The COVID-19 pandemic has led to many organizations around the world enforcing face mask rules for personal protection. Manual checking whether individuals entering an organization's premises are wearing masks is cumbersome and possibly confrontational. There has been relatively little work on automatic face mask rule violations thus far. We propose a system for automatic monitoring for face mask rule violations for enterprises. Our method is an efficient two-stage facial mask detection model. The first stage is based on facial landmark extraction and clustering, and the second stage analyzes the clustered nose region. A thorough accuracy evaluation on five types of sample face images (no mask, beard and mustache, single-color mask, multi-color mask, and skin-color mask) finds that the overall accuracy of the two-stage model is an excellent 97.13%, outperforming simpler single-stage models. IntroductionGlobally, at the time of writing, over 36 million people are infected and over 1,056,186 deaths have been caused by the COVID-19 pandemic [1]. The World Health Organization has recommended that mask-wearing can reduce the chances of being infected or spreading COVID-19 by respiratory droplets, which constitute the main vector

No abstract

Real time detection of falls and unstable movement by elderly people is vital to their quality of life and safety. We present an edge processing device integrated with a cloud computation framework that can be used for activity profiling as well as trigger alerts for falls and unstable motion by elderly people at home. The proposed system uses fixed cameras to track and analyze each visible person in the scene, classifying their actions into nine ordinary activities, a fall, or unstable movement. An alert notification is sent to caregivers whenever a fall or unstable movement is detected. The major components of the system include an embedded device (NVIDIA JETSON TX2) and cloud-based storage and analysis infrastructure. The system is composed of modules for detecting, tracking and recognizing humans, a cascaded hierarchical classifier for nine ordinary activities and falls, and a long short-term memory (LSTM) module to predict unstable movement in video. The system is designed for accuracy, usability, and cost. A prototype system has been subjected to individual module tests along with a field test within a volunteer’s household. It achieved an accuracy of 91.6% for ordinary actions and falls with a recall of 97.02% for unstable motion. Future phases will expand deployment to multiple homes.