Semi-Automatic Video Object Segmentation Using LVQ with Color and Spatial Features

Hariadi MOCHAMAD  Hui Chien LOY  Takafumi AOKI  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E88-D   No.7   pp.1553-1560
Publication Date: 2005/07/01
Online ISSN: 
DOI: 10.1093/ietisy/e88-d.7.1553
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Section on Recent Advances in Circuits and Systems--Part 1)
Category: Image Processing and Multimedia Systems
Keyword: 
object extraction,  object segmentation,  learning vector quantization,  video processing,  MPEG,  

Full Text: PDF(1.9MB)>>
Buy this Article




Summary: 
This paper presents a semi-automatic algorithm for video object segmentation. Our algorithm assumes the use of multiple key video frames in which a semantic object of interest is defined 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. We introduce a parameter K to adjust the balance of spatial and color information. Experimental results demonstrate that the algorithm can segment the video object consistently with less than 2% average error when the object is moving at a moderate speed.