Elderly Fall Detection Algorithm Based on Improved YOLOv5s
The indoor fall detection for the elderly can effectively help the treatment after falling, but many existing detection methods have the problems of inconvenient use, high misjudgement rate and slow speed. Using deep learning methods can effectively solve these problems, and YOLOv5s is a kind of dee...
Uloženo v:
| Vydáno v: | Information technology and control Ročník 53; číslo 2; s. 601 - 618 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Kaunas University of Technology
26.06.2024
|
| Témata: | |
| ISSN: | 1392-124X, 2335-884X |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | The indoor fall detection for the elderly can effectively help the treatment after falling, but many existing detection methods have the problems of inconvenient use, high misjudgement rate and slow speed. Using deep learning methods can effectively solve these problems, and YOLOv5s is a kind of deep learning algorithm that can perform real-time fall detection. In order to achieve a more lightweight and higher detection accuracy, this paper proposes a fall detection algorithm for the elderly based on improved YOLOv5s, called YOLOv5s-GCC. Firstly, the original Conv and C3 structures are replaced by GhostConv and C3GhostV2 structures in backbone to achieve model lightweight, which reduces model computation and improves accuracy. Secondly, the lightweight upsampling operator CARAFE is introduced to expand the receptive field for data feature fusion and reduce the loss of feature information in upsampling. Finally, the deepest C3 is integrated with CBAM attention mechanism in the neck, because the deepest neck receives more abundant feature information, and CBAM can increase the efficiency of the algorithm in extracting important information from the feature map. Experimental results show that YOLOv5s-GCC has increased by 1.2% to 0.935 on the hybrid open source fall dataset mAP@0.5; FLOPs decreased by 29.1%. Params are reduced by 27.5% and have obvious advantages over
similar object detection algorithms. |
|---|---|
| AbstractList | The indoor fall detection for the elderly can effectively help the treatment after falling, but many existing detection methods have the problems of inconvenient use, high misjudgement rate and slow speed. Using deep learning methods can effectively solve these problems, and YOLOv5s is a kind of deep learning algorithm that can perform real-time fall detection. In order to achieve a more lightweight and higher detection accuracy, this paper proposes a fall detection algorithm for the elderly based on improved YOLOv5s, called YOLOv5s-GCC. Firstly, the original Conv and C3 structures are replaced by GhostConv and C3GhostV2 structures in backbone to achieve model lightweight, which reduces model computation and improves accuracy. Secondly, the lightweight upsampling operator CARAFE is introduced to expand the receptive field for data feature fusion and reduce the loss of feature information in upsampling. Finally, the deepest C3 is integrated with CBAM attention mechanism in the neck, because the deepest neck receives more abundant feature information, and CBAM can increase the efficiency of the algorithm in extracting important information from the feature map. Experimental results show that YOLOv5s-GCC has increased by 1.2% to 0.935 on the hybrid open source fall dataset mAP@0.5; FLOPs decreased by 29.1%. Params are reduced by 27.5% and have obvious advantages over
similar object detection algorithms. The indoor fall detection for the elderly can effectively help the treatment after falling, but many existing detection methods have the problems of inconvenient use, high misjudgement rate and slow speed. Using deep learning methods can effectively solve these problems, and YOLOv5s is a kind of deep learning algorithm that can perform real-time fall detection. In order to achieve a more lightweight and higher detection accuracy, this paper proposes a fall detection algorithm for the elderly based on improved YOLOv5s, called YOLOv5s-GCC. Firstly, the original Conv and C3 structures are replaced by GhostConv and C3GhostV2 structures in backbone to achieve model lightweight, which reduces model computation and improves accuracy. Secondly, the lightweight upsampling operator CARAFE is introduced to expand the receptive field for data feature fusion and reduce the loss of feature information in upsampling. Finally, the deepest C3 is integrated with CBAM attention mechanism in the neck, because the deepest neck receives more abundant feature information, and CBAM can increase the efficiency of the algorithm in extracting important information from the feature map. Experimental results show that YOLOv5s-GCC has increased by 1.2% to 0.935 on the hybrid open source fall dataset mAP@0.5; FLOPs decreased by 29.1%. Params are reduced by 27.5% and have obvious advantages oversimilar object detection algorithms. |
| Author | Dong, Guanghui Zhao, Yifu Jia, Siying Zeng, Xiaoyu Niu, Hongjun Luo, Zhongze |
| Author_xml | – sequence: 1 givenname: Zhongze surname: Luo fullname: Luo, Zhongze organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China – sequence: 2 givenname: Siying surname: Jia fullname: Jia, Siying organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China – sequence: 3 givenname: Hongjun surname: Niu fullname: Niu, Hongjun organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China – sequence: 4 givenname: Yifu surname: Zhao fullname: Zhao, Yifu organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China – sequence: 5 givenname: Xiaoyu surname: Zeng fullname: Zeng, Xiaoyu organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China – sequence: 6 givenname: Guanghui surname: Dong fullname: Dong, Guanghui organization: College of computer and control engineering, Northeast Forestry University, Harbin, 150040, China |
| BookMark | eNotkN1OAjEQRhuDiYi8gFfrA-zadrY_eIcISrIJN5rgVVPari6WXdIWEt7eVbj6Jl_mTCbnFg3arnUI3RNcMMHY4xaTokmmYFDQAjgAv0JDCsByKcv1AA0JTGhOaLm-QeMYtxhjyjCDkgzR09xbF_wpW2jvsxeXnElN12ZT_9WFJn3vsmcdnc36arnbh-7Yz5-ranVk8Q5d19pHN77kCH0s5u-zt7xavS5n0yo3lMuUG7kpRc20kBLXVJZCYsYAM2s11hq4xVI7IUStLVi-4UI6vplII4h1wk4ojBA93zWhizG4Wu1Ds9PhpAhWfwJUL0D1AhQDRdW_gB56OEM_6aC23SG0_YtKh9QY7y47v8zfXBc |
| ContentType | Journal Article |
| Copyright | Copyright (c) 2024 Information Technology and Control |
| Copyright_xml | – notice: Copyright (c) 2024 Information Technology and Control |
| DBID | AJMEP AAYXX CITATION |
| DOI | 10.5755/j01.itc.53.2.36336 |
| DatabaseName | Kaunas University of Technology Press Journals CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | CrossRef |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2335-884X |
| EndPage | 618 |
| ExternalDocumentID | 10_5755_j01_itc_53_2_36336 36336 |
| GroupedDBID | 5GY AAKPC AENEX AJMEP ALMA_UNASSIGNED_HOLDINGS GROUPED_DOAJ OK1 TR2 AAYXX CITATION |
| ID | FETCH-LOGICAL-c268t-c8b47f5a7880f28478055305dda0aa36d08ae777fad3d6b678e6b98c71de7d923 |
| ISICitedReferencesCount | 5 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001266770800019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1392-124X |
| IngestDate | Thu Oct 16 04:44:16 EDT 2025 Tue Jul 08 22:49:12 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| IssueTitle | Articles |
| Keywords | Improved YOLOv5s CARAFE Fall detection GhostNetV2 CBAM attention mechanism |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c268t-c8b47f5a7880f28478055305dda0aa36d08ae777fad3d6b678e6b98c71de7d923 |
| OpenAccessLink | http://dx.doi.org/10.5755/j01.itc.53.2.36336 |
| PageCount | 18 |
| ParticipantIDs | crossref_primary_10_5755_j01_itc_53_2_36336 ktu_journals_article_36336 |
| PublicationCentury | 2000 |
| PublicationDate | 20240626 |
| PublicationDateYYYYMMDD | 2024-06-26 |
| PublicationDate_xml | – month: 06 year: 2024 text: 20240626 day: 26 |
| PublicationDecade | 2020 |
| PublicationTitle | Information technology and control |
| PublicationTitleAbbrev | ITC |
| PublicationYear | 2024 |
| Publisher | Kaunas University of Technology |
| Publisher_xml | – name: Kaunas University of Technology |
| SSID | ssj0002505341 |
| Score | 2.3468764 |
| Snippet | The indoor fall detection for the elderly can effectively help the treatment after falling, but many existing detection methods have the problems of... |
| SourceID | crossref ktu |
| SourceType | Index Database Publisher |
| StartPage | 601 |
| Title | Elderly Fall Detection Algorithm Based on Improved YOLOv5s |
| URI | https://itc.ktu.lt/index.php/ITC/article/view/36336 |
| Volume | 53 |
| WOSCitedRecordID | wos001266770800019&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2335-884X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002505341 issn: 1392-124X databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Nb9MwFLe6jQMcEBsgNj6UA7fKJY0T2-E2YBOapm0S29TtYjmxs2aUdGqTauPKP87zR0PYQGIHLlH62j61fr-8L7_nh9BbnqW5ZCrHIeEUxzrmmBckxCnlioLCjId2SsTpPjs44KNRetTr_Vj2wiwmrKr49XV69V9FDTQQtmmdvYe4W6ZAgHsQOlxB7HD9J8HvmLnbk5v-rtl0_qRr7YaBb08uprOyHn_rfwDDpcwmgUsowP3Z4f7hIpl3HVXfpmS_Wrfpd98FZ6vb21KexmZbz8fT6uJ7C5M9V4T7pbxZ2ka7-dFYUwefvGxaVJ6PpeVwVhZNNwkRxaZYynW6e70JbhYGV2HkzIqlRYQkmHNP88rWnQzsQRV1NCf1OQ1nhKlTyrf1O_iW5iiMy3A4KOt8kJBBNCCUkD8cpn3LyLWlhxD0GC4CeAjgIRIiImF5rKC1iCUp78TlxpwbH5HELnD3f9I1Xxk27-7-lN8cnJWvddPxV46foMc-0Ai2HUDWUU9XG-hR5_jJp-i9h0pgoBK0UAlaqAQWKgGQllAJPFSeoZPdneOPn7GfpYHziPIa5zyLWZFIBvq6MC4JD83AqEQpGUpJqAq51IyxQiqiaAYujKZZynM2VJopiAKeo9VqWukXKCjgJbWBMPCkuc6IyozfXYRxEUnKNlF_uQDiyh2ZIv6-6ptoC9ZI-AdoLvxz497cuherl-jhL2y-Qqv1rNGv0YN8UZfz2Rsr1Z9_z2sH |
| linkProvider | Directory of Open Access Journals |
| 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=Elderly+Fall+Detection+Algorithm+Based+on+Improved+YOLOv5s&rft.jtitle=Information+technology+and+control&rft.au=Luo%2C+Zhongze&rft.au=Jia%2C+Siying&rft.au=Niu%2C+Hongjun&rft.au=Zhao%2C+Yifu&rft.date=2024-06-26&rft.issn=1392-124X&rft.eissn=2335-884X&rft.volume=53&rft.issue=2&rft.spage=601&rft.epage=618&rft_id=info:doi/10.5755%2Fj01.itc.53.2.36336&rft.externalDBID=n%2Fa&rft.externalDocID=10_5755_j01_itc_53_2_36336 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1392-124X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1392-124X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1392-124X&client=summon |