Share Email Print

Proceedings Paper

Automatic moving object extraction algorithm using histogram mapping and local watershed techniques for shadow effect
Author(s): Hong-Yeon Yu; Min-Sung Kim; Do-Young Jun; Chang-Hyun Kim; Sung-Hoon Hong
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Background subtraction method is a typical technique used for real-time extraction of moving objects in video sequences. In this paper, we propose an efficient moving object extraction algorithm which is suitable for digital video monitoring applications. The proposed algorithm combines the histogram modification and the local watershed techniques. The present background image is estimated by sing the histogram modification table which maps the original background image to the present on. Then, the moving object region is extracted by background subtraction. Finally, the local watershed segmentation and hierarchical queue based region merging are applied on the uncertain region of moving object mask instead of whole image region, which can decrease processing time. Also proposed method is robust to both noise and intensity changes in the present input image. The proposed method is evaluated for real-time sequences and produces promising results.

Paper Details

Date Published: 9 January 2008
PDF: 6 pages
Proc. SPIE 6794, ICMIT 2007: Mechatronics, MEMS, and Smart Materials, 679442 (9 January 2008); doi: 10.1117/12.784027
Show Author Affiliations
Hong-Yeon Yu, Chonnam National Univ. (South Korea)
Min-Sung Kim, Chonnam National Univ. (South Korea)
Do-Young Jun, Chonnam National Univ. (South Korea)
Chang-Hyun Kim, Chonnam National Univ. (South Korea)
Sung-Hoon Hong, Chonnam National Univ. (South Korea)

Published in SPIE Proceedings Vol. 6794:
ICMIT 2007: Mechatronics, MEMS, and Smart Materials
Minoru Sasaki; Gisang Choi Sang; Zushu Li; Ryojun Ikeura; Hyungki Kim; Fangzheng Xue, Editor(s)

© SPIE. Terms of Use
Back to Top