Video object segmentation and its salient motion detection using adaptive background generation

被引：7

作者：

Kim, T. K. ^{[1
]}

Im, J. H. ^{[1
]}

Paik, J. K. ^{[1
]}

机构：

[1] Chung Ang Univ, Dept Image Engn, Image Proc & Intelligent Syst Lab, Grad Sch Adv Imaging Sci Multimedia & Film, Seoul 156756, South Korea

来源：

ELECTRONICS LETTERS | 2009年 / 45卷 / 11期

关键词：

Image segmentation;

D O I：

10.1049/el.2009.0663

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Video object segmentation often fails when the background and foreground contain a similar distribution of colours. Proposed is a novel image segmentation algorithm to detect salient motion under a complex environment by combining temporal difference and background generation. Experimental results show that the proposed algorithm provides a twice higher matching ratio than the conventional Gaussian mixture-based approaches under various conditions.

引用

页码：542 / U24

页数：2

共 7 条

[1] Mittal A, 2004, PROC CVPR IEEE, P302
[2] Monnet A, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P1305
[3] Motion detection with non-stationary background
Ren, Y
Chua, CS
Ho, YK
[J]. 11TH INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, PROCEEDINGS, 2001, : 78 - 83
[4] Stauffer C., 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149), P246, DOI 10.1109/CVPR.1999.784637
[5] VELASTIN S, 2006, P METH TECHN BEH RES
[6] Wildes RP, 1998, 1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 3, P183, DOI 10.1109/ICIP.1998.727163
[7] Detecting salient motion by accumulating directionally-consistent flow
Wixson, L
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) : 774 - 780

← 1 →