Title :
Human-Area Segmentation by Selecting Similar Silhouette Images Based on Weak-Classifier Response
Author :
Ando, Hiroaki ; Fujiyoshi, Hironobu
Author_Institution :
Dept. of Comput. Sci., Chubu Univ., Kasugai, Japan
Abstract :
Human-area segmentation is a major issue in video surveillance. Many existing methods estimate individual human areas from the foreground area obtained by background subtraction, but the effects of camera movement can make it difficult to obtain a background image. We have achieved human-area segmentation requiring no background image by using chamfer matching to match the results of human detection using Real AdaBoost with silhouette images. Although accuracy in chamfer matching drops as the number of templates increases, the proposed method enables segmentation accuracy to be improved by selecting silhouette images similar to the matching target beforehand based on response values from weak classifiers in Real AdaBoost.
Keywords :
image classification; image matching; image segmentation; video surveillance; background image; background subtraction; camera movement; chamfer matching; foreground area; human detection; human-area segmentation; real AdaBoost; silhouette images; video surveillance; weak-classifier response; Accuracy; Detectors; Feature extraction; Humans; Image segmentation; Shape; Training; Object detection and recognition;
Conference_Titel :
Pattern Recognition (ICPR), 2010 20th International Conference on
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-7542-1
DOI :
10.1109/ICPR.2010.841