Measuring physiological signals from the human face and body using cameras is an emerging research topic that has grown rapidly in the last decade. Avoiding mechanical contact of skin, remote cameras have been used to measure vital signs (e.g. heart rate, heart rate variability, respiration rate, blood oxygenation saturation, pulse transit time, body temperature, etc.) from an image sequence registering a human skin or body. This leads to contactless, continuous and comfortable heath monitoring, which improves user experience/clinical workflow and eliminates potential risks of infection/contamination caused by contact bio-sensors. Imaging methods for recovering vital signs also present new opportunities for machine vision applications that require better understanding of human physiology (e.g. affective computing and cognitive recognition). In addition to vital signs monitoring, cameras also enable the analysis of high-level image/video semantics and context by leveraging computer vision (CV) and artificial intelligence (AI) techniques, such as facial expression analysis for pain/discomfort/delirium detection; emotion recognition for depression analysis; body motion for sleep staging; activity recognition for patient actigraphy or gait analysis; clinical workflow monitoring and optimization; etc. Camera-based monitoring will bring a rich set of compelling CV and healthcare applications that directly improve upon the human’s life and care experience, such as in hospital care units, sleep/senior centers, assisted-living homes, telemedicine and e-health, home-based baby and elderly care, fitness and sports, driver monitoring in automotive, AR/VR entertainment, etc. Especially in the background of COVID-19, contactless health monitoring of cameras can be served to control the pandemic, such as vital signs screening, home-based monitoring, social distancing alarm, etc.
The CVPM workshop aims to unite the researchers working in this field, and those who can directly/indirectly benefit from and/or contribute to it (including CV and AI researchers, doctors/clinicians, medical experts and psychologists). Although targeted at computer vision audiences, and aimed at promoting advancements in methods, a unique aspect of this workshop is that it brings a rich set of compelling applications (e.g., from video health monitoring to affective computing to face anti-spoofing and biometric security) that attracts broader audiences from fields beyond computer science.