LAUSR

Video surveillance cameras play a vital role in society. Elderly monitoring is one of the major applications of surveillance camera. It is observed that most of the elderly people live alone at homes. They desire aging at homes. Due to aging elderly people may experience some abnormal behaviors like chest pain, headache etc. Since they live alone these abnormal activities are unnoticed. This unnoticed activities cause severe health problems and finally may cause death. So a monitoring system is needed to monitor the behavior and give alerts to the care givers. A computer vision based elderly health care monitoring system using Dynamic Bayesian network (DBN) is developed. Modelling sequential data is an important feature in machine learning domain. The DBN model detects the abnormal activities such as backward fall, chest pain, forward fall, headache, and vomit. Human postures are recognized from silhouettes so that the privacy of the people is preserved and this model is robust to different environmental setup. This DBN model is both generative and discriminative and evaluated with real time video sequences and gives 82% accuracy. This system helps to give immediate attention to the people who are suffering in home alone due to severe health issues.