Please use this identifier to cite or link to this item:
Title: Contextual motion field-based distance for video analysis
Authors: Mu, Y.
Yan, S. 
Huang, T.
Zhou, B.
Keywords: Activity classification
Motion field
Video analysis
Issue Date: Jul-2008
Citation: Mu, Y., Yan, S., Huang, T., Zhou, B. (2008-07). Contextual motion field-based distance for video analysis. Visual Computer 24 (7-9) : 595-603. ScholarBank@NUS Repository.
Abstract: In this work, we propose a general method for computing distance between video frames or sequences. Unlike conventional appearance-based methods, we first extract motion fields from original videos. To avoid the huge memory requirement demanded by the previous approaches, we utilize the "bag of motion vectors" model, and select Gaussian mixture model as compact representation. Thus, estimating distance between two frames is equivalent to calculating the distance between their corresponding Gaussian mixture models, which is solved via earth mover distance (EMD) in this paper. On the basis of the inter-frame distance, we further develop the distance measures for both full video sequences. Our main contribution is four-fold. Firstly, we operate on a tangent vector field of spatiooral 2D surface manifold generated by video motions, rather than the intensity gradient space. Here we argue that the former space is more fundamental. Secondly, the correlations between frames are explicitly exploited using a generative model named dynamic conditional random fields (DCRF). Under this framework, motion fields are estimated by Markov volumetric regression, which is more robust and may avoid the rank deficiency problem. Thirdly, our definition for video distance is in accord with human intuition and makes a better tradeoff between frame dissimilarity and chronological ordering. Lastly, our definition for frame distance allows for partial distance. © 2008 Springer-Verlag.
Source Title: Visual Computer
ISSN: 01782789
DOI: 10.1007/s00371-008-0240-1
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Oct 20, 2021


checked on Oct 20, 2021

Page view(s)

checked on Oct 14, 2021

Google ScholarTM



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