Histogram based fall prediction of patients using a thermal imagery camera

This paper proposes a monitoring system to prevent falls from a bed. The position of patient on the bed is categorized as stable and unstable. The system has defined the unstable condition as the situation where a patient is lying on the edge of the bed. The patient was then observed using a thermal imagery camera. We extracted x-, and y-axis histograms that can be used as a feature, using this camera. We used the SVM (Support Vector Machine) to decide an optimal decision boundary and achieved an accuracy of 99.70%.