A SEGMENTATION SCHEME FOR HEAD-SHOULDER VIDEO IN MPEG COMPRESSED DOMAIN  

作　　者：Liu Long Han Chongzhao Wang Zhanhui Bai Yan 

机构地区：[1]Xi＇an Jiaotong University, Xi＇an 710049, China [2]Navy University of Engineering, Wuhan 430033, China

出　　处：《Journal of Electronics(China)》2006年第2期236-243,共8页电子科学学刊（英文版）

基　　金：Supported by the National 973 Project of China (No.2001CB309403).

摘　　要：More attention has been paid to the study of video object segmentation in compressed domain these years, which has already led to some practical technology. In this paper, a scheme is put forward for segmentation of head-shoulder video in MPEG (Motion Picture Experts Group) compressed domain. The conception of DCT (Discrete Cosine Transform) feature plane is defined. In the suggested scheme, firstly, the face region is detected by clustering skin-tone DCT feature points in the DCT feature plane. Secondly, the region of head-shoulder is approximately regarded as combination of the head rectangle and shoulder rectangle, and head rectangle is confirmed by double template matching. Thirdly, Canny operator and morphological operation are applied to the region of head-shoulder in feature plane to get the object mask and the region of object mask is rectified by correlation of DCT blocks to get high-quality segmentation.More attention has been paid to the study of video object segmentation in compressed domain these years, which has already led to some practical technology. In this paper, a scheme is put forward for segmentation of head-shoulder video in MPEG （Motion Picture Experts Group） compressed domain. The conception of DCT （Discrete Cosine Transform） feature plane is defined. In the suggested scheme, firstly, the face region is detected by clustering skin-tone DCT feature points in the DCT feature plane. Secondly, the region of head-shoulder is approximately regarded as combination of the head rectangle and shoulder rectangle, and head rectangle is confirmed by double template matching. Thirdly, Canny operator and morphological operation are applied to the region of head-shoulder in feature plane to get the object mask and the region of object mask is rectified by correlation of DCT blocks to get high-quality segmentation.

关 键 词：SEGMENTATION Compressed domain MPEG Head-shoulder 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]