A multi‐camera vision system for fall detection and alarm generation

TLDR

In‑house video surveillance supports people with limited autonomy, and affordable digital cameras are increasingly used for semi‑automatic safety assurance. The paper presents a multi‑camera vision system that detects and tracks people and recognizes dangerous behaviours such as falls. The system warps silhouettes to exchange visual information between overlapping cameras during handover, sends alarms via SMS, and delivers live video streams through a multi‑client, multi‑threaded transcoding server that uses semantic and event‑based algorithms to optimize bandwidth. In a two‑room laboratory setup the system was evaluated, and preliminary results demonstrating its performance were reported.

Abstract

Abstract: In‐house video surveillance can represent an excellent support for people with some difficulties (e.g. elderly or disabled people) living alone and with a limited autonomy. New hardware technologies and in particular digital cameras are now affordable and they have recently gained credit as tools for (semi‐)automatically assuring people's safety. In this paper a multi‐camera vision system for detecting and tracking people and recognizing dangerous behaviours and events such as a fall is presented. In such a situation a suitable alarm can be sent, e.g. by means of an SMS. A novel technique of warping people's silhouette is proposed to exchange visual information between partially overlapped cameras whenever a camera handover occurs. Finally, a multi‐client and multi‐threaded transcoding video server delivers live video streams to operators/remote users in order to check the validity of a received alarm. Semantic and event‐based transcoding algorithms are used to optimize the bandwidth usage. A two‐room setup has been created in our laboratory to test the performance of the overall system and some of the results obtained are reported.