Fall Detection Using Multi-Property Spatiotemporal Autoencoders in Maritime Environments
Man overboard is an emergency in which fast and efficient detection of the critical event is the key factor for the recovery of the victim. Its severity urges the utilization of intelligent video surveillance systems that monitor the ship’s perimeter in real time and trigger the relative alarms that...
Saved in:
Published in | Technologies (Basel) Vol. 10; no. 2; p. 47 |
---|---|
Main Authors | , , , , |
Format | Journal Article |
Language | English |
Published |
Basel
MDPI AG
01.04.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Man overboard is an emergency in which fast and efficient detection of the critical event is the key factor for the recovery of the victim. Its severity urges the utilization of intelligent video surveillance systems that monitor the ship’s perimeter in real time and trigger the relative alarms that initiate the rescue mission. In terms of deep learning analysis, since man overboard incidents occur rarely, they present a severe class imbalance problem, and thus, supervised classification methods are not suitable. To tackle this obstacle, we follow an alternative philosophy and present a novel deep learning framework that formulates man overboard identification as an anomaly detection task. The proposed system, in the absence of training data, utilizes a multi-property spatiotemporal convolutional autoencoder that is trained only on the normal situation. We explore the use of RGB video sequences to extract specific properties of the scene, such as gradient and saliency, and utilize the autoencoders to detect anomalies. To the best of our knowledge, this is the first time that man overboard detection is made in a fully unsupervised manner while jointly learning the spatiotemporal features from RGB video streams. The algorithm achieved 97.30% accuracy and a 96.01% F1-score, surpassing the other state-of-the-art approaches significantly. |
---|---|
AbstractList | Man overboard is an emergency in which fast and efficient detection of the critical event is the key factor for the recovery of the victim. Its severity urges the utilization of intelligent video surveillance systems that monitor the ship’s perimeter in real time and trigger the relative alarms that initiate the rescue mission. In terms of deep learning analysis, since man overboard incidents occur rarely, they present a severe class imbalance problem, and thus, supervised classification methods are not suitable. To tackle this obstacle, we follow an alternative philosophy and present a novel deep learning framework that formulates man overboard identification as an anomaly detection task. The proposed system, in the absence of training data, utilizes a multi-property spatiotemporal convolutional autoencoder that is trained only on the normal situation. We explore the use of RGB video sequences to extract specific properties of the scene, such as gradient and saliency, and utilize the autoencoders to detect anomalies. To the best of our knowledge, this is the first time that man overboard detection is made in a fully unsupervised manner while jointly learning the spatiotemporal features from RGB video streams. The algorithm achieved 97.30% accuracy and a 96.01% F1-score, surpassing the other state-of-the-art approaches significantly. |
Author | Bakalos, Nikolaos Katsamenis, Iason Doulamis, Anastasios Karolou, Eleni Eirini Doulamis, Nikolaos |
Author_xml | – sequence: 1 givenname: Iason orcidid: 0000-0001-9339-1546 surname: Katsamenis fullname: Katsamenis, Iason – sequence: 2 givenname: Nikolaos surname: Bakalos fullname: Bakalos, Nikolaos – sequence: 3 givenname: Eleni Eirini surname: Karolou fullname: Karolou, Eleni Eirini – sequence: 4 givenname: Anastasios surname: Doulamis fullname: Doulamis, Anastasios – sequence: 5 givenname: Nikolaos orcidid: 0000-0002-4064-8990 surname: Doulamis fullname: Doulamis, Nikolaos |
BookMark | eNptkU9LAzEQxYMoWGu_gYcFz6uz-bObPZbaaqFFwQreQpJNa8o2WZNU6Ld3tSIenMsMM4_fG3gX6NR5ZxC6KuCGkBpuk9Fvzrd-Y00sADAArU7QAGNc5RVwOP0zn6NRjFvoqy4IL9kAvc5k22Z3pqck6132Eq3bZMt9m2z-FHxnQjpkz53sj8nsOh9km433yRunfWNCzKzLljLYZHcmm7oPG7zbGZfiJTpbyzaa0U8fotVsupo85IvH-_lkvMg1wUXKmW4IlYqTuqaVpliRqqGYKspAycboSmtK2Rr4WtWKKsVYwYCZAte8VI0mQzQ_Yhsvt6ILdifDQXhpxffCh42QIVndGsGZVFJXtK5kSVXZAwgDzjkByRqgsmddH1ld8O97E5PY-n1w_fcCl4wALmnBehU9qnTwMQaz_nUtQHwlIv5LhHwCn3WENA |
CitedBy_id | crossref_primary_10_1155_2022_9325803 crossref_primary_10_1016_j_jreng_2024_01_005 crossref_primary_10_1515_ijeeps_2023_0143 |
Cites_doi | 10.1109/ICEE50131.2020.9261057 10.3906/elk-1308-154 10.1109/COASE.2017.8256202 10.1145/3054977.3057314 10.1007/978-3-319-71249-9_3 10.5244/C.29.8 10.1109/ICCV.2013.22 10.1109/THS.2007.370022 10.1007/s11042-012-0993-4 10.1109/WACV.2017.118 10.1109/CVPR.2007.383197 10.1016/j.icte.2017.11.016 10.1016/j.cviu.2016.10.010 10.1109/TCCN.2020.2999479 10.1109/TPAMI.2012.261 10.1007/s10586-017-1117-8 10.3390/electronics10111345 10.1145/1877868.1877880 10.1109/ICCV.2013.257 10.1007/978-3-319-46454-1_21 10.1109/ICCVW.2017.330 10.1109/TCSVT.2011.2129370 10.1145/3123266.3123451 10.1007/978-3-319-93659-8_53 10.1145/3389189.3397997 10.1109/TPAMI.2021.3054775 10.1007/978-3-642-21735-7_7 10.1109/IWAIT.2018.8369778 10.1109/ICIP.2018.8451070 10.1016/j.compbiomed.2019.103520 10.1109/BigData.2018.8622342 10.1016/j.patrec.2017.07.016 10.1007/978-3-030-64556-4_13 10.1109/IWSSIP.2019.8787213 10.1109/ICORR.2019.8779504 10.1109/TITB.2012.2214786 10.1109/ICIP.2019.8803671 10.5244/C.31.139 10.1016/j.autcon.2022.104182 10.1109/ICPR48806.2021.9412632 10.23919/MVA.2017.7986795 10.1109/CVPRW.2011.5981811 10.1109/TCSVT.2013.2280061 10.1109/CVPR.2016.86 10.1007/s41666-019-00061-4 10.1109/EMBC.2018.8512586 10.1145/3389189.3397998 10.1109/SSRR50563.2020.9292632 10.1007/s11042-015-2513-9 10.1109/TIP.2017.2670780 10.1007/s11042-012-0994-3 10.1007/978-3-540-24670-1_6 10.1007/s12652-022-03728-w 10.1109/VS-GAMES.2017.8056576 10.1109/CISP-BMEI.2017.8302004 10.1109/ICCV.2017.315 10.1109/DICTA.2018.8615759 10.1109/MSP.2018.2885359 10.1109/JBHI.2018.2808281 10.1109/TIP.2008.2012070 10.1109/ICMEW.2018.8551564 10.1177/1550147717703257 10.1016/j.cviu.2019.102897 |
ContentType | Journal Article |
Copyright | 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | AAYXX CITATION 8FD 8FE 8FG ABJCF ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU D1I DWQXO F28 FR3 GNUQQ HCIFZ JQ2 K7- KB. L6V M7S P5Z P62 PDBOC PIMPY PQEST PQQKQ PQUKI PTHSS DOA |
DOI | 10.3390/technologies10020047 |
DatabaseName | CrossRef Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Aerospace Collection ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Materials Science Collection ProQuest Central ANTE: Abstracts in New Technology & Engineering Engineering Research Database ProQuest Central Student SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Computer Science Collection Computer Science Database ProQuest Materials Science Database ProQuest Engineering Collection ProQuest Engineering Database ProQuest Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Materials Science Collection Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition Engineering Collection Directory of Open Access Journals |
DatabaseTitle | CrossRef Publicly Available Content Database Computer Science Database ProQuest Central Student Technology Collection Technology Research Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Materials Science Collection ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central ProQuest Engineering Collection ProQuest Central Korea Materials Science Database Engineering Collection ANTE: Abstracts in New Technology & Engineering ProQuest Materials Science Collection Advanced Technologies & Aerospace Collection Engineering Database ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition Materials Science & Engineering Collection Engineering Research Database ProQuest One Academic |
DatabaseTitleList | Publicly Available Content Database CrossRef |
Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2227-7080 |
ExternalDocumentID | oai_doaj_org_article_85abac7497a64b698635088830a5d04a 10_3390_technologies10020047 |
GroupedDBID | 5VS 8FE 8FG AADQD AAFWJ AAYXX ABJCF ADBBV AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS ARAPS BCNDV BENPR BGLVJ CCPQU CITATION CZ9 D1I GROUPED_DOAJ HCIFZ IAO K6V K7- KB. KC. KQ8 L6V M7S MODMG M~E OK1 P62 PDBOC PIMPY PROAC PTHSS 8FD ABUWG AZQEC DWQXO F28 FR3 GNUQQ JQ2 PQEST PQQKQ PQUKI |
ID | FETCH-LOGICAL-c321t-5cd34ab839947c42b37d424b450badec7cc445f08fb9b4bb551505e12986bdc3 |
IEDL.DBID | DOA |
ISSN | 2227-7080 |
IngestDate | Tue Oct 22 15:16:28 EDT 2024 Thu Oct 10 19:23:38 EDT 2024 Wed Jul 31 12:47:34 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 2 |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c321t-5cd34ab839947c42b37d424b450badec7cc445f08fb9b4bb551505e12986bdc3 |
ORCID | 0000-0001-9339-1546 0000-0002-4064-8990 |
OpenAccessLink | https://doaj.org/article/85abac7497a64b698635088830a5d04a |
PQID | 2653026415 |
PQPubID | 2032323 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_85abac7497a64b698635088830a5d04a proquest_journals_2653026415 crossref_primary_10_3390_technologies10020047 |
PublicationCentury | 2000 |
PublicationDate | 2022-04-01 |
PublicationDateYYYYMMDD | 2022-04-01 |
PublicationDate_xml | – month: 04 year: 2022 text: 2022-04-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Basel |
PublicationPlace_xml | – name: Basel |
PublicationTitle | Technologies (Basel) |
PublicationYear | 2022 |
Publisher | MDPI AG |
Publisher_xml | – name: MDPI AG |
References | ref_50 Katsamenis (ref_5) 2022; 137 Yu (ref_34) 2012; 16 ref_58 ref_13 ref_12 ref_56 ref_11 ref_55 ref_10 ref_54 ref_52 ref_51 ref_17 Kwon (ref_7) 2019; 22 ref_16 ref_15 Lu (ref_47) 2019; 23 Zhao (ref_14) 2020; 6 Yang (ref_27) 2013; 35 Sheu (ref_75) 2020; 32 Karaca (ref_2) 2016; 24 Chen (ref_9) 2020; 192 ref_25 Dutta (ref_57) 2015; Volume 29 ref_69 ref_24 ref_68 Chowdhury (ref_20) 2018; 4 ref_23 ref_22 Lin (ref_46) 2018; 34 ref_66 ref_21 Jiang (ref_60) 2009; 18 ref_65 ref_64 ref_63 Sabokrou (ref_70) 2017; 26 ref_62 ref_29 ref_28 Voulodimos (ref_30) 2014; 69 ref_26 Xu (ref_67) 2017; 156 ref_72 Lalos (ref_8) 2014; 69 ref_71 ref_36 ref_35 ref_77 ref_76 ref_31 Mo (ref_59) 2014; 24 Ribeiro (ref_61) 2018; 105 ref_74 Baccouche (ref_18) 2012; Volume 1 Espinosa (ref_38) 2019; 115 ref_39 Tsai (ref_53) 2019; 7 ref_37 Rougier (ref_33) 2011; 21 ref_45 Hsieh (ref_40) 2017; 6 ref_44 ref_43 ref_42 ref_41 ref_1 Makantasis (ref_32) 2016; 75 ref_3 ref_49 Bakalos (ref_73) 2019; 36 ref_48 ref_4 Nogas (ref_19) 2020; 4 ref_6 |
References_xml | – ident: ref_69 doi: 10.1109/ICEE50131.2020.9261057 – volume: 24 start-page: 762 year: 2016 ident: ref_2 article-title: Design and Implementation of a Man-Overboard Emergency Discovery System Based on Wireless Sensor Networks publication-title: Turk. J. Electr. Eng. Comput. Sci. doi: 10.3906/elk-1308-154 contributor: fullname: Karaca – ident: ref_48 doi: 10.1109/COASE.2017.8256202 – ident: ref_41 doi: 10.1145/3054977.3057314 – ident: ref_62 doi: 10.1007/978-3-319-71249-9_3 – ident: ref_72 doi: 10.5244/C.29.8 – ident: ref_28 doi: 10.1109/ICCV.2013.22 – ident: ref_4 doi: 10.1109/THS.2007.370022 – volume: 69 start-page: 293 year: 2014 ident: ref_30 article-title: A Top-down Event-Driven Approach for Concurrent Activity Recognition publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-012-0993-4 contributor: fullname: Voulodimos – ident: ref_66 doi: 10.1109/WACV.2017.118 – ident: ref_16 – ident: ref_26 doi: 10.1109/CVPR.2007.383197 – ident: ref_42 – ident: ref_1 – volume: 4 start-page: 216 year: 2018 ident: ref_20 article-title: Human Detection Utilizing Adaptive Background Mixture Models and Improved Histogram of Oriented Gradients publication-title: ICT Express. doi: 10.1016/j.icte.2017.11.016 contributor: fullname: Chowdhury – volume: 156 start-page: 117 year: 2017 ident: ref_67 article-title: Detecting Anomalous Events in Videos by Learning Deep Representations of Appearance and Motion publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2016.10.010 contributor: fullname: Xu – volume: 6 start-page: 1146 year: 2020 ident: ref_14 article-title: Lightweight Deep Learning Based Intelligent Edge Surveillance Techniques publication-title: IEEE Trans. Cogn. Commun. Netw. doi: 10.1109/TCCN.2020.2999479 contributor: fullname: Zhao – volume: 35 start-page: 2878 year: 2013 ident: ref_27 article-title: Articulated Human Detection with Flexible Mixtures of Parts publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2012.261 contributor: fullname: Yang – volume: 22 start-page: 949 year: 2019 ident: ref_7 article-title: A Survey of Deep Learning-Based Network Anomaly Detection publication-title: Cluster Comput. doi: 10.1007/s10586-017-1117-8 contributor: fullname: Kwon – ident: ref_76 doi: 10.3390/electronics10111345 – ident: ref_31 doi: 10.1145/1877868.1877880 – ident: ref_52 – ident: ref_29 doi: 10.1109/ICCV.2013.257 – ident: ref_56 doi: 10.1007/978-3-319-46454-1_21 – ident: ref_23 doi: 10.1109/ICCVW.2017.330 – volume: 21 start-page: 611 year: 2011 ident: ref_33 article-title: Robust Video Surveillance for Fall Detection Based on Human Shape Deformation publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2011.2129370 contributor: fullname: Rougier – ident: ref_68 doi: 10.1145/3123266.3123451 – volume: 34 start-page: 577 year: 2018 ident: ref_46 article-title: Convolutional recurrent neural networks for posture analysis in fall detection publication-title: J. Inf. Sci. Eng. contributor: fullname: Lin – volume: 6 start-page: 6048 year: 2017 ident: ref_40 article-title: Development of home intelligent fall detection IoT system based on feedback optical flow convolutional neural network publication-title: IEEE Access Pract. Innov. Open Solut. contributor: fullname: Hsieh – ident: ref_50 doi: 10.1007/978-3-319-93659-8_53 – ident: ref_12 doi: 10.1145/3389189.3397997 – volume: Volume 1 start-page: 12 year: 2012 ident: ref_18 article-title: Spatio-Temporal Convolutional Sparse Auto-Encoder for Sequence Classification publication-title: Proceedings of the British Machine Vision Conference contributor: fullname: Baccouche – ident: ref_11 doi: 10.1109/TPAMI.2021.3054775 – volume: 32 start-page: 197 year: 2020 ident: ref_75 article-title: Real-Time Alarm, Dynamic GPS Tracking, and Monitoring System for Man Overboard publication-title: Sens. Mater. contributor: fullname: Sheu – ident: ref_17 doi: 10.1007/978-3-642-21735-7_7 – ident: ref_45 doi: 10.1109/IWAIT.2018.8369778 – ident: ref_71 doi: 10.1109/ICIP.2018.8451070 – volume: 115 start-page: 103520 year: 2019 ident: ref_38 article-title: A vision-based approach for fall detection using multiple cameras and convolutional neural networks: A case study using the UP-Fall detection dataset publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2019.103520 contributor: fullname: Espinosa – ident: ref_49 doi: 10.1109/BigData.2018.8622342 – volume: 105 start-page: 13 year: 2018 ident: ref_61 article-title: A Study of Deep Convolutional Auto-Encoders for Anomaly Detection in Videos publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2017.07.016 contributor: fullname: Ribeiro – ident: ref_6 doi: 10.1007/978-3-030-64556-4_13 – ident: ref_37 doi: 10.1109/IWSSIP.2019.8787213 – volume: Volume 29 start-page: 3755 year: 2015 ident: ref_57 article-title: Online Detection of Abnormal Events Using Incremental Coding Length publication-title: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence contributor: fullname: Dutta – ident: ref_44 doi: 10.1109/ICORR.2019.8779504 – volume: 16 start-page: 1274 year: 2012 ident: ref_34 article-title: A Posture Recognition Based Fall Detection System for Monitoring an Elderly Person in a Smart Home Environment publication-title: IEEE Trans. Inf. Technol. Biomed. doi: 10.1109/TITB.2012.2214786 contributor: fullname: Yu – ident: ref_63 – ident: ref_54 doi: 10.1109/ICIP.2019.8803671 – ident: ref_64 doi: 10.5244/C.31.139 – volume: 137 start-page: 104182 year: 2022 ident: ref_5 article-title: Simultaneous Precise Localization and Classification of metal rust defects for robotic-driven maintenance and prefabrication using residual attention U-Net publication-title: Autom. Constr. doi: 10.1016/j.autcon.2022.104182 contributor: fullname: Katsamenis – ident: ref_21 – ident: ref_74 doi: 10.1109/ICPR48806.2021.9412632 – ident: ref_36 doi: 10.23919/MVA.2017.7986795 – ident: ref_25 doi: 10.1109/CVPRW.2011.5981811 – volume: 24 start-page: 631 year: 2014 ident: ref_59 article-title: Adaptive Sparse Representations for Video Anomaly Detection publication-title: IEEE Trans. Circuits Syst. Video Technol. doi: 10.1109/TCSVT.2013.2280061 contributor: fullname: Mo – ident: ref_65 doi: 10.1109/CVPR.2016.86 – volume: 4 start-page: 50 year: 2020 ident: ref_19 article-title: DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal Convolutional Autoencoders publication-title: J. Healthc. Inform. Res. doi: 10.1007/s41666-019-00061-4 contributor: fullname: Nogas – ident: ref_39 doi: 10.1109/EMBC.2018.8512586 – ident: ref_3 doi: 10.1145/3389189.3397998 – ident: ref_13 doi: 10.1109/SSRR50563.2020.9292632 – volume: 75 start-page: 15017 year: 2016 ident: ref_32 article-title: 3D Measures Exploitation for a Monocular Semi-Supervised Fall Detection System publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-015-2513-9 contributor: fullname: Makantasis – volume: 26 start-page: 1992 year: 2017 ident: ref_70 article-title: Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2017.2670780 contributor: fullname: Sabokrou – volume: 69 start-page: 277 year: 2014 ident: ref_8 article-title: Efficient Tracking Using a Robust Motion Estimation Technique publication-title: Multimed. Tools Appl. doi: 10.1007/s11042-012-0994-3 contributor: fullname: Lalos – ident: ref_24 doi: 10.1007/978-3-540-24670-1_6 – ident: ref_77 doi: 10.1007/s12652-022-03728-w – ident: ref_10 doi: 10.1109/VS-GAMES.2017.8056576 – ident: ref_15 – ident: ref_43 doi: 10.1109/CISP-BMEI.2017.8302004 – ident: ref_58 doi: 10.1109/ICCV.2017.315 – ident: ref_35 doi: 10.1109/DICTA.2018.8615759 – volume: 36 start-page: 36 year: 2019 ident: ref_73 article-title: Protecting Water Infrastructure from Cyber and Physical Threats: Using Multimodal Data Fusion and Adaptive Deep Learning to Monitor Critical Systems publication-title: IEEE Signal Process. Mag. doi: 10.1109/MSP.2018.2885359 contributor: fullname: Bakalos – volume: 23 start-page: 314 year: 2019 ident: ref_47 article-title: Deep learning for fall detection: Three-dimensional CNN combined with LSTM on video kinematic data publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2808281 contributor: fullname: Lu – volume: 18 start-page: 907 year: 2009 ident: ref_60 article-title: A Dynamic Hierarchical Clustering Method for Trajectory-Based Unusual Video Event Detection publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2008.2012070 contributor: fullname: Jiang – volume: 7 start-page: 153049 year: 2019 ident: ref_53 article-title: Implementation of fall detection system based on 3D skeleton for deep learning technique publication-title: IEEE Access Pract. Innov. Open Solut. contributor: fullname: Tsai – ident: ref_55 doi: 10.1109/ICMEW.2018.8551564 – ident: ref_22 – ident: ref_51 doi: 10.1177/1550147717703257 – volume: 192 start-page: 102897 year: 2020 ident: ref_9 article-title: Monocular Human Pose Estimation: A Survey of Deep Learning-Based Methods publication-title: Comput. Vis. Image Underst. doi: 10.1016/j.cviu.2019.102897 contributor: fullname: Chen |
SSID | ssj0000913865 |
Score | 2.2608442 |
Snippet | Man overboard is an emergency in which fast and efficient detection of the critical event is the key factor for the recovery of the victim. Its severity urges... |
SourceID | doaj proquest crossref |
SourceType | Open Website Aggregation Database |
StartPage | 47 |
SubjectTerms | Algorithms Anomalies computer vision convolutional autoencoder Datasets Deep learning Fall detection Machine learning man overboard Neural networks Sensors spatiotemporal data Surveillance Surveillance systems unsupervised learning Video data |
SummonAdditionalLinks | – databaseName: AUTh Library subscriptions: ProQuest Central dbid: BENPR link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NT8IwFG8ULnowfkYUTQ9eF8b61nUnIwohJhCimHBb2q4zJjgUx8H_3r5SEKPxssPWbMtr3_d7v0fIlbBysZ0XPOBhJAMA3bYsZS9JkgocRMCNQ7wZDHn_Ce4n8cQH3D58WeVKJjpBnc80xshbEcf5Ntzqm-u39wCnRmF21Y_Q2Cb1qA2Ypq13usPRwzrKgqiXgsfLnjlm_ftWtYpYW0cU4UcRLvGHTnLQ_b8ks1M3vX2y5-1EerPc2AOyZcpDsruBHnhEJj05ndI7U7lqqpK67D91HbXBCGPs8-qTPrqKaQ9AZd-3qGYIXYnly_SlpAOJoEavhnY3Gt6OybjXHd_2Az8oIdAsaldBrHMGUllbJ4VEQ6RYkkMECuJQydzoRGuAuAhFoVIFSlkryRo-xqp6wVWu2QmplbPSnBKqZZ4WwAsmjRWhsVTS-rCp0kIwUaRGNEiwolT2toTDyKwbgZTN_qJsg3SQnOu1CGbtbszmz5nnjUzgd3QCaSI5KG5_iqHZKFgo4zwE2SDN1WZknsM-su_zcPb_43OyE2HLgqu2aZJaNV-YC2tIVOrSn5YvpnLKjQ priority: 102 providerName: ProQuest |
Title | Fall Detection Using Multi-Property Spatiotemporal Autoencoders in Maritime Environments |
URI | https://www.proquest.com/docview/2653026415 https://doaj.org/article/85abac7497a64b698635088830a5d04a |
Volume | 10 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8NAEB60XvQgPrE-yh68huax2ewerTYWoaVohd7C7mYDQk2lpgf_vbObVCIKXrzkEEISvsnOfLOZ-QbgmqNfDPKCecwPpUepDnBJ4SFJBLeDCJhxijfjCRs904d5PG-N-rI1YbU8cA1cn8dSSZ1QkUhGFRMcIySuDB75Ms59WlOjIG4lU84Hi8AOs6x75SLM6_vVZqcaE1ArO2plEr_FIifZ_8MjuzCTHsB-ww_JTf1eh7BlyiPYa6kGHsM8lYsFuTOVq6IqifvrT1wnrTe1e-ur6oM8uUrpRngK77eullay0pYtk5eSjKUVM3o1ZNhqdDuBWTqc3Y68ZkCCp6MwqLxY5xGVCjmOoImmoYqSnIZU0dhXMjc60ZrSuPB5oYSiSiE7QsJjMMRzpnIdnUKnXJbmDIiWuSgoKyJp0HVayDF3FUojzrwQhnfB2yCVvdUyGBmmDxbZ7DdkuzCwcH5da0Ws3Qk0bdaYNvvLtF243Bgja1bWexYyO-eIIe84_49nXMBuaBsaXC3OJXSq1dpcIc2oVA-2eXrfg53BcDJ97Lnv6xOnstNF |
link.rule.ids | 315,786,790,870,2115,12792,21416,27955,27956,33406,33777,43633,43838,74390,74657 |
linkProvider | Directory of Open Access Journals |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NT8IwFG8UD-rB-BlR1B68Loz1retOxg8QFYiJmHBb2q4zJjgQxsH_3r4yUKPxssPWbMvr--57v0fIubB6sZFm3ON-ID0A3bAiZS9RFAscRMCNQ7zp9nj7Ge4H4aBMuE3LssqFTnSKOh1pzJHXA47zbbi1Nxfjdw-nRuHpajlCY5WsAeMM-Vy0bpc5FsS8FDycd8wxG93Xi0W-2oahCD6KYIk_LJID7v-ll52xaW2TrdJLpJfzbd0hKybfJZvfsAP3yKAlh0N6YwpXS5VTd_ZPXT-t94gZ9knxQZ9cvXQJP2XfNytGCFyJxcv0NaddiZBGb4Y2v7W77ZN-q9m_bnvlmARPs6BReKFOGUhlPZ0YIg2BYlEKASgIfSVToyOtAcLMF5mKFShlfSTr9hhr6AVXqWYHpJKPcnNIqJZpnAHPmDRWgYZSSRvBxkoLwUQWG1El3oJSyXgOhpHYIAIpm_xF2Sq5QnIu1yKUtbsxmrwkpWQkAr-jI4gjyUFx-1MMnUbBfBmmPsgqqS02Iynla5p8ccPR_4_PyHq73-0knbvewzHZCLB5wdXd1EilmMzMiXUpCnXq-OYT3bfMFA |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3JTsMwELVYJAQHxCoKBXzgGjWNHcc5Ibawo0oUqbfIdhyEVNLSpgf-nhnXZRGISw5JlERje-Z58uYNIUcS_GK7KEUgwkgFnJs2LCk4JEkqsRGBsE7x5v5BXD3xm17c8_ynsadVznyic9TFwGCOvBUJ7G8jIN60Sk-L6Jxnx8O3ADtI4Z9W305jniwiyMY2DjK7_My3oP6lFPG0eo7B9VY9y13DlhSFSFE48Ud0ciL-v3y0CzzZGln1iJGeTId4nczZaoOsfNMR3CS9TPX79NzWjldVUccDoK62Nuhgtn1Uv9NHx532UlTwvEk9QBFLJDLTl4reK5Q3erX04lvp2xbpZhfds6vAt0wIDIvadRCbgnGlAfWkPDE80iwpeMQ1j0OtCmsSYziPy1CWOtVca8BLAIEsBH0pdGHYNlmoBpXdIdSoIi25KJmy4ExjpRXsZlNtpGSyTK1skGBmqXw4FcbIYUOBls3_smyDnKI5P-9FWWt3YjB6zv0qySW-xyQ8TZTgWsBHMQSQkoUqLkKuGqQ5G4zcr7Vx_jUzdv-_fEiWYMrkd9cPt3tkOcI6BkfBaZKFejSx-4Auan3gps0HGsvQSQ |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Fall+Detection+Using+Multi-Property+Spatiotemporal+Autoencoders+in+Maritime+Environments&rft.jtitle=Technologies+%28Basel%29&rft.au=Iason+Katsamenis&rft.au=Nikolaos+Bakalos&rft.au=Eleni+Eirini+Karolou&rft.au=Anastasios+Doulamis&rft.date=2022-04-01&rft.pub=MDPI+AG&rft.eissn=2227-7080&rft.volume=10&rft.issue=2&rft.spage=47&rft_id=info:doi/10.3390%2Ftechnologies10020047&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_85abac7497a64b698635088830a5d04a |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2227-7080&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2227-7080&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2227-7080&client=summon |