A Multi-sensor approach for People Fall Detection in Home Environment

This paper presents a hardware and software framework for reliable fall detection in the home environment, with particular focus on the protection and assistance to the elderly. The integrated proto- type includes three different sensors: a 3D Time-Of-Flight range camera, a wearable MEMS accelerometer and a microphone. These devices are connected with custom interface circuits to a central PC that collects and processes the information with a multi-threading approach. For each of the three sensors, an optimized algorithm for fall-detection has been developed and benchmarked on a collected mulitimodal database. This work is expected to lead to a multi-sensory approach employing appro- priate fusion techniques aiming to improve system precision and recall.