METHOD FOR ADAPTIVE THRESHOLDING FOR BACKGROUND SUBTRACTION

摘要

A METHOD (200) FOR EXTRACTING FOREGROUND OBJECTS OF A CURRENTLY OBSERVED IMAGE IS PROVIDED HEREWITH. THE METHOD COMPRISES SEGMENTING (202) BACKGROUND OBJECTS OF A PREVIOUSLY OBSERVED IMAGE INTO REGIONS OF HOMOGENEOUS BRIGHTNESS AND SETTING INITIAL THRESHOLD VALUES FOR EACH SEGMENTED REGIONS TO INITIALIZE A BACKGROUND IMAGE INFORMATION THAT INCLUDES BACKGROUND IMAGE AND INITIAL THRESHOLD VALUES OF THE CURRENTLY OBSERVED IMAGE, SUBTRACTING (401) THE CURRENTLY OBSERVED IMAGE FROM THE BACKGROUND IMAGE INFORMATION AND THRESHOLDING (402) THE IMAGE DIFFERENCE USING THE INITIAL THRESHOLD VALUES TO EXTRACT FOREGROUND OF THE CURRENTLY OBSERVED IMAGE, AND COMPARING (405A) THE FOREGROUND OF THE CURRENTLY OBSERVED IMAGE AGAINST FOREGROUND OF THE PREVIOUSLY OBSERVED IMAGE TO UPDATE THE INITIAL THRESHOLD VALUES OF THE BACKGROUND IMAGE INFORMATION. (FIG.1)