A combined multiple action recognition and summarization for surveillance video sequences

<p>Human action recognition and video summarization represent challenging tasks for several computer vision applications including video surveillance, criminal investigations, and sports applications. For long videos, it is difficult to search within a video for a specific action and/or person...

Full description

Saved in:
Bibliographic Details
Main Author: Omar Elharrouss (14150895) (author)
Other Authors: Noor Almaadeed (14150898) (author), Somaya Al-Maadeed (5178131) (author), Ahmed Bouridane (2270131) (author), Azeddine Beghdadi (14150901) (author)
Published: 2022
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513567939624960
author Omar Elharrouss (14150895)
author2 Noor Almaadeed (14150898)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Azeddine Beghdadi (14150901)
author2_role author
author
author
author
author_facet Omar Elharrouss (14150895)
Noor Almaadeed (14150898)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Azeddine Beghdadi (14150901)
author_role author
dc.creator.none.fl_str_mv Omar Elharrouss (14150895)
Noor Almaadeed (14150898)
Somaya Al-Maadeed (5178131)
Ahmed Bouridane (2270131)
Azeddine Beghdadi (14150901)
dc.date.none.fl_str_mv 2022-11-22T21:12:53Z
dc.identifier.none.fl_str_mv 10.1007/s10489-020-01823-z
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_combined_multiple_action_recognition_and_summarization_for_surveillance_video_sequences/21597177
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Video summarization
Human action recognition
CNN
HOG
TDMap
dc.title.none.fl_str_mv A combined multiple action recognition and summarization for surveillance video sequences
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Human action recognition and video summarization represent challenging tasks for several computer vision applications including video surveillance, criminal investigations, and sports applications. For long videos, it is difficult to search within a video for a specific action and/or person. Usually, human action recognition approaches presented in the literature deal with videos that contain only a single person, and they are able to recognize his action. This paper proposes an effective approach to multiple human action detection, recognition, and summarization. The multiple action detection extracts human bodies’ silhouette, then generates a specific sequence for each one of them using motion detection and tracking method. Each of the extracted sequences is then divided into shots that represent homogeneous actions in the sequence using the similarity between each pair frames. Using the histogram of the oriented gradient (HOG) of the Temporal Difference Map (TDMap) of the frames of each shot, we recognize the action by performing a comparison between the generated HOG and the existed HOGs in the training phase which represents all the HOGs of many actions using a set of videos for training. Also, using the TDMap images we recognize the action using a proposed CNN model. Action summarization is performed for each detected person. The efficiency of the proposed approach is shown through the obtained results for mainly multi-action detection and recognition.</p><h2>Other Information</h2> <p> Published in: Applied Intelligence<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10489-020-01823-z" target="_blank">http://dx.doi.org/10.1007/s10489-020-01823-z</a></p>
eu_rights_str_mv openAccess
id Manara2_8c0789d5842df980027a5e32f356b99e
identifier_str_mv 10.1007/s10489-020-01823-z
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/21597177
publishDate 2022
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A combined multiple action recognition and summarization for surveillance video sequencesOmar Elharrouss (14150895)Noor Almaadeed (14150898)Somaya Al-Maadeed (5178131)Ahmed Bouridane (2270131)Azeddine Beghdadi (14150901)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationVideo summarizationHuman action recognitionCNNHOGTDMap<p>Human action recognition and video summarization represent challenging tasks for several computer vision applications including video surveillance, criminal investigations, and sports applications. For long videos, it is difficult to search within a video for a specific action and/or person. Usually, human action recognition approaches presented in the literature deal with videos that contain only a single person, and they are able to recognize his action. This paper proposes an effective approach to multiple human action detection, recognition, and summarization. The multiple action detection extracts human bodies’ silhouette, then generates a specific sequence for each one of them using motion detection and tracking method. Each of the extracted sequences is then divided into shots that represent homogeneous actions in the sequence using the similarity between each pair frames. Using the histogram of the oriented gradient (HOG) of the Temporal Difference Map (TDMap) of the frames of each shot, we recognize the action by performing a comparison between the generated HOG and the existed HOGs in the training phase which represents all the HOGs of many actions using a set of videos for training. Also, using the TDMap images we recognize the action using a proposed CNN model. Action summarization is performed for each detected person. The efficiency of the proposed approach is shown through the obtained results for mainly multi-action detection and recognition.</p><h2>Other Information</h2> <p> Published in: Applied Intelligence<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="http://dx.doi.org/10.1007/s10489-020-01823-z" target="_blank">http://dx.doi.org/10.1007/s10489-020-01823-z</a></p>2022-11-22T21:12:53ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s10489-020-01823-zhttps://figshare.com/articles/journal_contribution/A_combined_multiple_action_recognition_and_summarization_for_surveillance_video_sequences/21597177CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/215971772022-11-22T21:12:53Z
spellingShingle A combined multiple action recognition and summarization for surveillance video sequences
Omar Elharrouss (14150895)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Video summarization
Human action recognition
CNN
HOG
TDMap
status_str publishedVersion
title A combined multiple action recognition and summarization for surveillance video sequences
title_full A combined multiple action recognition and summarization for surveillance video sequences
title_fullStr A combined multiple action recognition and summarization for surveillance video sequences
title_full_unstemmed A combined multiple action recognition and summarization for surveillance video sequences
title_short A combined multiple action recognition and summarization for surveillance video sequences
title_sort A combined multiple action recognition and summarization for surveillance video sequences
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Video summarization
Human action recognition
CNN
HOG
TDMap