Improved Wifi-Based Respiration Tracking via Contrast Enhancement

Respiratory rate tracking has gained more and more interest in the past few years because of its great potential in exploring different pathological conditions of human beings. Conventional approaches usually require dedicated wearable devices, making them intrusive and unfriendly to users. To tackle the issue, many WiFi-based respiration tracking systems have been proposed because of WiFi's ubiquity, low-cost, and most importantly, contactlessness. However, most existing works are of limited coverage and inflexible deployment, which greatly hinders their applications. In this paper, we propose WiResP, a practical and innovative WiFi-based respiration tracking system that utilizes a contrast enhancement technique to improve the detection of respiration. This approach combines both instantaneous and time-domain information, resulting in better recognition of breaths and identification of breath patterns. Extensive experiments under different settings show that WiResP can well capture respiratory rate during sleep under flexible deployments. Moreover, it remarkably increases the sensing coverage compared with the existing methods, making it a potential candidate toward real-world applications.