A novel web-based depth video rewind approach toward fall preventive interventions in hospitals

The purpose of this study was to implement a web based application to provide the ability to rewind and review depth videos captured in hospital rooms to investigate the event chains that led to patient´s fall at a specific time. In this research, Kinect depth images are being used to capture shadow-like images of the patient and their room to resolve concerns about patients´ privacy. As a result of our previous research, a fall detection system has been developed and installed in hospital rooms, and fall alarms are generated if any falls are detected by the system. Then nurses will go through the stored depth videos to investigate for possible injury as well as the reasons and events that may have caused the patient´s fall to prevent future occurrences. This paper proposes a novel web application to ease the process of search and reviewing the videos by means of new visualization techniques to highlight video frames that contain potential risk of fall based on our previous research.