Temporal Segmentation of MPEG Video Streams

Many algorithms for temporal video partitioning rely on the analysis of uncompressed video features. Since the information relevant to the partitioning process can be extracted directly from the MPEG compressed stream, higher efficiency can be achieved utilizing information from the MPEG compressed...

Full description

Bibliographic Details
Main Authors: Janko Calic, Ebroul Izquierdo
Format: Article
Language:English
Published: SpringerOpen 2002-06-01
Series:EURASIP Journal on Advances in Signal Processing
Subjects:
Online Access:http://dx.doi.org/10.1155/S1110865702000938
_version_ 1819161376973651968
author Janko Calic
Ebroul Izquierdo
author_facet Janko Calic
Ebroul Izquierdo
author_sort Janko Calic
collection DOAJ
description Many algorithms for temporal video partitioning rely on the analysis of uncompressed video features. Since the information relevant to the partitioning process can be extracted directly from the MPEG compressed stream, higher efficiency can be achieved utilizing information from the MPEG compressed domain. This paper introduces a real-time algorithm for scene change detection that analyses the statistics of the macroblock features extracted directly from the MPEG stream. A method for extraction of the continuous frame difference that transforms the 3D video stream into a 1D curve is presented. This transform is then further employed to extract temporal units within the analysed video sequence. Results of computer simulations are reported.
first_indexed 2024-12-22T17:11:22Z
format Article
id doaj.art-052741f32a1c4c27a58b994ff1a16129
institution Directory Open Access Journal
issn 1687-6172
1687-6180
language English
last_indexed 2024-12-22T17:11:22Z
publishDate 2002-06-01
publisher SpringerOpen
record_format Article
series EURASIP Journal on Advances in Signal Processing
spelling doaj.art-052741f32a1c4c27a58b994ff1a161292022-12-21T18:19:03ZengSpringerOpenEURASIP Journal on Advances in Signal Processing1687-61721687-61802002-06-012002656156510.1155/S1687617202000938Temporal Segmentation of MPEG Video StreamsJanko CalicEbroul IzquierdoMany algorithms for temporal video partitioning rely on the analysis of uncompressed video features. Since the information relevant to the partitioning process can be extracted directly from the MPEG compressed stream, higher efficiency can be achieved utilizing information from the MPEG compressed domain. This paper introduces a real-time algorithm for scene change detection that analyses the statistics of the macroblock features extracted directly from the MPEG stream. A method for extraction of the continuous frame difference that transforms the 3D video stream into a 1D curve is presented. This transform is then further employed to extract temporal units within the analysed video sequence. Results of computer simulations are reported.http://dx.doi.org/10.1155/S1110865702000938shot detectionvideo indexingcompressed domainMPEG stream.
spellingShingle Janko Calic
Ebroul Izquierdo
Temporal Segmentation of MPEG Video Streams
EURASIP Journal on Advances in Signal Processing
shot detection
video indexing
compressed domain
MPEG stream.
title Temporal Segmentation of MPEG Video Streams
title_full Temporal Segmentation of MPEG Video Streams
title_fullStr Temporal Segmentation of MPEG Video Streams
title_full_unstemmed Temporal Segmentation of MPEG Video Streams
title_short Temporal Segmentation of MPEG Video Streams
title_sort temporal segmentation of mpeg video streams
topic shot detection
video indexing
compressed domain
MPEG stream.
url http://dx.doi.org/10.1155/S1110865702000938
work_keys_str_mv AT jankocalic temporalsegmentationofmpegvideostreams
AT ebroulizquierdo temporalsegmentationofmpegvideostreams