A kind of passenger flow statistics method and device, computer readable storage medium

Abstract

The present application discloses a passenger flow statistics method, comprising: obtaining monitoring video within a preset time period; extracting image frames in the monitoring video according to a preset time interval, processing the image frames to obtain pixel values ​​of the image frames; The pixel value of the image frame is used as feature information, and input into the pre-trained face recognition model and gesture recognition model to identify customer information and customer consumption gesture information; The information is counted to obtain the number of customers who enter the store for consumption and the number of customers who enter the store without consumption. The application also discloses a passenger flow counting device and a computer-readable storage medium. This application extracts the image frames in the monitoring video and uses the pixel values ​​of the image frames as feature information, and inputs the face recognition and gesture recognition models to identify customers and customers' consumption gesture information, which improves the statistical efficiency of the effective passenger flow of restaurants or convenience stores and accuracy, saving labor costs.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a passenger flow counting method and device, and a computer-readable storage medium. Background technique [0002] In the era of increasingly fierce competition in the catering industry, effective customer flow and per capita consumption directly determine the level of restaurant turnover. When the per capita consumption of customers is constant, it is particularly important to increase the effective customer flow of restaurants. The so-called effective customer flow refers to the number of customers who enter the restaurant and consume. In reality, there are often some customers who enter the restaurant but do not consume, so under the premise of a certain restaurant traffic, the proportion of these customers to the restaurant traffic will directly affect the restaurant's turnover. [0003] How to count the number of customers who entered the store but d...

AI Technical Summary

Problems solved by technology

If we only rely on manual statistics, on the one hand, the labor cost of the restaurant will be increased, and on the other hand, the statistics will be time-consuming and the accuracy is not high. For example, once repeated statistics or omissions occur, it is impossible to re-count or re-count is too time-consuming

Images