Home > Research > Publications & Outputs > Combined Feature-Level Video Indexing Using Blo...
View graph of relations

Combined Feature-Level Video Indexing Using Block-Based Motion Estimation.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Combined Feature-Level Video Indexing Using Block-Based Motion Estimation. / Bhaskar, H.; Mihaylova, L.

13th Conference on Information Fusion (FUSION), 2010. IEEE, 2010. p. 1-8.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Bhaskar, H & Mihaylova, L 2010, Combined Feature-Level Video Indexing Using Block-Based Motion Estimation. in 13th Conference on Information Fusion (FUSION), 2010. IEEE, pp. 1-8, 13th International Conference on Information Fusion, Edinburgh, UK, 26/07/10.

APA

Bhaskar, H., & Mihaylova, L. (2010). Combined Feature-Level Video Indexing Using Block-Based Motion Estimation. In 13th Conference on Information Fusion (FUSION), 2010 (pp. 1-8). IEEE.

Vancouver

Bhaskar H, Mihaylova L. Combined Feature-Level Video Indexing Using Block-Based Motion Estimation. In 13th Conference on Information Fusion (FUSION), 2010. IEEE. 2010. p. 1-8

Author

Bhaskar, H. ; Mihaylova, L. / Combined Feature-Level Video Indexing Using Block-Based Motion Estimation. 13th Conference on Information Fusion (FUSION), 2010. IEEE, 2010. pp. 1-8

Bibtex

@inproceedings{a2f079386caf45998b1effdee81f24ae,
title = "Combined Feature-Level Video Indexing Using Block-Based Motion Estimation.",
abstract = "We describe a method for attaching content-based labels to video data using a weighted combination of low-level features (such as colour, texture, motion, etc.) estimated during motion analysis. Every frame of a video sequence is modeled using a fixed set of low-level feature attributes together with a set of corresponding weights using a block-based motion estimation technique. Indexing a new video involves an alternative scheme in which the weights of the features are first estimated and then classification is performed to determine the label corresponding to the video. A hierarchical architecture of increasingly complexity is used to achieve robust indexing of new videos. We explore the effect of different model parameters on performance and prove that the proposed method is effective using publicly available datasets.",
keywords = "Tracking, filtering, estimation, fuzzy logic, resource management",
author = "H. Bhaskar and L. Mihaylova",
note = "Catalogue number: CFP10FUS-CDR ISBN:978-0-9824438-1-1",
year = "2010",
month = "7",
day = "28",
language = "English",
isbn = "978-0-9824438-1-1",
pages = "1--8",
booktitle = "13th Conference on Information Fusion (FUSION), 2010",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Combined Feature-Level Video Indexing Using Block-Based Motion Estimation.

AU - Bhaskar, H.

AU - Mihaylova, L.

N1 - Catalogue number: CFP10FUS-CDR ISBN:978-0-9824438-1-1

PY - 2010/7/28

Y1 - 2010/7/28

N2 - We describe a method for attaching content-based labels to video data using a weighted combination of low-level features (such as colour, texture, motion, etc.) estimated during motion analysis. Every frame of a video sequence is modeled using a fixed set of low-level feature attributes together with a set of corresponding weights using a block-based motion estimation technique. Indexing a new video involves an alternative scheme in which the weights of the features are first estimated and then classification is performed to determine the label corresponding to the video. A hierarchical architecture of increasingly complexity is used to achieve robust indexing of new videos. We explore the effect of different model parameters on performance and prove that the proposed method is effective using publicly available datasets.

AB - We describe a method for attaching content-based labels to video data using a weighted combination of low-level features (such as colour, texture, motion, etc.) estimated during motion analysis. Every frame of a video sequence is modeled using a fixed set of low-level feature attributes together with a set of corresponding weights using a block-based motion estimation technique. Indexing a new video involves an alternative scheme in which the weights of the features are first estimated and then classification is performed to determine the label corresponding to the video. A hierarchical architecture of increasingly complexity is used to achieve robust indexing of new videos. We explore the effect of different model parameters on performance and prove that the proposed method is effective using publicly available datasets.

KW - Tracking

KW - filtering

KW - estimation

KW - fuzzy logic

KW - resource management

M3 - Conference contribution/Paper

SN - 978-0-9824438-1-1

SP - 1

EP - 8

BT - 13th Conference on Information Fusion (FUSION), 2010

PB - IEEE

ER -