Non-intrusive head movement analysis of videotaped seizures of epileptic origin

In this work we propose a non-intrusive video analytic system for patient´s body parts movement analysis in Epilepsy Monitoring Unit. The system utilizes skin color modeling, head/face pose template matching and face detection to analyze and quantify the head movements. Epileptic patients´ heads are analyzed holistically to infer seizure and normal random movements. The patient does not require to wear any special clothing, markers or sensors, hence it is totally non-intrusive. The user initializes the person-specific skin color and selects few face/head poses in the initial few frames. The system then tracks the head/face and extracts spatio-temporal features. Support vector machines are then used on these features to classify seizure-like movements from normal random movements. Experiments are performed on numerous long hour video sequences captured in an Epilepsy Monitoring Unit at a local hospital. The results demonstrate the feasibility of the proposed system in pediatric epilepsy monitoring and seizure detection.