Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on

Bibliographic Details
Title: Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on
Authors: Duan, Di, Lyu, Shengzhe, Yuan, Mu, Xue, Hongfei, Li, Tianxing, Xu, Weitao, Wu, Kaishun, Xing, Guoliang
Publication Year: 2024
Collection: Computer Science
Subject Terms: Computer Science - Human-Computer Interaction, C.3
More Details: In this paper, we propose Argus, a wearable add-on system based on stripped-down (i.e., compact, lightweight, low-power, limited-capability) mmWave radars. It is the first to achieve egocentric human mesh reconstruction in a multi-view manner. Compared with conventional frontal-view mmWave sensing solutions, it addresses several pain points, such as restricted sensing range, occlusion, and the multipath effect caused by surroundings. To overcome the limited capabilities of the stripped-down mmWave radars (with only one transmit antenna and three receive antennas), we tackle three main challenges and propose a holistic solution, including tailored hardware design, sophisticated signal processing, and a deep neural network optimized for high-dimensional complex point clouds. Extensive evaluation shows that Argus achieves performance comparable to traditional solutions based on high-capability mmWave radars, with an average vertex error of 6.5 cm, solely using stripped-down radars deployed in a multi-view configuration. It presents robustness and practicality across conditions, such as with unseen users and different host devices.
Comment: 15 pages, 25 figures
Document Type: Working Paper
Access URL: http://arxiv.org/abs/2411.00419
Accession Number: edsarx.2411.00419
Database: arXiv
FullText Text:
  Availability: 0
CustomLinks:
  – Url: http://arxiv.org/abs/2411.00419
    Name: EDS - Arxiv
    Category: fullText
    Text: View this record from Arxiv
    MouseOverText: View this record from Arxiv
  – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20241101&spage=&pages=&title=Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on&atitle=Argus%3A%20Multi-View%20Egocentric%20Human%20Mesh%20Reconstruction%20Based%20on%20Stripped-Down%20Wearable%20mmWave%20Add-on&aulast=Duan%2C%20Di&id=DOI:
    Name: Full Text Finder (for New FTF UI) (s8985755)
    Category: fullText
    Text: Find It @ SCU Libraries
    MouseOverText: Find It @ SCU Libraries
Header DbId: edsarx
DbLabel: arXiv
An: edsarx.2411.00419
RelevancyScore: 1128
AccessLevel: 3
PubType: Report
PubTypeId: report
PreciseRelevancyScore: 1128.02990722656
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Duan%2C+Di%22">Duan, Di</searchLink><br /><searchLink fieldCode="AR" term="%22Lyu%2C+Shengzhe%22">Lyu, Shengzhe</searchLink><br /><searchLink fieldCode="AR" term="%22Yuan%2C+Mu%22">Yuan, Mu</searchLink><br /><searchLink fieldCode="AR" term="%22Xue%2C+Hongfei%22">Xue, Hongfei</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Tianxing%22">Li, Tianxing</searchLink><br /><searchLink fieldCode="AR" term="%22Xu%2C+Weitao%22">Xu, Weitao</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+Kaishun%22">Wu, Kaishun</searchLink><br /><searchLink fieldCode="AR" term="%22Xing%2C+Guoliang%22">Xing, Guoliang</searchLink>
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2024
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Computer Science
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Human-Computer+Interaction%22">Computer Science - Human-Computer Interaction</searchLink><br /><searchLink fieldCode="DE" term="%22C%2E3%22">C.3</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: In this paper, we propose Argus, a wearable add-on system based on stripped-down (i.e., compact, lightweight, low-power, limited-capability) mmWave radars. It is the first to achieve egocentric human mesh reconstruction in a multi-view manner. Compared with conventional frontal-view mmWave sensing solutions, it addresses several pain points, such as restricted sensing range, occlusion, and the multipath effect caused by surroundings. To overcome the limited capabilities of the stripped-down mmWave radars (with only one transmit antenna and three receive antennas), we tackle three main challenges and propose a holistic solution, including tailored hardware design, sophisticated signal processing, and a deep neural network optimized for high-dimensional complex point clouds. Extensive evaluation shows that Argus achieves performance comparable to traditional solutions based on high-capability mmWave radars, with an average vertex error of 6.5 cm, solely using stripped-down radars deployed in a multi-view configuration. It presents robustness and practicality across conditions, such as with unseen users and different host devices.<br />Comment: 15 pages, 25 figures
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Working Paper
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2411.00419" linkWindow="_blank">http://arxiv.org/abs/2411.00419</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsarx.2411.00419
PLink https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2411.00419
RecordInfo BibRecord:
  BibEntity:
    Subjects:
      – SubjectFull: Computer Science - Human-Computer Interaction
        Type: general
      – SubjectFull: C.3
        Type: general
    Titles:
      – TitleFull: Argus: Multi-View Egocentric Human Mesh Reconstruction Based on Stripped-Down Wearable mmWave Add-on
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Duan, Di
      – PersonEntity:
          Name:
            NameFull: Lyu, Shengzhe
      – PersonEntity:
          Name:
            NameFull: Yuan, Mu
      – PersonEntity:
          Name:
            NameFull: Xue, Hongfei
      – PersonEntity:
          Name:
            NameFull: Li, Tianxing
      – PersonEntity:
          Name:
            NameFull: Xu, Weitao
      – PersonEntity:
          Name:
            NameFull: Wu, Kaishun
      – PersonEntity:
          Name:
            NameFull: Xing, Guoliang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Type: published
              Y: 2024
ResultId 1