WiFi-based non-contact museum multi-area audience counting method

Abstract

The invention discloses a non-contact museum multi-area audience counting method based on WiFi, and the method comprises the steps: taking the entrance and exit positions of a plurality of monitoring areas of a museum as monitoring points, and deploying a WiFi transmitter and a WiFi receiver at each monitoring point; the WiFi transmitter transmits a WiFi signal, two antennas of the WiFi receiver respectively collect channel state information amplitudes when people flow in and out at a monitoring point, and filtering, smoothing, time region segmentation and linear interpolation processing are carried out on the channel state information amplitudes to obtain museum sample data; in combination with laboratory sample data and labels, counting the number of people in the museum sample data by using an audience number recognition model trained based on an environment transfer learning network; performing direction statistics on the museum sample data by using an audience direction identification model trained based on an environment transfer learning network; and determining the number of audiences in the monitoring area by combining the number counting result and the direction counting result of the monitoring point.

Description

technical field [0001] The invention belongs to the field of museum audience behavior monitoring, and in particular relates to a WiFi-based non-contact museum multi-area audience counting method. Background technique [0002] The proposal of the concept of smart museum puts forward higher requirements for the application of Internet of Things technology in museum environment perception and monitoring, and the visitor's visit behavior in the museum is one of the important perception objects. On the one hand, the real-time and fine-grained traffic statistics in the exhibition hall are conducive to the flexible scheduling of museum staff and the study of the stay time of visitors in different areas; However, the existing multi-region audience traffic statistics technology in museums is difficult to meet the natural, large-scale deployment and privacy protection monitoring effects at the same time. [0003] According to whether the audience needs to carry additional equipment, ...

AI Technical Summary

Problems solved by technology

Considering that the museum is a public space, the existing technology needs to manually label a large number of samples at each monitoring point during the deployment phase, which is not only inefficient, but may also affect the visitor experience

Images