A compressed-domain robust descriptor for near duplicate video copy detection

Rouhi, A and Thom, J 2014, 'A compressed-domain robust descriptor for near duplicate video copy detection', in M. J. Cree (ed.) Proceedings of the 29th International Conference on Image and Vision Computing New Zealand, Hamilton, New Zealand, 19-21 November 2014, pp. 130-135.


Document type: Conference Paper
Collection: Conference Papers

Title A compressed-domain robust descriptor for near duplicate video copy detection
Author(s) Rouhi, A
Thom, J
Year 2014
Conference name IVCNZ 2014
Conference location Hamilton, New Zealand
Conference dates 19-21 November 2014
Proceedings title Proceedings of the 29th International Conference on Image and Vision Computing New Zealand
Editor(s) M. J. Cree
Publisher Association for Computing Machinery
Place of publication New York, United States
Start page 130
End page 135
Total pages 6
Abstract This paper introduces a global descriptor from the compressed video domain (H.264) for near duplicate video copy detection tasks. The proposed descriptor uses a spatial-temporal feature structure in an ordinal pattern distribution format. The proposed descriptor is constructed from Intra-Prediction Modes (IPM) of key frames (IDR & I slices) and extracted from the compressed video files, using the MPEG4/AVC (H.264) codec. Intra-prediction is the compression technique used in the key frames of the H.264 codec. As the proposed feature describes pictures globally, this research compares the feature with the two other well-known global image descriptors, ordinal intensity/colour Histograms and ordinal Auto-correlograms, as baselines. Our experiments show how the proposed feature outperforms the baseline features in non-geometric transformations T3, T4 and T5 in effectiveness as well as efficiency. It is due to better representation of the image content and smaller feature vector size. The core competency of the proposed feature is in non-linear brightness and contrast changes (Gamma expansion and compression) in which the intensity/colour Histograms and Auto-correlograms are deficient.
Subjects Image Processing
Coding and Information Theory
Information Retrieval and Web Search
Keyword(s) Content-based Copy Detection
Global descriptors
Intraprediction
Near-duplicate video copy detection
Non-linear brightness and contrast changes
Compressed domain
H.264
MPEG-4 AVC
DOI - identifier 10.1145/2683405.2683417
Copyright notice © ACM 2014
ISBN 9781450331845
Versions
Version Filter Type
Altmetric details:
Access Statistics: 263 Abstract Views  -  Detailed Statistics
Created: Wed, 04 Feb 2015, 13:19:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us