A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks
Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of 3D convolutional neural networks (3D ConvNet), a novel violent video detection scheme based on the modified 3D ConvNet is proposed. In this pape...
Gespeichert in:
| Veröffentlicht in: | IEEE access 2019, Vol.7, p.39172-39179 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 39179 |
|---|---|
| container_issue | |
| container_start_page | 39172 |
| container_title | IEEE access |
| container_volume | 7 |
| creator | Song, Wei Zhang, Dongliang Zhao, Xiaobing Yu, Jing Zheng, Rui Wang, Antai |
| description | Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of 3D convolutional neural networks (3D ConvNet), a novel violent video detection scheme based on the modified 3D ConvNet is proposed. In this paper, the preprocessing method of data is improved, and a new sampling method by using the key frame as dividing nodes is designed. Then, a random sampling method is adapted to produce the input frame sequence. With experimental evaluations on the crowd violence dataset, the results demonstrate the effectiveness of the proposed new sampling method. For three public violent detection datasets: hockey fight, movies, and crowd violence, individualized strategies are implemented to suit the varied clip length. For the short clips, the 3D ConvNet is constructed by using the uniform sampling method. For the longer clips, the new frame sampling strategy is adopted. The proposed scheme obtains competitive results: 99.62% on hockey fight, 99.97% on movies, and 94.3% on crowd violence. The experimental results show that our method is simple and effective. |
| doi_str_mv | 10.1109/ACCESS.2019.2906275 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_ACCESS_2019_2906275</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8669768</ieee_id><doaj_id>oai_doaj_org_article_84b726f80d73459ba434b74cae4b2bc7</doaj_id><sourcerecordid>2455617118</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-6e8a307972fd3230f7b53648184433428b88f8c596f1f555fdc4216a7cf1f4cf3</originalsourceid><addsrcrecordid>eNpNUctOwzAQjBBIIOgX9BKJc4vfdo4l5VEJyqGAxMlynDWkpDXYKYi_x20qhC-7O5qZ9WqybIjRGGNUXEzK8mqxGBOEizEpkCCSH2QnBItiRDkVh__642wQ4xKlpxLE5Un2Msnn_gva_LnxLay7VGvw-RQ6sF3j1_nCvsEK8ksToc7TfO_rxjWpp9O89Osv3262PNPmc9iEXem-fXiPZ9mRM22Ewb6eZk_XV4_l7eju4WZWTu5GliHVjQQoQ5EsJHE1JRQ5WaWPMoUVY5QyoiqlnLK8EA47zrmrLUv3GGnTzKyjp9ms9629WeqP0KxM-NHeNHoH-PCqTega24JWrJJEOIVqSRkvKsNoQpg1wCpSWZm8znuvj-A_NxA7vfSbkI6LmjDOBZYYq8SiPcsGH2MA97cVI72NRPeR6G0keh9JUg17VQMAfwolRCGFor-u3YWV</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2455617118</pqid></control><display><type>article</type><title>A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks</title><source>IEEE Open Access Journals</source><source>DOAJ Directory of Open Access Journals</source><source>EZB-FREE-00999 freely available EZB journals</source><creator>Song, Wei ; Zhang, Dongliang ; Zhao, Xiaobing ; Yu, Jing ; Zheng, Rui ; Wang, Antai</creator><creatorcontrib>Song, Wei ; Zhang, Dongliang ; Zhao, Xiaobing ; Yu, Jing ; Zheng, Rui ; Wang, Antai</creatorcontrib><description>Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of 3D convolutional neural networks (3D ConvNet), a novel violent video detection scheme based on the modified 3D ConvNet is proposed. In this paper, the preprocessing method of data is improved, and a new sampling method by using the key frame as dividing nodes is designed. Then, a random sampling method is adapted to produce the input frame sequence. With experimental evaluations on the crowd violence dataset, the results demonstrate the effectiveness of the proposed new sampling method. For three public violent detection datasets: hockey fight, movies, and crowd violence, individualized strategies are implemented to suit the varied clip length. For the short clips, the 3D ConvNet is constructed by using the uniform sampling method. For the longer clips, the new frame sampling strategy is adopted. The proposed scheme obtains competitive results: 99.62% on hockey fight, 99.97% on movies, and 94.3% on crowd violence. The experimental results show that our method is simple and effective.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2019.2906275</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>3D ConvNet ; Algorithms ; Artificial neural networks ; Business competition ; Clips ; Convolution ; Datasets ; Deep learning ; Feature extraction ; Hockey ; key frame extraction ; Motion pictures ; Neural networks ; Random sampling ; Sampling methods ; Three-dimensional displays ; Violence ; Violent video detection ; Visualization</subject><ispartof>IEEE access, 2019, Vol.7, p.39172-39179</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-6e8a307972fd3230f7b53648184433428b88f8c596f1f555fdc4216a7cf1f4cf3</citedby><cites>FETCH-LOGICAL-c408t-6e8a307972fd3230f7b53648184433428b88f8c596f1f555fdc4216a7cf1f4cf3</cites><orcidid>0000-0002-2324-4302</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8669768$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,864,2102,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Song, Wei</creatorcontrib><creatorcontrib>Zhang, Dongliang</creatorcontrib><creatorcontrib>Zhao, Xiaobing</creatorcontrib><creatorcontrib>Yu, Jing</creatorcontrib><creatorcontrib>Zheng, Rui</creatorcontrib><creatorcontrib>Wang, Antai</creatorcontrib><title>A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks</title><title>IEEE access</title><addtitle>Access</addtitle><description>Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of 3D convolutional neural networks (3D ConvNet), a novel violent video detection scheme based on the modified 3D ConvNet is proposed. In this paper, the preprocessing method of data is improved, and a new sampling method by using the key frame as dividing nodes is designed. Then, a random sampling method is adapted to produce the input frame sequence. With experimental evaluations on the crowd violence dataset, the results demonstrate the effectiveness of the proposed new sampling method. For three public violent detection datasets: hockey fight, movies, and crowd violence, individualized strategies are implemented to suit the varied clip length. For the short clips, the 3D ConvNet is constructed by using the uniform sampling method. For the longer clips, the new frame sampling strategy is adopted. The proposed scheme obtains competitive results: 99.62% on hockey fight, 99.97% on movies, and 94.3% on crowd violence. The experimental results show that our method is simple and effective.</description><subject>3D ConvNet</subject><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Business competition</subject><subject>Clips</subject><subject>Convolution</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>Hockey</subject><subject>key frame extraction</subject><subject>Motion pictures</subject><subject>Neural networks</subject><subject>Random sampling</subject><subject>Sampling methods</subject><subject>Three-dimensional displays</subject><subject>Violence</subject><subject>Violent video detection</subject><subject>Visualization</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><sourceid>DOA</sourceid><recordid>eNpNUctOwzAQjBBIIOgX9BKJc4vfdo4l5VEJyqGAxMlynDWkpDXYKYi_x20qhC-7O5qZ9WqybIjRGGNUXEzK8mqxGBOEizEpkCCSH2QnBItiRDkVh__642wQ4xKlpxLE5Un2Msnn_gva_LnxLay7VGvw-RQ6sF3j1_nCvsEK8ksToc7TfO_rxjWpp9O89Osv3262PNPmc9iEXem-fXiPZ9mRM22Ewb6eZk_XV4_l7eju4WZWTu5GliHVjQQoQ5EsJHE1JRQ5WaWPMoUVY5QyoiqlnLK8EA47zrmrLUv3GGnTzKyjp9ms9629WeqP0KxM-NHeNHoH-PCqTega24JWrJJEOIVqSRkvKsNoQpg1wCpSWZm8znuvj-A_NxA7vfSbkI6LmjDOBZYYq8SiPcsGH2MA97cVI72NRPeR6G0keh9JUg17VQMAfwolRCGFor-u3YWV</recordid><startdate>2019</startdate><enddate>2019</enddate><creator>Song, Wei</creator><creator>Zhang, Dongliang</creator><creator>Zhao, Xiaobing</creator><creator>Yu, Jing</creator><creator>Zheng, Rui</creator><creator>Wang, Antai</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-2324-4302</orcidid></search><sort><creationdate>2019</creationdate><title>A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks</title><author>Song, Wei ; Zhang, Dongliang ; Zhao, Xiaobing ; Yu, Jing ; Zheng, Rui ; Wang, Antai</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-6e8a307972fd3230f7b53648184433428b88f8c596f1f555fdc4216a7cf1f4cf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>3D ConvNet</topic><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Business competition</topic><topic>Clips</topic><topic>Convolution</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>Hockey</topic><topic>key frame extraction</topic><topic>Motion pictures</topic><topic>Neural networks</topic><topic>Random sampling</topic><topic>Sampling methods</topic><topic>Three-dimensional displays</topic><topic>Violence</topic><topic>Violent video detection</topic><topic>Visualization</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Song, Wei</creatorcontrib><creatorcontrib>Zhang, Dongliang</creatorcontrib><creatorcontrib>Zhao, Xiaobing</creatorcontrib><creatorcontrib>Yu, Jing</creatorcontrib><creatorcontrib>Zheng, Rui</creatorcontrib><creatorcontrib>Wang, Antai</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Song, Wei</au><au>Zhang, Dongliang</au><au>Zhao, Xiaobing</au><au>Yu, Jing</au><au>Zheng, Rui</au><au>Wang, Antai</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2019</date><risdate>2019</risdate><volume>7</volume><spage>39172</spage><epage>39179</epage><pages>39172-39179</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Violent video constitutes a threat to public security, and effective detection algorithms are in urgent need. In order to improve the detection accuracy of 3D convolutional neural networks (3D ConvNet), a novel violent video detection scheme based on the modified 3D ConvNet is proposed. In this paper, the preprocessing method of data is improved, and a new sampling method by using the key frame as dividing nodes is designed. Then, a random sampling method is adapted to produce the input frame sequence. With experimental evaluations on the crowd violence dataset, the results demonstrate the effectiveness of the proposed new sampling method. For three public violent detection datasets: hockey fight, movies, and crowd violence, individualized strategies are implemented to suit the varied clip length. For the short clips, the 3D ConvNet is constructed by using the uniform sampling method. For the longer clips, the new frame sampling strategy is adopted. The proposed scheme obtains competitive results: 99.62% on hockey fight, 99.97% on movies, and 94.3% on crowd violence. The experimental results show that our method is simple and effective.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2019.2906275</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0002-2324-4302</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2169-3536 |
| ispartof | IEEE access, 2019, Vol.7, p.39172-39179 |
| issn | 2169-3536 2169-3536 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_ACCESS_2019_2906275 |
| source | IEEE Open Access Journals; DOAJ Directory of Open Access Journals; EZB-FREE-00999 freely available EZB journals |
| subjects | 3D ConvNet Algorithms Artificial neural networks Business competition Clips Convolution Datasets Deep learning Feature extraction Hockey key frame extraction Motion pictures Neural networks Random sampling Sampling methods Three-dimensional displays Violence Violent video detection Visualization |
| title | A Novel Violent Video Detection Scheme Based on Modified 3D Convolutional Neural Networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T19%3A31%3A25IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Novel%20Violent%20Video%20Detection%20Scheme%20Based%20on%20Modified%203D%20Convolutional%20Neural%20Networks&rft.jtitle=IEEE%20access&rft.au=Song,%20Wei&rft.date=2019&rft.volume=7&rft.spage=39172&rft.epage=39179&rft.pages=39172-39179&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2019.2906275&rft_dat=%3Cproquest_cross%3E2455617118%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2455617118&rft_id=info:pmid/&rft_ieee_id=8669768&rft_doaj_id=oai_doaj_org_article_84b726f80d73459ba434b74cae4b2bc7&rfr_iscdi=true |