Systems and methods for audience monitoring are provided that include receiving an input including a recording or live feed of an audience composed of several persons, detecting foreground of the input, performing blob segmentation of the input, and analyzing human presence on each segmented blob by identifying at least one person, identifying a spatial distribution of at least one identified person, determining a dwell time of at least one identified person, determining a temporal distribution of at least one identified person, and determining a gaze direction of at least one identified person. Such detecting provides the ability to track individual persons present in the audience, and how long they remain in the audience. The method also provides the ability to determine gaze direction of persons in the audience, and how long one or more persons are gazing in a particular direction.