Toward Multi-area Contactless Museum Visitor Counting with Commodity WiFi

Multi-area visitor counting plays a critical role in museum management, which can help administrative staff better study visitor flows and hotspots, so that they can ensure the quality and safety of visits. Internet of Things (IoT) techniques facilitate efficient recording and understanding of visitors’ spatial and temporal distribution in museums, and traditional visitor tracking applications use surveillance cameras or wireless connections with portable smart devices. However, these methods either involve privacy concerns or face the obstacle of getting natural behavioral data of all visitors. This article explores an IoT monitoring methodology in the field of museum studies, proposing a commodity WiFi-based head-counting framework that does not need the visitor to connect with any device. Our system analyzes the Channel State Information amplitude fluctuations at the fixed receiver caused when visitors cross the line-of-sight link. It enables multi-area visitor counting by achieving In-and-Out traffic detection at different sites with a convolutional neural network algorithm. The method also allows for a rough classification of visitor types based on body size, and an extra transfer module is presented to reduce training time for increasing sensing scenarios. Over 2,300 samples at five different sites were collected to test the usability. Experiment 1 implemented in three environments/deployments demonstrated that the proposed approach can be potentially implemented in variable sites of museums. It achieved high up to 95% and 99% accuracies for identifying the number and direction of people crossing, respectively. Experiment 2 sampled adults, children, and adult-child groups at a science museum and achieved approximately 89% classification accuracy of visitor types. Experiment 3 collected data for all cases in which up to three targets entered and exited simultaneously, and reached a recognition accuracy of around 88% for nine different cases. The potential and limitations for the practical application of wireless contactless sensing to cultural spaces are discussed.