Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval
The extensive video surveillance networks gather an enormous amount of data exponentially on a daily basis and its management is a challenging task, requiring efficient and effective techniques for searching, indexing, and retrieval. The employed mainstream techniques are focusing on general categor...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9218944/ |
id |
doaj-9c567b6c131b43fe85952e05cea95158 |
---|---|
record_format |
Article |
spelling |
doaj-9c567b6c131b43fe85952e05cea951582021-03-30T04:16:39ZengIEEEIEEE Access2169-35362020-01-01819652919654010.1109/ACCESS.2020.30298349218944Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video RetrievalAmin Ullah0https://orcid.org/0000-0001-7538-2689Khan Muhammad1https://orcid.org/0000-0002-5302-1150Tanveer Hussain2https://orcid.org/0000-0003-4861-8347Sung Wook Baik3https://orcid.org/0000-0002-6678-7788Victor Hugo C. De Albuquerque4https://orcid.org/0000-0003-3886-4309Intelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South KoreaIntelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South KoreaIntelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South KoreaIntelligent Media Laboratory, Digital Contents Research Institute, Sejong University, Seoul, South KoreaUniversity of Fortaleza, Fortaleza, CE, BrazilThe extensive video surveillance networks gather an enormous amount of data exponentially on a daily basis and its management is a challenging task, requiring efficient and effective techniques for searching, indexing, and retrieval. The employed mainstream techniques are focusing on general category videos, where the important events in surveillance require fine-grained events retrieval. In this paper, we introduce an event-oriented feature selection mechanism by utilizing the intermediate convolutional layer of a pre-trained 3D-CNN model, that is selected after deep investigation of its weights and response to a particular event. The extracted exclusive features represent an event semantically and effectively eliminate those neurons which do not respond to an event. Furthermore, the event-oriented convolutional features are of very high-dimensions, requiring additional storage, and take more time in feature comparison for retrieval. Therefore, we generate compact binary codes from these features using principle component analysis (PCA) algorithm. This makes our system more efficient to retrieve videos from large scale database. We evaluated our approach on the challenging events of UCF101 and HMDB51 datasets for original features and generated compact codes to achieve reduced execution time and better precision and recall scores.https://ieeexplore.ieee.org/document/9218944/Deep learningfeature selectionvideo retrievalvideo analyticshash codessurveillance event analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Amin Ullah Khan Muhammad Tanveer Hussain Sung Wook Baik Victor Hugo C. De Albuquerque |
spellingShingle |
Amin Ullah Khan Muhammad Tanveer Hussain Sung Wook Baik Victor Hugo C. De Albuquerque Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval IEEE Access Deep learning feature selection video retrieval video analytics hash codes surveillance event analysis |
author_facet |
Amin Ullah Khan Muhammad Tanveer Hussain Sung Wook Baik Victor Hugo C. De Albuquerque |
author_sort |
Amin Ullah |
title |
Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval |
title_short |
Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval |
title_full |
Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval |
title_fullStr |
Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval |
title_full_unstemmed |
Event-Oriented 3D Convolutional Features Selection and Hash Codes Generation Using PCA for Video Retrieval |
title_sort |
event-oriented 3d convolutional features selection and hash codes generation using pca for video retrieval |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
The extensive video surveillance networks gather an enormous amount of data exponentially on a daily basis and its management is a challenging task, requiring efficient and effective techniques for searching, indexing, and retrieval. The employed mainstream techniques are focusing on general category videos, where the important events in surveillance require fine-grained events retrieval. In this paper, we introduce an event-oriented feature selection mechanism by utilizing the intermediate convolutional layer of a pre-trained 3D-CNN model, that is selected after deep investigation of its weights and response to a particular event. The extracted exclusive features represent an event semantically and effectively eliminate those neurons which do not respond to an event. Furthermore, the event-oriented convolutional features are of very high-dimensions, requiring additional storage, and take more time in feature comparison for retrieval. Therefore, we generate compact binary codes from these features using principle component analysis (PCA) algorithm. This makes our system more efficient to retrieve videos from large scale database. We evaluated our approach on the challenging events of UCF101 and HMDB51 datasets for original features and generated compact codes to achieve reduced execution time and better precision and recall scores. |
topic |
Deep learning feature selection video retrieval video analytics hash codes surveillance event analysis |
url |
https://ieeexplore.ieee.org/document/9218944/ |
work_keys_str_mv |
AT aminullah eventoriented3dconvolutionalfeaturesselectionandhashcodesgenerationusingpcaforvideoretrieval AT khanmuhammad eventoriented3dconvolutionalfeaturesselectionandhashcodesgenerationusingpcaforvideoretrieval AT tanveerhussain eventoriented3dconvolutionalfeaturesselectionandhashcodesgenerationusingpcaforvideoretrieval AT sungwookbaik eventoriented3dconvolutionalfeaturesselectionandhashcodesgenerationusingpcaforvideoretrieval AT victorhugocdealbuquerque eventoriented3dconvolutionalfeaturesselectionandhashcodesgenerationusingpcaforvideoretrieval |
_version_ |
1724182114295873536 |