Overview of Behavioural Understanding System with Filtered Vision Sensor

Understanding human behaviour and activities is a challenging problem in computer vision. In application areas like health care and ambient intelligence, the use of a camera feed might be seen as too invasive and may be resented. Human behaviour understanding can combine images, signals, feature extraction and other machine learning techniques. This paper presents an overview of our technique that aims to investigate low cost and acceptable visual camera monitoring systems for the elderly. The main idea is to limit the amount of information that needs to be transmitted from the visual sensor unit. The proposed technique will use only filtered images, without saving or transmitting any visual information and thus maintaining privacy.