Falling motion detection algorithm based on deep learning
Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical health problems due to the fall, so fall detection is necessary. The traditional fall detection methods are mostly based on wearable devices,...
Saved in:
Published in | IET image processing Vol. 16; no. 11; pp. 2845 - 2853 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Wiley
01.09.2022
|
Online Access | Get full text |
Cover
Loading…
Abstract | Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical health problems due to the fall, so fall detection is necessary. The traditional fall detection methods are mostly based on wearable devices, which need to be worn all the time, and the cost of the device is high. In recent years, the fall detection method based on computer vision has become a research hot spot. This paper proposes a framework for falling motion detection based on deep learning. To quickly and accurately classify human movements, a method using bone key points as the feature descriptors of human movements is proposed. The OpenPose algorithm is used to extract the human skeleton point information as the primary human body feature, and then use the deep learning method to classify further and recognise our action features. In this paper, four types of daily actions, such as falling and walking, are classified and recognised. The results show that the algorithm achieves an accuracy of 99.4% on our dataset. Simultaneously, 86.1% accuracy is reached in the public dataset fall detection dataset. |
---|---|
AbstractList | Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical health problems due to the fall, so fall detection is necessary. The traditional fall detection methods are mostly based on wearable devices, which need to be worn all the time, and the cost of the device is high. In recent years, the fall detection method based on computer vision has become a research hot spot. This paper proposes a framework for falling motion detection based on deep learning. To quickly and accurately classify human movements, a method using bone key points as the feature descriptors of human movements is proposed. The OpenPose algorithm is used to extract the human skeleton point information as the primary human body feature, and then use the deep learning method to classify further and recognise our action features. In this paper, four types of daily actions, such as falling and walking, are classified and recognised. The results show that the algorithm achieves an accuracy of 99.4% on our dataset. Simultaneously, 86.1% accuracy is reached in the public dataset fall detection dataset. Abstract Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical health problems due to the fall, so fall detection is necessary. The traditional fall detection methods are mostly based on wearable devices, which need to be worn all the time, and the cost of the device is high. In recent years, the fall detection method based on computer vision has become a research hot spot. This paper proposes a framework for falling motion detection based on deep learning. To quickly and accurately classify human movements, a method using bone key points as the feature descriptors of human movements is proposed. The OpenPose algorithm is used to extract the human skeleton point information as the primary human body feature, and then use the deep learning method to classify further and recognise our action features. In this paper, four types of daily actions, such as falling and walking, are classified and recognised. The results show that the algorithm achieves an accuracy of 99.4% on our dataset. Simultaneously, 86.1% accuracy is reached in the public dataset fall detection dataset. |
Author | Zhu, Na Zhao, Guangzhe Zhang, Xiaolong Jin, Zhexue |
Author_xml | – sequence: 1 givenname: Na surname: Zhu fullname: Zhu, Na organization: Beijing University of Civil Engineering and Architecture – sequence: 2 givenname: Guangzhe orcidid: 0000-0002-6850-9335 surname: Zhao fullname: Zhao, Guangzhe organization: Beijing University of Civil Engineering and Architecture – sequence: 3 givenname: Xiaolong surname: Zhang fullname: Zhang, Xiaolong organization: Beijing Academy of Artifivial Intellgence – sequence: 4 givenname: Zhexue surname: Jin fullname: Jin, Zhexue email: jinzhexue@ybu.edu.cn organization: Yanbian University |
BookMark | eNp9kE9Lw0AUxBepYFu9-AlyFlJ3k7f_jlKsFgqK6HnZTV7iljRbNgHptzdNpEdPb5g38zvMgsza0CIh94yuGAX96I8xW7Eso-qKzJnkLNVCyNlFc31DFl23p5Rrqvic6I1tGt_WySH0PrRJiT0Wo7JNHaLvvw-Jsx2WyfjEY9Kgje3QuCXXlW06vPu7S_K1ef5cv6a7t5ft-mmXFrnkKgXFWO6wULa0qHO0GpxzvJLUgYPBowCyEg4Gg5WVoJozmTmF1EmBqsyXZDtxy2D35hj9wcaTCdab0QixNjb2vmjQAFAhQRYiUwXojGkQzGoUSgoAzqqB9TCxihi6LmJ14TFqzgOa84BmHHAIsyn84xs8_ZM02_ePbOr8AmOwczE |
CitedBy_id | crossref_primary_10_3390_s22113991 crossref_primary_10_3389_fmats_2023_1269992 crossref_primary_10_3390_make5010020 crossref_primary_10_1108_IJWIS_01_2023_0006 crossref_primary_10_1007_s11042_024_18305_w crossref_primary_10_3390_s23042153 |
Cites_doi | 10.1109/ACCESS.2018.2861331 10.1016/j.physa.2019.123205 10.1007/978-3-030-38748-8_5 10.1109/ICIEA.2014.6931308 10.1109/MPRV.2016.27 10.5815/ijigsp.2015.12.05 10.1109/MMUL.2012.24 10.1007/978-3-319-46448-0_2 10.3758/BF03212378 10.1007/978-981-10-8663-2_23 10.1007/s11760-019-01490-9 10.1109/TPAMI.2019.2929257 10.1109/AVSS.2014.6918647 10.1007/978-981-32-9291-8_33 10.3390/s17092096 10.3390/s18041101 10.23919/MVA.2017.7986795 10.23919/ChiCC.2019.8865732 10.1177/1847979018787905 10.1371/journal.pone.0124068 10.1016/j.procs.2019.01.264 10.1016/j.cviu.2015.10.013 10.1109/TFUZZ.2016.2514366 10.1109/CVPR.2016.91 |
ContentType | Journal Article |
Copyright | 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. |
Copyright_xml | – notice: 2021 The Authors. published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology. |
DBID | 24P WIN AAYXX CITATION DOA |
DOI | 10.1049/ipr2.12208 |
DatabaseName | Wiley-Blackwell Open Access Collection Wiley Online Library Free Content CrossRef Directory of Open Access Journals |
DatabaseTitle | CrossRef |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 24P name: Wiley-Blackwell Open Access Collection url: https://authorservices.wiley.com/open-science/open-access/browse-journals.html sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Applied Sciences |
EISSN | 1751-9667 |
EndPage | 2853 |
ExternalDocumentID | oai_doaj_org_article_4406747c628c49219461a9e68764451f 10_1049_ipr2_12208 IPR212208 |
Genre | article |
GrantInformation_xml | – fundername: National Aerospace Science Foundation of China funderid: 61871021 |
GroupedDBID | .DC 0R~ 1OC 24P 29I 5GY 6IK 8VB AAHHS AAHJG AAJGR ABQXS ACCFJ ACESK ACGFS ACIWK ACXQS ADZOD AEEZP AENEX AEQDE AIWBW AJBDE ALMA_UNASSIGNED_HOLDINGS ALUQN AVUZU CS3 DU5 EBS ESX GROUPED_DOAJ HZ~ IAO IFIPE IPLJI JAVBF K1G LAI MCNEO MS~ O9- OCL OK1 P2P QWB RIE RNS ROL RUI WIN ZL0 4.4 8FE 8FG AAYXX ABJCF AFKRA ARAPS BENPR BGLVJ CCPQU CITATION EJD HCIFZ ITC L6V M43 M7S P62 PTHSS S0W |
ID | FETCH-LOGICAL-c3758-48113bec8adae93ea94bbb5f70b4b4dae0447f6b470b1df6095172b8e0b76e8d3 |
IEDL.DBID | 24P |
ISSN | 1751-9659 |
IngestDate | Fri Oct 04 13:14:06 EDT 2024 Thu Sep 26 16:57:47 EDT 2024 Sat Aug 24 00:55:15 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 11 |
Language | English |
License | Attribution |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c3758-48113bec8adae93ea94bbb5f70b4b4dae0447f6b470b1df6095172b8e0b76e8d3 |
ORCID | 0000-0002-6850-9335 |
OpenAccessLink | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fipr2.12208 |
PageCount | 9 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_4406747c628c49219461a9e68764451f crossref_primary_10_1049_ipr2_12208 wiley_primary_10_1049_ipr2_12208_IPR212208 |
PublicationCentury | 2000 |
PublicationDate | 2022-09-01 |
PublicationDateYYYYMMDD | 2022-09-01 |
PublicationDate_xml | – month: 09 year: 2022 text: 2022-09-01 day: 01 |
PublicationDecade | 2020 |
PublicationTitle | IET image processing |
PublicationYear | 2022 |
Publisher | Wiley |
Publisher_xml | – name: Wiley |
References | 2015; 12 2015; 5 2019; 13 1973; 14 2015; 10 2008 2016; 144 2012; 19 2019; 147 2016; 15 2018; 6 2018; 18 2020; A 540 2017; 17 2020 2019; 43 2019 2018 2017 2016 2015 2014 2018; 10 2016; 24 2020; 29 e_1_2_7_6_1 e_1_2_7_5_1 e_1_2_7_4_1 e_1_2_7_3_1 e_1_2_7_9_1 e_1_2_7_8_1 e_1_2_7_7_1 e_1_2_7_18_1 e_1_2_7_17_1 e_1_2_7_16_1 e_1_2_7_2_1 e_1_2_7_15_1 e_1_2_7_14_1 e_1_2_7_13_1 e_1_2_7_12_1 e_1_2_7_11_1 e_1_2_7_10_1 e_1_2_7_27_1 e_1_2_7_28_1 e_1_2_7_29_1 Iqbal J.M. (e_1_2_7_19_1) 2015; 5 e_1_2_7_25_1 e_1_2_7_24_1 e_1_2_7_23_1 e_1_2_7_22_1 e_1_2_7_21_1 e_1_2_7_20_1 Farzad A. (e_1_2_7_26_1) 2015; 12 Abedi W.M.S. (e_1_2_7_30_1) 2020; 29 |
References_xml | – volume: 43 start-page: 172 year: 2019 end-page: 186 article-title: Openpose: realtime multi‐person 2d pose estimation using part affinity fields publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 10 start-page: 1 year: 2015 end-page: 16 article-title: Remote safety monitoring for elderly persons based on omni‐vision analysis publication-title: PloS One – volume: A 540 start-page: 123205 year: 2020 end-page: 123218 article-title: Fall prediction based on key points of human bones publication-title: Physica – start-page: 994 year: 2014 end-page: 997 article-title: An efficient camera‐based surveillance for fall detection of elderly people – volume: 17 start-page: 2096 year: 2017 end-page: 2111 article-title: Highly portable, sensor‐based system for human fall monitoring publication-title: Sensors – volume: 6 start-page: 43563 year: 2018 end-page: 43574 article-title: A novel monitoring system for fall detection in older people publication-title: IEEE Access – volume: 147 start-page: 276 year: 2019 end-page: 282 article-title: A hog‐svm based fall detection IOT system for elderly persons using deep sensor publication-title: Procedia Comput. Sci. – volume: 10 start-page: 1847979018787905 year: 2018 end-page: 1847979018787912 article-title: An artificial neural network–based fall detection publication-title: Int. J. Eng. Bus. Manage. – volume: 18 start-page: 1101 year: 2018 end-page: 1119 article-title: Real‐life/real‐time elderly fall detection with a triaxial accelerometer publication-title: Sensors – start-page: 217 year: 2019 end-page: 234 – volume: 5 start-page: 3748 year: 2015 end-page: 3751 article-title: Abnormal human activity recognition using scale invariant feature transform publication-title: International Journal of Current Engineering and Technology – volume: 14 start-page: 201 year: 1973 end-page: 211 article-title: Visual perception of biological motion and a model for its analysis publication-title: Perception & Psychophysics – volume: 15 start-page: 40 year: 2016 end-page: 47 article-title: Floor pressure imaging for fall detection with fiber‐optic sensors publication-title: IEEE Pervasive Comput. – year: 2018 – volume: 12 start-page: 31 year: 2015 end-page: 38 article-title: Recognition and classification of human behavior in intelligent surveillance systems using hidden markov model publication-title: IJ Image, Graphics and Signal Processing – start-page: 21 year: 2016 end-page: 37 article-title: Ssd: single shot multibox detector – volume: 144 start-page: 46 year: 2016 end-page: 61 article-title: Activity detection using sequential statistical boundary detection (SSBD) publication-title: Comput. Vision Image Understanding – volume: 29 start-page: 3830 year: 2020 end-page: 3841 article-title: Modified deep learning method for body postures recognition publication-title: International Journal of Advanced Science and Technology – start-page: 417 year: 2020 end-page: 429 article-title: Activity recognition for indoor fall detection in 360‐degree videos using deep learning techniques – volume: 24 start-page: 1307 year: 2016 end-page: 1319 article-title: A big bang–big crunch type2 fuzzy logic system for machine‐vision‐based event detection and summarization in real‐world ambient‐assisted living publication-title: IEEE Trans. Fuzzy Syst. – year: 2008 – start-page: 97 year: 2020 end-page: 120 – start-page: 779 year: 2016 end-page: 788 article-title: You only look once: Unified, real‐time object detection – start-page: 336 year: 2015 end-page: 341 article-title: Recognition of abnormal human activity using the changes in orientation of silhouette in key frames – volume: 13 start-page: 1431 year: 2019 end-page: 1439 article-title: Comprehensive evaluation of skeleton features‐based fall detection from microsoft kinect v2 publication-title: Signal, Image and Video Processing – volume: 19 start-page: 4 year: 2012 end-page: 10 article-title: Microsoft kinect sensor and its effect publication-title: IEEE Multimedia – start-page: 8488 year: 2019 end-page: 8493 article-title: Human posture recognition and fall detection using kinect v2 camera – start-page: 81 year: 2017 end-page: 84 article-title: Activity recognition for indoor fall detection using convolutional neural network – start-page: 74 year: 2014 end-page: 80 article-title: Real‐time life logging via a depth silhouette‐based human activity recognition system for smart home services – ident: e_1_2_7_7_1 doi: 10.1109/ACCESS.2018.2861331 – ident: e_1_2_7_12_1 doi: 10.1016/j.physa.2019.123205 – ident: e_1_2_7_11_1 doi: 10.1007/978-3-030-38748-8_5 – volume: 5 start-page: 3748 year: 2015 ident: e_1_2_7_19_1 article-title: Abnormal human activity recognition using scale invariant feature transform publication-title: International Journal of Current Engineering and Technology contributor: fullname: Iqbal J.M. – ident: e_1_2_7_13_1 doi: 10.1109/ICIEA.2014.6931308 – ident: e_1_2_7_6_1 doi: 10.1109/MPRV.2016.27 – volume: 12 start-page: 31 year: 2015 ident: e_1_2_7_26_1 article-title: Recognition and classification of human behavior in intelligent surveillance systems using hidden markov model publication-title: IJ Image, Graphics and Signal Processing doi: 10.5815/ijigsp.2015.12.05 contributor: fullname: Farzad A. – ident: e_1_2_7_23_1 doi: 10.1109/MMUL.2012.24 – ident: e_1_2_7_25_1 – ident: e_1_2_7_16_1 doi: 10.1007/978-3-319-46448-0_2 – ident: e_1_2_7_17_1 – ident: e_1_2_7_20_1 doi: 10.3758/BF03212378 – ident: e_1_2_7_5_1 doi: 10.1007/978-981-10-8663-2_23 – ident: e_1_2_7_22_1 doi: 10.1007/s11760-019-01490-9 – ident: e_1_2_7_24_1 doi: 10.1109/TPAMI.2019.2929257 – ident: e_1_2_7_28_1 doi: 10.1109/AVSS.2014.6918647 – ident: e_1_2_7_2_1 – ident: e_1_2_7_10_1 doi: 10.1007/978-981-32-9291-8_33 – ident: e_1_2_7_3_1 doi: 10.3390/s17092096 – ident: e_1_2_7_4_1 doi: 10.3390/s18041101 – ident: e_1_2_7_8_1 doi: 10.23919/MVA.2017.7986795 – ident: e_1_2_7_9_1 doi: 10.23919/ChiCC.2019.8865732 – ident: e_1_2_7_29_1 doi: 10.1177/1847979018787905 – ident: e_1_2_7_14_1 doi: 10.1371/journal.pone.0124068 – ident: e_1_2_7_27_1 doi: 10.1016/j.procs.2019.01.264 – volume: 29 start-page: 3830 year: 2020 ident: e_1_2_7_30_1 article-title: Modified deep learning method for body postures recognition publication-title: International Journal of Advanced Science and Technology contributor: fullname: Abedi W.M.S. – ident: e_1_2_7_18_1 doi: 10.1016/j.cviu.2015.10.013 – ident: e_1_2_7_21_1 doi: 10.1109/TFUZZ.2016.2514366 – ident: e_1_2_7_15_1 doi: 10.1109/CVPR.2016.91 |
SSID | ssj0059085 |
Score | 2.3712103 |
Snippet | Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have physical... Abstract Falling is a significant cause of injuries and even death in the elderly. The timely detection of the fall action helps to rescue people who may have... |
SourceID | doaj crossref wiley |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 2845 |
SummonAdditionalLinks | – databaseName: Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PS8MwFA6ykxd_i_MXAT0JdWv6kjZHFcf0ICIOditJk0xBuzHn_-_LayfzohdvIS2kfC8v7wtNvo-xcx20hwCYaTK1CWhnEisKlVjpZQ4VBOdI7fNBDUdwP5bjFauveCaskQdugOsBVhykvJUSRQUa8wtUarRXmMVRWyvQ6pvK5WaqWYOjkbekq5DRRF5JvRQmBd17nc3FZSpENJRcKUWk2P-ToVKJGWyxjZYb8qvmm7bZmq932GbLE3mbhR-7TA8MKWnzxoKHO7-gA1U1N2-TKe72X955rE6O00M_4603xGSPjQa3zzfDpLVASKoMmXwCRZpmCHNhnPE680aDtVaGvG_BAvb1AfKgLGBH6kJUj0NGYgvft7nyhcv2Waee1v6AccitCZWSOGyBVTvTRjshMBTaSWzKLjtbolHOGqWLkv5Qgy4jZiVh1mXXEajvN6I6NXVgzMo2ZuVfMeuyC4L5l3HKu8cnQa3D_xjxiK2LeG-BDocds85i_ulPkE0s7ClNnC8Qy8Hm priority: 102 providerName: Directory of Open Access Journals |
Title | Falling motion detection algorithm based on deep learning |
URI | https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fipr2.12208 https://doaj.org/article/4406747c628c49219461a9e68764451f |
Volume | 16 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA6lXrz4FuujBPQkrHazk2wCXlQs1YMUsdDbkmySKui21Pr_nWS3lV4Eb2E2S2CSmflmN_MNIRfKKwce0NJ4ahJQVieGSZEY7ngOJXhrI9vnsxiM4GnMxy1ys6yFqfkhVh_cgmVEfx0MXJu6CwmCWtzE99mcXaWMhUrfDcQ1MpxpBsOlHw7NvHkshwyN5AVXS3JSUNe_766Fo8jav45SY5jp75CtBh_S23pDd0nLVXtku8GKtLHEr32i-jqyadO6DQ-1bhEvVVVUf0ymmPG_fdIQoSyND92MNv0hJgdk1H94vR8kTRuEpMwQzScg0zRDVUtttVOZ0wqMMdznPQMGUNYDyL0wgILU-sAgh6jESNczuXDSZoekXU0rd0Qo5Eb7UnBcVmLkzpRWljHcDmU5DnmHnC-1Ucxqtosi_qUGVQSdFVFnHXIXFLWaERiqo2A6nxTNgS8AkQKmKqVgsgSFfhFEqpUT6H0DJ5rvkMuo5j_WKR6HLyyOjv8z-YRsslCjEC-CnZL2Yv7tzhA5LEw3HpBuzLt_AJpfvZA |
link.rule.ids | 315,786,790,870,2115,11589,27955,27956,46085,46509,50847,50956 |
linkProvider | Wiley-Blackwell |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5SD3rxLdZnQE_Cajc7yW6OKpZWaynSQm9LskmqoG2p9f-byW4rvQjeQjZLYJKZ-ZLMfEPIlXTSggOvaTzWEUijIs0yEWlueQoFOGMC22dXtAbwNOTDKjYHc2FKfojlhRtqRrDXqOB4IV0eOAFJMt-nM3YTM4apvuuATHBI7Ay9hSHGat485ENiJXnB5YKdFOTt778r_ijQ9q_C1OBnmjtkqwKI9K5c0V2yZsd7ZLsCi7RSxa99Ipsq0GnTsg4PNXYeoqrGVH2MJv7I__ZJ0UUZGj7aKa0KRIwOyKD52H9oRVUdhKhIPJyPIIvjxMs6U0ZZmVglQWvNXdrQoMH3NQBSJzT4jtg4pJDzsERntqFTYTOTHJLaeDK2R4RCqpUrBPfTZt51J1JJw5hfD2m4b_I6uVxII5-WdBd5eKYGmaPM8iCzOrlHQS1HIEV16JjMRnm143PwUMGfVQrBsgKkN4wgYiWt8OYXSdFcnVwHMf8xT97uvbLQOv7P4Auy0eq_dPJOu_t8QjYZJiyEqLBTUpvPvu2ZhxFzfR42yw9mpsAD |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwEA_iQHzxW5yfAX0Sqmt6SRvwZX6MTWUMcSK-lKRJpqDbmPP_95J2E18E38I1JXDJ3f2uzf2OkBPppAUHaGk81hFIoyLNMhFpbnkKBThjAttnV7T7cPvMnxfIxawWpuSHmH9w85YR_LU38LFxZb4JniPzbTxhZzFjvtK3hjADMPWqNZ_6L_2ZJ_btvHkoiPSt5AWXM3pSkOc_b_8KSIG3_zdODYGmtUZWKoRIm-WWrpMFO9wgqxVapJUtfm4S2VKBT5uWjXiosdNwrWpI1ftghDn_6wf1McrQ8NCOadUhYrBF-q2bx6t2VDVCiIoE8XwEWRwnqOxMGWVlYpUErTV3aUODBpQ1AFInNKAgNs5zyCEu0Zlt6FTYzCTbZHE4GtodQiHVyhWC47IZxu5EKmkYww2RhuOQ18nxTBv5uOS7yMN_apC511kedFYnl15R8xmeozoIRpNBXh35HBArYLJSCJYVINEzgoiVtAL9r2dFc3VyGtT8xzp5p_fAwmj3P5OPyFLvupXfd7p3e2SZ-YKFcCtsnyxOJ1_2AGHEVB9Wp-UbKanA-w |
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=Falling+motion+detection+algorithm+based+on+deep+learning&rft.jtitle=IET+image+processing&rft.au=Zhu%2C+Na&rft.au=Zhao%2C+Guangzhe&rft.au=Zhang%2C+Xiaolong&rft.au=Jin%2C+Zhexue&rft.date=2022-09-01&rft.issn=1751-9659&rft.eissn=1751-9667&rft.volume=16&rft.issue=11&rft.spage=2845&rft.epage=2853&rft_id=info:doi/10.1049%2Fipr2.12208&rft.externalDBID=10.1049%252Fipr2.12208&rft.externalDocID=IPR212208 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1751-9659&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1751-9659&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1751-9659&client=summon |