Alexander Hauptmann (Carnegie Mellon University, USA)

Video Information Extraction for Long Term Activity Analysis in Health Care

Analyzing human activity is the key to understand and search surveillance videos. I will discuss the current results from a study to utilize automatic human activities analysis to improve geriatric health care. Beyond just recognizing human activities observed on video, we mine a 25 day archive of observations in a nursing home, and link the observational results to medical records. This work explores the statistical patterns between a patient's daily activity and his/her clinical diagnosis.

Our main contribution is in developing and using an intelligent visual surveillance system based on efficient and robust activity analysis and a demonstration of the feasibility of exploiting long term human activity patterns though video analysis.

Presentation at SSR