Motion Segmentation and Retrieval for 3D Video Based on Modified Shape Distribution. (14th December 2006)

• Record Type: Journal Article
• Authors: Yamasaki Yamasaki, Toshihiko Toshihiko; Aizawa Aizawa, Kiyoharu Kiyoharu
• Other Names: Chen Chen Tsuhan Tsuhan Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2007(2007)
• Publication Date: 2006-12-14
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2007/59535
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : A similar motion search and retrieval system for 3D video are presented based on a modified shape distribution algorithm. 3D video is a sequence of 3D models made for a real-world object. In the present work, three fundamental functions for efficient retrieval have been developed: feature extraction, motion segmentation, and similarity evaluation. Stable-shape feature representation of 3D models has been realized by a modified shape distribution algorithm. Motion segmentation has been conducted by analyzing the degree of motion using the extracted feature vectors. Then, similar motion retrieval has been achieved employing the dynamic programming algorithm in the feature vector space. The experimental results using 3D video sequences of dances have demonstrated very promising results for motion segmentation and retrieval.