File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: An Anomaly Comprehension Neural Network for Surveillance Videos on Terminal Devices

TitleAn Anomaly Comprehension Neural Network for Surveillance Videos on Terminal Devices
Authors
Keywordsfeature extraction
learning (artificial intelligence)
recurrent neural nets
video signal processing
video surveillance
Issue Date2020
PublisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000198
Citation
2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 9-13 March 2020, p. 1396-1401 How to Cite?
AbstractAnomaly comprehension in surveillance videos is more challenging than detection. This work introduces the design of a lightweight and fast anomaly comprehension neural network. For comprehension, a spatio-temporal LSTM model is developed based on the structured, tensorized time-series features extracted from surveillance videos. Deep compression of network size is achieved by tensorization and quantization for the implementation on terminal devices. Experiments on large-scale video anomaly dataset UCF-Crime demonstrate that the proposed network can achieve an impressive inference speed of 266 FPS on a GTX-1080Ti GPU, which is 4.29 faster than ConvLSTM-based method; a 3.34% AUC improvement with 5.55% accuracy niche versus the 3D-CNN based approach; and at least 15k× parameter reduction and 228× storage compression over the RNN-based approaches. Moreover, the proposed framework has been realized on an ARM-core based IOT board with only 2.4W power consumption.
Persistent Identifierhttp://hdl.handle.net/10722/289867
ISSN

 

DC FieldValueLanguage
dc.contributor.authorCheng, Y-
dc.contributor.authorHuang, G-
dc.contributor.authorZhen, P-
dc.contributor.authorLiu, B-
dc.contributor.authorChen, HB-
dc.contributor.authorWong, N-
dc.contributor.authorYu, H-
dc.date.accessioned2020-10-22T08:18:36Z-
dc.date.available2020-10-22T08:18:36Z-
dc.date.issued2020-
dc.identifier.citation2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 9-13 March 2020, p. 1396-1401-
dc.identifier.issn1530-1591-
dc.identifier.urihttp://hdl.handle.net/10722/289867-
dc.description.abstractAnomaly comprehension in surveillance videos is more challenging than detection. This work introduces the design of a lightweight and fast anomaly comprehension neural network. For comprehension, a spatio-temporal LSTM model is developed based on the structured, tensorized time-series features extracted from surveillance videos. Deep compression of network size is achieved by tensorization and quantization for the implementation on terminal devices. Experiments on large-scale video anomaly dataset UCF-Crime demonstrate that the proposed network can achieve an impressive inference speed of 266 FPS on a GTX-1080Ti GPU, which is 4.29 faster than ConvLSTM-based method; a 3.34% AUC improvement with 5.55% accuracy niche versus the 3D-CNN based approach; and at least 15k× parameter reduction and 228× storage compression over the RNN-based approaches. Moreover, the proposed framework has been realized on an ARM-core based IOT board with only 2.4W power consumption.-
dc.languageeng-
dc.publisherIEEE Computer Society. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000198-
dc.relation.ispartofDesign, Automation, and Test in Europe Conference and Exhibition Proceedings-
dc.rightsDesign, Automation, and Test in Europe Conference and Exhibition Proceedings. Copyright © I E E E Computer Society.-
dc.rights©2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectfeature extraction-
dc.subjectlearning (artificial intelligence)-
dc.subjectrecurrent neural nets-
dc.subjectvideo signal processing-
dc.subjectvideo surveillance-
dc.titleAn Anomaly Comprehension Neural Network for Surveillance Videos on Terminal Devices-
dc.typeConference_Paper-
dc.identifier.emailCheng, Y: cyuan328@hku.hk-
dc.identifier.emailWong, N: nwong@eee.hku.hk-
dc.identifier.authorityWong, N=rp00190-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.23919/DATE48585.2020.9116533-
dc.identifier.scopuseid_2-s2.0-85087400770-
dc.identifier.hkuros315888-
dc.identifier.spage1396-
dc.identifier.epage1401-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats