Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378233602> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4378233602 endingPage "e1401" @default.
- W4378233602 startingPage "e1401" @default.
- W4378233602 abstract "Model-based 3D pose estimation has been widely used in many 3D human motion analysis applications, in which vision-based and inertial-based are two distinct lines. Multi-view images in a vision-based markerless capture system provide essential data for motion analysis, but erroneous estimates still occur due to ambiguities, occlusion, or noise in images. Besides, the multi-view setting is hard for the application in the wild. Although inertial measurement units (IMUs) can obtain accurate direction without occlusion, they are usually susceptible to magnetic field interference and drifts. Hybrid motion capture has drawn the attention of researchers in recent years. Existing 3D pose estimation methods jointly optimize the parameters of the 3D pose by minimizing the discrepancy between the image and IMU data. However, these hybrid methods still suffer from the issues such as complex peripheral devices, sensitivity to initialization, and slow convergence.This article presents an approach to improve 3D human pose estimation by fusing a single image with sparse inertial measurement units (IMUs). Based on a dual-stream feature extract network, we design a model-attention network with a residual module to closely couple the dual-modal feature from a static image and sparse inertial measurement units. The final 3D pose and shape parameters are directly obtained by a regression strategy.Extensive experiments are conducted on two benchmark datasets for 3D human pose estimation. Compared to state-of-the-art methods, the per vertex error (PVE) of human mesh reduces by 9.4 mm on Total Capture dataset and the mean per joint position error (MPJPE) reduces by 7.8 mm on the Human3.6M dataset. The quantitative comparison demonstrates that the proposed method could effectively fuse sparse IMU data and images and improve pose accuracy." @default.
- W4378233602 created "2023-05-26" @default.
- W4378233602 creator A5020141096 @default.
- W4378233602 creator A5028279763 @default.
- W4378233602 creator A5037731599 @default.
- W4378233602 creator A5050959786 @default.
- W4378233602 creator A5052662600 @default.
- W4378233602 creator A5087622441 @default.
- W4378233602 date "2023-05-24" @default.
- W4378233602 modified "2023-10-16" @default.
- W4378233602 title "Reconstructing 3D human pose and shape from a single image and sparse IMUs" @default.
- W4378233602 cites W1967554269 @default.
- W4378233602 cites W2064675550 @default.
- W4378233602 cites W2101032778 @default.
- W4378233602 cites W2131389448 @default.
- W4378233602 cites W2131774270 @default.
- W4378233602 cites W2135533529 @default.
- W4378233602 cites W2333544554 @default.
- W4378233602 cites W2810607340 @default.
- W4378233602 cites W2891718801 @default.
- W4378233602 cites W2898073175 @default.
- W4378233602 cites W2994660296 @default.
- W4378233602 cites W2997288107 @default.
- W4378233602 cites W3084394676 @default.
- W4378233602 cites W3089173771 @default.
- W4378233602 cites W3113581368 @default.
- W4378233602 cites W3180730526 @default.
- W4378233602 cites W4312896572 @default.
- W4378233602 doi "https://doi.org/10.7717/peerj-cs.1401" @default.
- W4378233602 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37346531" @default.
- W4378233602 hasPublicationYear "2023" @default.
- W4378233602 type Work @default.
- W4378233602 citedByCount "0" @default.
- W4378233602 crossrefType "journal-article" @default.
- W4378233602 hasAuthorship W4378233602A5020141096 @default.
- W4378233602 hasAuthorship W4378233602A5028279763 @default.
- W4378233602 hasAuthorship W4378233602A5037731599 @default.
- W4378233602 hasAuthorship W4378233602A5050959786 @default.
- W4378233602 hasAuthorship W4378233602A5052662600 @default.
- W4378233602 hasAuthorship W4378233602A5087622441 @default.
- W4378233602 hasBestOaLocation W43782336021 @default.
- W4378233602 hasConcept C104114177 @default.
- W4378233602 hasConcept C114466953 @default.
- W4378233602 hasConcept C131979681 @default.
- W4378233602 hasConcept C13280743 @default.
- W4378233602 hasConcept C138885662 @default.
- W4378233602 hasConcept C153180895 @default.
- W4378233602 hasConcept C154945302 @default.
- W4378233602 hasConcept C185798385 @default.
- W4378233602 hasConcept C199360897 @default.
- W4378233602 hasConcept C205649164 @default.
- W4378233602 hasConcept C2776401178 @default.
- W4378233602 hasConcept C31972630 @default.
- W4378233602 hasConcept C36613465 @default.
- W4378233602 hasConcept C41008148 @default.
- W4378233602 hasConcept C41895202 @default.
- W4378233602 hasConcept C48007421 @default.
- W4378233602 hasConcept C52102323 @default.
- W4378233602 hasConcept C79061980 @default.
- W4378233602 hasConceptScore W4378233602C104114177 @default.
- W4378233602 hasConceptScore W4378233602C114466953 @default.
- W4378233602 hasConceptScore W4378233602C131979681 @default.
- W4378233602 hasConceptScore W4378233602C13280743 @default.
- W4378233602 hasConceptScore W4378233602C138885662 @default.
- W4378233602 hasConceptScore W4378233602C153180895 @default.
- W4378233602 hasConceptScore W4378233602C154945302 @default.
- W4378233602 hasConceptScore W4378233602C185798385 @default.
- W4378233602 hasConceptScore W4378233602C199360897 @default.
- W4378233602 hasConceptScore W4378233602C205649164 @default.
- W4378233602 hasConceptScore W4378233602C2776401178 @default.
- W4378233602 hasConceptScore W4378233602C31972630 @default.
- W4378233602 hasConceptScore W4378233602C36613465 @default.
- W4378233602 hasConceptScore W4378233602C41008148 @default.
- W4378233602 hasConceptScore W4378233602C41895202 @default.
- W4378233602 hasConceptScore W4378233602C48007421 @default.
- W4378233602 hasConceptScore W4378233602C52102323 @default.
- W4378233602 hasConceptScore W4378233602C79061980 @default.
- W4378233602 hasLocation W43782336021 @default.
- W4378233602 hasLocation W43782336022 @default.
- W4378233602 hasOpenAccess W4378233602 @default.
- W4378233602 hasPrimaryLocation W43782336021 @default.
- W4378233602 hasRelatedWork W2099272513 @default.
- W4378233602 hasRelatedWork W2556085923 @default.
- W4378233602 hasRelatedWork W2756935747 @default.
- W4378233602 hasRelatedWork W2768816801 @default.
- W4378233602 hasRelatedWork W290666912 @default.
- W4378233602 hasRelatedWork W2997897143 @default.
- W4378233602 hasRelatedWork W3089173771 @default.
- W4378233602 hasRelatedWork W4290774832 @default.
- W4378233602 hasRelatedWork W4378233602 @default.
- W4378233602 hasRelatedWork W54333131 @default.
- W4378233602 hasVolume "9" @default.
- W4378233602 isParatext "false" @default.
- W4378233602 isRetracted "false" @default.
- W4378233602 workType "article" @default.