Presentation 2006/11/17
LVQ-Based Video Object Extraction and Its Performance Improvement
Surya SUMPENO, Hariadi MOCHAMAD, Koichi ITO, Takafumi AOKI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a semi-automatic algorithm for video object extraction. The proposed algorithm assumes the use of multiple key video frames in which a semantic object of interest is denned in advance with human assistance. For video frames between every two key frames, the specified video object is tracked and segmented automatically using Learning Vector Quantization (LVQ). Each pixel of a video frame is represented by a 5-dimensional feature vector integrating spatial and color information. This paper also presents a technique for improving extraction performance of the proposed algorithm. Experimental evaluation using MPEG standard test video sequences demonstrates that the proposed algorithm can extract the video object with 1% average error.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object extraction / learning vector quantization / video processing
Paper # SIS2006-67
Date of Issue

Conference Information
Committee SIS
Conference Date 2006/11/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) LVQ-Based Video Object Extraction and Its Performance Improvement
Sub Title (in English)
Keyword(1) object extraction
Keyword(2) learning vector quantization
Keyword(3) video processing
1st Author's Name Surya SUMPENO
1st Author's Affiliation Graduate School of Information Sciences, Tohoku University()
2nd Author's Name Hariadi MOCHAMAD
2nd Author's Affiliation Department of Electrical Engineering, Sepuluh November Institute of Technology (ITS)
3rd Author's Name Koichi ITO
3rd Author's Affiliation Graduate School of Information Sciences, Tohoku University
4th Author's Name Takafumi AOKI
4th Author's Affiliation Graduate School of Information Sciences, Tohoku University
Date 2006/11/17
Paper # SIS2006-67
Volume (vol) vol.106
Number (no) 374
Page pp.pp.-
#Pages 6
Date of Issue