Monitoring of medication intake using a camera system.

This paper presents a computer vision system for monitoring medication intake in the context of home care services. We use a method based on color and shape to detect the body parts and the medication bottles. Color is used for skin detection, and the shape is used to distinguish the face from the hands and to differentiate bottles of medicine. To track these objects, we use a method based on color histograms, Hu moments, and edges. For the recognition of medication intake, we use a Petri network and event recognition. Our method has an accuracy of more than 75% and allows the detection of the medication intake in various scenarios where the user is cooperative.