1 September 2007 Multiresolution segmentation of video objects in the compression domain
Author Affiliations +
Optical Engineering, 46(9), 097401 (2007). doi:10.1117/1.2784773
Abstract
This paper proposes a multiresolution method for video object segmentation in the compression domain. We first calculate global motion parameters using only background macroblocks with tiny residual dc coefficients of the P frame, and then get true motion vectors projected to the immediate adjoined I frame. The basic layer image is obtained with only dc coefficients of the I frame. The enhancement texture characteristics are provided by the ac coefficients for partial decoding. The true object motion vectors and the basic layer image are fed into a morphological motion filter to get the lowest-resolution regions of moving objects, called the layer4 region of interest (L4-ROI). Only some of the ac coefficients in L4-ROI are decoded to obtain a higher-resolution image, called layer3, that mainly consists of blocks of the moving object. The moving object of interest in the highest resolution is obtained from a morphological motion filter with L2-ROI and the true object motion vectors. The number of ac coefficients determines the resulting resolution. Experiments show that the new algorithm can extract multiresolution moving objects efficiently.
Xu-li Shi, Zhao-Yang Zhang, Liquan Shen, Yu Lu, Suxing Liu, "Multiresolution segmentation of video objects in the compression domain," Optical Engineering 46(9), 097401 (1 September 2007). http://dx.doi.org/10.1117/1.2784773
JOURNAL ARTICLE
6 PAGES


SHARE
KEYWORDS
Video

Image segmentation

Image filtering

Video compression

Cameras

Image processing algorithms and systems

Motion estimation

Back to Top