoring region, mapping the objects to be counted to the global image, identifying the identical objects to be counted, combining the objects, and counting the quantity or the flow of the objects to be counted in the monitoring region by tracking the combined objects to be counted in the global image, so that the monitoring region is enlarged, the repeated objects to be counted are eliminated through combination, and the flow is counted. The limitations, which are caused by the large monitoring region, in the counting of the objects which move wonderingly or do cross-region movement inside and outside the monitoring region in the prior art are eliminated; furthermore, conventional hardware equipment and conventional software systems are used to the maximum extent, and the development and maintenance costs are lowered.

Description

Technical field [0001] The present invention relates to the field of monitoring technology, in particular to an image-based object statistics method and system. Background technique [0002] With the development and improvement of the social economy and the increase of social mobility, the flow of people in various public places (shopping malls, supermarkets) is increasing. Today, when information is value, information on the number of pedestrians and walking paths is of great significance both in terms of commercial value and in providing support for public decision-making. Shopping malls can guide commercial activities and improve economic benefits based on passenger flow information in different time periods and locations; public places can also use this passenger flow information to guide passenger flow in a timely manner and maintain public order. [0003] Currently, there are two broad categories of technologies used in pedestrian tracking and counting: contact and non-conta...

AI Technical Summary

Problems solved by technology

This method is less affected by the external light environment; however, the amount of information obtained from the laser equipment is small, and the passenger flow counting scheme is immature, so this scheme is rarely used in actual scenarios

Images