Face tracking in video using a joint probabilistic data association filter (JPDAF)

摘要

A method for tracking faces in multiple video frames includes obtaining a predicted position of a face in a video frame (310). A search (320) is performed to determine appearance model similarity values of a detected face. Motion and appearance probabilities of the detected face are obtained, and the detected face in the video frame is associated with a track (330) as a function of a joint probabilistic data association filter.