SegmentedFusion: 3D human body reconstruction using stitched bounding boxes

Shih Hsuan Yao, Diego Thomas, Akihiro Sugimoto, Shang Hong Lai, Rin Ichiro Taniguchi Kyushu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents SegmentedFusion, a method possessing the capability of reconstructing non-rigid 3D models of a human body by using a single depth camera with skeleton information. Our method estimates a dense volumetric 6D motion field that warps the integrated model into the live frame by segmenting a human body into different parts and building a canonical space for each part. The key feature of this work is that a deformed and connected canonical volume for each part is created, and it is used to integrate data. The dense volumetric warp field of one volume is represented efficiently by blending a few rigid transformations. Overall, SegmentedFusion is able to scan a non-rigidly deformed human surface as well as to estimate the dense motion field by using a consumer-grade depth camera. The experimental results demonstrate that SegmentedFusion is robust against fast inter-frame motion and topological changes. Since our method does not require prior assumption, SegmentedFusion can be applied to a wide range of human motions.

Original languageEnglish
Title of host publicationProceedings - 2018 International Conference on 3D Vision, 3DV 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages190-198
Number of pages9
ISBN (Electronic)9781538684252
DOIs
Publication statusPublished - Oct 12 2018
Event6th International Conference on 3D Vision, 3DV 2018 - Verona, Italy
Duration: Sep 5 2018Sep 8 2018

Publication series

NameProceedings - 2018 International Conference on 3D Vision, 3DV 2018

Other

Other6th International Conference on 3D Vision, 3DV 2018
CountryItaly
CityVerona
Period9/5/189/8/18

Fingerprint

Cameras

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Yao, S. H., Thomas, D., Sugimoto, A., Lai, S. H., & Kyushu, R. I. T. (2018). SegmentedFusion: 3D human body reconstruction using stitched bounding boxes. In Proceedings - 2018 International Conference on 3D Vision, 3DV 2018 (pp. 190-198). [8490969] (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/3DV.2018.00031

SegmentedFusion : 3D human body reconstruction using stitched bounding boxes. / Yao, Shih Hsuan; Thomas, Diego; Sugimoto, Akihiro; Lai, Shang Hong; Kyushu, Rin Ichiro Taniguchi.

Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 190-198 8490969 (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yao, SH, Thomas, D, Sugimoto, A, Lai, SH & Kyushu, RIT 2018, SegmentedFusion: 3D human body reconstruction using stitched bounding boxes. in Proceedings - 2018 International Conference on 3D Vision, 3DV 2018., 8490969, Proceedings - 2018 International Conference on 3D Vision, 3DV 2018, Institute of Electrical and Electronics Engineers Inc., pp. 190-198, 6th International Conference on 3D Vision, 3DV 2018, Verona, Italy, 9/5/18. https://doi.org/10.1109/3DV.2018.00031
Yao SH, Thomas D, Sugimoto A, Lai SH, Kyushu RIT. SegmentedFusion: 3D human body reconstruction using stitched bounding boxes. In Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 190-198. 8490969. (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018). https://doi.org/10.1109/3DV.2018.00031
Yao, Shih Hsuan ; Thomas, Diego ; Sugimoto, Akihiro ; Lai, Shang Hong ; Kyushu, Rin Ichiro Taniguchi. / SegmentedFusion : 3D human body reconstruction using stitched bounding boxes. Proceedings - 2018 International Conference on 3D Vision, 3DV 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 190-198 (Proceedings - 2018 International Conference on 3D Vision, 3DV 2018).
@inproceedings{3672252021024c9f9add1d2312c4da67,
title = "SegmentedFusion: 3D human body reconstruction using stitched bounding boxes",
abstract = "This paper presents SegmentedFusion, a method possessing the capability of reconstructing non-rigid 3D models of a human body by using a single depth camera with skeleton information. Our method estimates a dense volumetric 6D motion field that warps the integrated model into the live frame by segmenting a human body into different parts and building a canonical space for each part. The key feature of this work is that a deformed and connected canonical volume for each part is created, and it is used to integrate data. The dense volumetric warp field of one volume is represented efficiently by blending a few rigid transformations. Overall, SegmentedFusion is able to scan a non-rigidly deformed human surface as well as to estimate the dense motion field by using a consumer-grade depth camera. The experimental results demonstrate that SegmentedFusion is robust against fast inter-frame motion and topological changes. Since our method does not require prior assumption, SegmentedFusion can be applied to a wide range of human motions.",
author = "Yao, {Shih Hsuan} and Diego Thomas and Akihiro Sugimoto and Lai, {Shang Hong} and Kyushu, {Rin Ichiro Taniguchi}",
year = "2018",
month = "10",
day = "12",
doi = "10.1109/3DV.2018.00031",
language = "English",
series = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "190--198",
booktitle = "Proceedings - 2018 International Conference on 3D Vision, 3DV 2018",
address = "United States",

}

TY - GEN

T1 - SegmentedFusion

T2 - 3D human body reconstruction using stitched bounding boxes

AU - Yao, Shih Hsuan

AU - Thomas, Diego

AU - Sugimoto, Akihiro

AU - Lai, Shang Hong

AU - Kyushu, Rin Ichiro Taniguchi

PY - 2018/10/12

Y1 - 2018/10/12

N2 - This paper presents SegmentedFusion, a method possessing the capability of reconstructing non-rigid 3D models of a human body by using a single depth camera with skeleton information. Our method estimates a dense volumetric 6D motion field that warps the integrated model into the live frame by segmenting a human body into different parts and building a canonical space for each part. The key feature of this work is that a deformed and connected canonical volume for each part is created, and it is used to integrate data. The dense volumetric warp field of one volume is represented efficiently by blending a few rigid transformations. Overall, SegmentedFusion is able to scan a non-rigidly deformed human surface as well as to estimate the dense motion field by using a consumer-grade depth camera. The experimental results demonstrate that SegmentedFusion is robust against fast inter-frame motion and topological changes. Since our method does not require prior assumption, SegmentedFusion can be applied to a wide range of human motions.

AB - This paper presents SegmentedFusion, a method possessing the capability of reconstructing non-rigid 3D models of a human body by using a single depth camera with skeleton information. Our method estimates a dense volumetric 6D motion field that warps the integrated model into the live frame by segmenting a human body into different parts and building a canonical space for each part. The key feature of this work is that a deformed and connected canonical volume for each part is created, and it is used to integrate data. The dense volumetric warp field of one volume is represented efficiently by blending a few rigid transformations. Overall, SegmentedFusion is able to scan a non-rigidly deformed human surface as well as to estimate the dense motion field by using a consumer-grade depth camera. The experimental results demonstrate that SegmentedFusion is robust against fast inter-frame motion and topological changes. Since our method does not require prior assumption, SegmentedFusion can be applied to a wide range of human motions.

UR - http://www.scopus.com/inward/record.url?scp=85056791907&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056791907&partnerID=8YFLogxK

U2 - 10.1109/3DV.2018.00031

DO - 10.1109/3DV.2018.00031

M3 - Conference contribution

AN - SCOPUS:85056791907

T3 - Proceedings - 2018 International Conference on 3D Vision, 3DV 2018

SP - 190

EP - 198

BT - Proceedings - 2018 International Conference on 3D Vision, 3DV 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -