Please use this identifier to cite or link to this item:
Title: Video representation and retrieval using spatio-temporal descriptors and region relations
Authors: Doulamis, Anastasios D. 
Kosmopoulos, Dimitrios 
Chatzis, Sotirios P. 
Doulamis, Anastasios D. 
Kosmopoulos, Dimitrios 
Keywords: Computer science;Neural networks;Algorithms;Graph theory;Problem solving;Machine learning
Issue Date: 2006
Publisher: Springer
Source: Artificial neural networks – ICANN 2006: 16th international conference, Athens, Greece, September 10-14, 2006. Proceedings, Part II, Pages 94-103
Abstract: This paper describes a novel methodology for video summarization and representation. The video shots are processed in space-time as 3D volumes of pixels. Pixel regions with consistent color and motion properties are extracted from these 3D volumes by a space-time segmentation technique based on a novel machine learning algorithm. Each region is then described by a high-dimensional point whose components represent the average position, motion velocity and color of the region. Subsequently, the spatio-temporal relations of the regions are deduced and a concise, graph-based description of them is generated. This graph-based description of the video shot's content, along with the region centroids, comprises a concise yet powerful description of the video-shot and is used for retrieval applications. The retrieval problem is formulated as an inexact graph matching problem between the data video shots and the query input which is also a video segment. Experimental results on action recognition and video retrieval are illustrated and discussed
ISBN: 978-3-540-38871-5 (print)
978-3-540-38873-9 (online)
DOI: 10.1007/11840930_10
Rights: © Springer-Verlag Berlin Heidelberg 2006
Type: Book Chapter
Appears in Collections:Κεφάλαια βιβλίων/Book chapters

Show full item record

Page view(s)

Last Week
Last month
checked on Dec 12, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.