Novel precision target detection with adaptive thresholding for dynamic segmentation

摘要

A new adaptive thresholding algorithm concern- ing extraction of targets form the background in a given image sequence is proposed. The conventional histogram- image sequence is proposed. The conventional histogram- based or fixed-value thresholdings are deficient in detecting targets due to the poor contrast between targets and the back- ground, or to the change of illumination. This research solves the problems mentioned above by learning the characteris- tics of the background from the given images and determines the proper thresholds based on this information.