DMCA
Kernel-based Multiple Cue Algorithm for Object Segmentation (2000)
Cached
Download Links
| Venue: | In SPIE Symposium on Electronic Imaging 2000, Image and Video Communications and Processing, SPIE Proceedings |
BibTeX
@INPROCEEDINGS{And00kernel-basedmultiple,
author = {Jian Wang And and Jian Wang and Ze-nian Li},
title = {Kernel-based Multiple Cue Algorithm for Object Segmentation},
booktitle = {In SPIE Symposium on Electronic Imaging 2000, Image and Video Communications and Processing, SPIE Proceedings},
year = {2000},
pages = {462--473}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper proposes a novel algorithm to solve the problem of segmenting foreground-moving objects from the background scene. The major cue used for object segmentation is the motion information, which is initially extracted from MPEG motion vectors. Since the MPEG motion vectors are generated for simple video compression without any consideration of visual objects, they may not correspond to the true motion of the macroblocks. We propose a Kernel-based Multiple Cue (KMC) algorithm to deal with the above inconsistency of MPEG motion vectors and use multiple cues to segment moving objects. KMC detects and calibrates camera movements; and then finds the kernels of moving objects. The segmentation starts from these kernels, which are textured regions with credible motion vectors. Beside motion information, it also makes use of color and texture to help achieving a better segmentation. Moreover, KMC can keep track of the segmented objects over multiple frames, which is useful for object-ba...
Keyphrases
object segmentation mpeg motion vector kernel-based multiple cue algorithm kmc detects segmented object use multiple cue kernel-based multiple cue multiple frame foreground-moving object credible motion vector simple video compression visual object beside motion information motion information major cue background scene novel algorithm true motion
