Video scene retrieval based on local region features

A Anjulan; CN Canagarajah

doi:10.1109/ICIP.2006.313044

Video scene retrieval based on local region features

A Anjulan, CN Canagarajah

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

14 Citations (Scopus)

403 Downloads (Pure)

Abstract

This paper describes a novel method for content extraction and scene retrieval for video sequences based on local region descriptors. The local invariant features are obtained for all frames in a sequence and tracked throughout the shot to extract stable features. The scenes in a shot are represented by these stable features rather than features from one or more key frames. Compared to previous key frame based approaches, the proposed method is highly robust to camera and object motions and can withstand severe illumination changes. The proposed approach is applied to scene retrieval experiments and excellent performance is demonstrated

Translated title of the contribution	Video scene retrieval based on local region features
Original language	English
Title of host publication	IEEE International Conference on Image Processing, 2006 (ICIP 2006)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	3177 - 3180
ISBN (Print)	1-4244-0480-0
DOIs	https://doi.org/10.1109/ICIP.2006.313044
Publication status	Published - Oct 2006
Event	International Conference on Image Processing - Atlanta, United States Duration: 1 Oct 2006 → …

Publication series

Name
ISSN (Print)	1522-4880
ISSN (Electronic)	2381-8549

Conference

Conference	International Conference on Image Processing
Country/Territory	United States
City	Atlanta
Period	1/10/06 → …

Bibliographical note

ISBN: 1424404819
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Name and Venue of Conference: International Conference on Image Processing, Atlanta, GA
Rose publication type: Conference contribution

Sponsorship: The work reported in this paper has formed part of the ICBR project
within the 3C Research programme of convergent technology research
for digital media processing and communications whose funding and
support is gratefully acknowledged.

Terms of use: Copyright © 2006 IEEE. Reprinted from IEEE International Conference on Image Processing, 2006 (ICIP 2006).

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected].

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Keywords

scene retrieval
invariant features
video segmentation
feature extraction
local region tracks

Access to Document

10.1109/ICIP.2006.313044

Full-text PDF (accepted author manuscript)Accepted author manuscript, 4.82 MB

Handle.net

Persistent link

Cite this

@inproceedings{3492dd2b06394d82a6ae39344b36041b,

title = "Video scene retrieval based on local region features",

abstract = "This paper describes a novel method for content extraction and scene retrieval for video sequences based on local region descriptors. The local invariant features are obtained for all frames in a sequence and tracked throughout the shot to extract stable features. The scenes in a shot are represented by these stable features rather than features from one or more key frames. Compared to previous key frame based approaches, the proposed method is highly robust to camera and object motions and can withstand severe illumination changes. The proposed approach is applied to scene retrieval experiments and excellent performance is demonstrated",

keywords = "scene retrieval, invariant features, video segmentation, feature extraction, local region tracks",

author = "A Anjulan and CN Canagarajah",

note = "ISBN: 1424404819 Publisher: Institute of Electrical and Electronics Engineers (IEEE) Name and Venue of Conference: International Conference on Image Processing, Atlanta, GA Rose publication type: Conference contribution Sponsorship: The work reported in this paper has formed part of the ICBR project within the 3C Research programme of convergent technology research for digital media processing and communications whose funding and support is gratefully acknowledged. Terms of use: Copyright {\textcopyright} 2006 IEEE. Reprinted from IEEE International Conference on Image Processing, 2006 (ICIP 2006). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. ; International Conference on Image Processing ; Conference date: 01-10-2006",

year = "2006",

month = oct,

doi = "10.1109/ICIP.2006.313044",

language = "English",

isbn = "1-4244-0480-0",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "3177 -- 3180",

booktitle = "IEEE International Conference on Image Processing, 2006 (ICIP 2006)",

address = "United States",

}

TY - GEN

T1 - Video scene retrieval based on local region features

AU - Anjulan, A

AU - Canagarajah, CN

N1 - ISBN: 1424404819 Publisher: Institute of Electrical and Electronics Engineers (IEEE) Name and Venue of Conference: International Conference on Image Processing, Atlanta, GA Rose publication type: Conference contribution Sponsorship: The work reported in this paper has formed part of the ICBR project within the 3C Research programme of convergent technology research for digital media processing and communications whose funding and support is gratefully acknowledged. Terms of use: Copyright © 2006 IEEE. Reprinted from IEEE International Conference on Image Processing, 2006 (ICIP 2006). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

PY - 2006/10

Y1 - 2006/10

N2 - This paper describes a novel method for content extraction and scene retrieval for video sequences based on local region descriptors. The local invariant features are obtained for all frames in a sequence and tracked throughout the shot to extract stable features. The scenes in a shot are represented by these stable features rather than features from one or more key frames. Compared to previous key frame based approaches, the proposed method is highly robust to camera and object motions and can withstand severe illumination changes. The proposed approach is applied to scene retrieval experiments and excellent performance is demonstrated

AB - This paper describes a novel method for content extraction and scene retrieval for video sequences based on local region descriptors. The local invariant features are obtained for all frames in a sequence and tracked throughout the shot to extract stable features. The scenes in a shot are represented by these stable features rather than features from one or more key frames. Compared to previous key frame based approaches, the proposed method is highly robust to camera and object motions and can withstand severe illumination changes. The proposed approach is applied to scene retrieval experiments and excellent performance is demonstrated

KW - scene retrieval

KW - invariant features

KW - video segmentation

KW - feature extraction

KW - local region tracks

U2 - 10.1109/ICIP.2006.313044

DO - 10.1109/ICIP.2006.313044

M3 - Conference Contribution (Conference Proceeding)

SN - 1-4244-0480-0

SP - 3177

EP - 3180

BT - IEEE International Conference on Image Processing, 2006 (ICIP 2006)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - International Conference on Image Processing

Y2 - 1 October 2006

ER -

Video scene retrieval based on local region features

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Handle.net

Fingerprint

Cite this