Novel methods for feature extraction based on motion history images and evaluation with regard to altering viewing angles

In recent years Western countries have been facing the impact of demographic change. Due to factors such as a rising lifetime expectancy and a decreasing birth rate, our society is getting older. This development is accompanied by constant lack of nursing staff, which leads to an imbalance of people who need care and professionally trained personnel caring for them. There already is a variety of approaches investigating vision-based action recognition. In this paper novel methods for feature extraction from motion history images are proposed.