Poster: KinFrame: Framework for Large Scale Surveillance of Vulnerable People using Depth Camera

With the advancement of technology in various domains, many efforts have been made to design advanced classification engines using depth cameras. Being inspired by its potential of providing information at the skeleton level using a non-invasive infrared camera, many studies have been done to aid vulnerable people such as children, elderly, and people that physically or mentally ill. However, most of these studies focus on the algorithms and processing of a single camera, and do not consider large scale issues that are found in practical deployments. We present KinFrame, a framework that: (1) considers challenges and requirements that are necessary in design a practical system for vulnerable people and allow application developers to easily setup multiple depth camera deployment, (2) adapts a flow control method to solve large scale bandwidth issues that exist while streaming data from multiple devices, and (3) uses a data management technique to control constant flow of realtime information and efficiently structure data storage. For improved usability of the system, we also design an alerting mechanism for quick emergency reports to parents and caregivers, and layout a user interface for them to verify emergency situations or analyze behavioral patterns of the vulnerable person being monitored. In this paper, we give an overview of KinFrame and demonstrate with an example of how it can be utilized in a real-world environment.