CrossCount: A Deep Learning System for Device-free Human Counting using WiFi

TL;DR

CrossCount is a deep learning system that accurately estimates human counts using WiFi link blockage patterns, outperforming traditional methods by being robust to noise and requiring minimal data collection.

Contribution

It introduces a novel WiFi-based human counting method leveraging temporal link-blockage patterns and addresses deep learning challenges like class imbalance and data augmentation.

Findings

Achieves up to 100% accuracy within 2 persons

Works reliably across multiple testbeds

Uses only a single WiFi link for counting

Abstract

Counting humans is an essential part of many people-centric applications. In this paper, we propose CrossCount: an accurate deep-learning-based human count estimator that uses a single WiFi link to estimate the human count in an area of interest. The main idea is to depend on the temporal link-blockage pattern as a discriminant feature that is more robust to wireless channel noise than the signal strength, hence delivering a ubiquitous and accurate human counting system. As part of its design, CrossCount addresses a number of deep learning challenges such as class imbalance and training data augmentation for enhancing the model generalizability. Implementation and evaluation of CrossCount in multiple testbeds show that it can achieve a human counting accuracy to within a maximum of 2 persons 100% of the time. This highlights the promise of CrossCount as a ubiquitous crowd estimator with non-labour-intensive data collection from off-the-shelf devices.