Method for categorizing digital video data

A computer implemented method for extracting information on actions or activities captured in digital data comprising steps of:

• a. providing a first digital data set comprising a temporal sequence of data frames;
• b. extracting and characterizing first features from the first digital data set;
• c. determining probability density function values for the first features;
• d. defining reference probability density functions;
• e. creating first clusters from the extracted first features according to first feature probability density function values and reference function distance calculations;
• f. providing a second digital data set;
• g. extracting and characterizing second features from the second digital data set;
• h. characterizing the extracted second features according to probability density functions and reference function distance calculations;
• and
• i. matching the second extracted features to a portion of the first extracted features clusters according to similarities in reference function distance calculations.