Video concept detection using Hadoop MapReduce framework

Indexing video collection with a large set of video concepts allows us to employ a query-by-concept paradigm. Through concept detection, the task is to detect in the shot- segmented video data the presence of a set of pre-defined semantic concepts. Columbia University provided 374 detectors based on...

Full description

Bibliographic Details
Main Authors: Affendey, Lilly Suriani, Chamasemani, Fereshteh Falah, Ishak, Iskandar, Sidi, Fatimah
Format: Conference or Workshop Item
Language:English
Published: 2014
Online Access:http://psasir.upm.edu.my/id/eprint/38455/1/38455.pdf
_version_ 1825949229567180800
author Affendey, Lilly Suriani
Chamasemani, Fereshteh Falah
Ishak, Iskandar
Sidi, Fatimah
author_facet Affendey, Lilly Suriani
Chamasemani, Fereshteh Falah
Ishak, Iskandar
Sidi, Fatimah
author_sort Affendey, Lilly Suriani
collection UPM
description Indexing video collection with a large set of video concepts allows us to employ a query-by-concept paradigm. Through concept detection, the task is to detect in the shot- segmented video data the presence of a set of pre-defined semantic concepts. Columbia University provided 374 detectors based on color, texture and edge features, and their unsupervised classifier fusion that can be utilized for concepts training purposes. We had successfully implemented a Concept-based Video retrieval System (CBVRS) to support query-by-concept. However, one of the main challenges is to reduce the training time of concepts to support the video concept detection. This paper presents an alternative architecture to overcome the issue. The proposed CBVRS framework, which consists of three main modules i.e. pre-processing, video analysis, and annotation module, shall utilize the Hadoop MapReduce framework for fast computation of the concept detection.
first_indexed 2024-03-06T08:41:21Z
format Conference or Workshop Item
id upm.eprints-38455
institution Universiti Putra Malaysia
language English
last_indexed 2024-03-06T08:41:21Z
publishDate 2014
record_format dspace
spelling upm.eprints-384552016-07-29T07:50:56Z http://psasir.upm.edu.my/id/eprint/38455/ Video concept detection using Hadoop MapReduce framework Affendey, Lilly Suriani Chamasemani, Fereshteh Falah Ishak, Iskandar Sidi, Fatimah Indexing video collection with a large set of video concepts allows us to employ a query-by-concept paradigm. Through concept detection, the task is to detect in the shot- segmented video data the presence of a set of pre-defined semantic concepts. Columbia University provided 374 detectors based on color, texture and edge features, and their unsupervised classifier fusion that can be utilized for concepts training purposes. We had successfully implemented a Concept-based Video retrieval System (CBVRS) to support query-by-concept. However, one of the main challenges is to reduce the training time of concepts to support the video concept detection. This paper presents an alternative architecture to overcome the issue. The proposed CBVRS framework, which consists of three main modules i.e. pre-processing, video analysis, and annotation module, shall utilize the Hadoop MapReduce framework for fast computation of the concept detection. 2014 Conference or Workshop Item NonPeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/38455/1/38455.pdf Affendey, Lilly Suriani and Chamasemani, Fereshteh Falah and Ishak, Iskandar and Sidi, Fatimah (2014) Video concept detection using Hadoop MapReduce framework. In: Malaysian National Conference of Databases 2014 (MaNCoD 2014), 17 Sept. 2014, Universiti Putra Malaysia, Serdang, Selangor. (pp. 46-49). (Unpublished) http://mancod2014.blogspot.my/p/proceedings.html
spellingShingle Affendey, Lilly Suriani
Chamasemani, Fereshteh Falah
Ishak, Iskandar
Sidi, Fatimah
Video concept detection using Hadoop MapReduce framework
title Video concept detection using Hadoop MapReduce framework
title_full Video concept detection using Hadoop MapReduce framework
title_fullStr Video concept detection using Hadoop MapReduce framework
title_full_unstemmed Video concept detection using Hadoop MapReduce framework
title_short Video concept detection using Hadoop MapReduce framework
title_sort video concept detection using hadoop mapreduce framework
url http://psasir.upm.edu.my/id/eprint/38455/1/38455.pdf
work_keys_str_mv AT affendeylillysuriani videoconceptdetectionusinghadoopmapreduceframework
AT chamasemanifereshtehfalah videoconceptdetectionusinghadoopmapreduceframework
AT ishakiskandar videoconceptdetectionusinghadoopmapreduceframework
AT sidifatimah videoconceptdetectionusinghadoopmapreduceframework