Using histograms to detect and track objects in color video

Abstract

Two methods of detecting and tracking objects in color video are presented. Color and edge histograms are explored as ways to model the background and foreground of a scene. The two types of methods are evaluated to determine their speed, accuracy and robustness. Histogram comparison techniques are used to compute similarity values that aid in identifying regions of interest. Foreground objects are detected and tracked by dividing each video frame into smaller regions (cells) and comparing the histogram of each cell to the background model. Results are presented for video sequences of human activity.