Literature DB >> 29990012

Panoptic Studio: A Massively Multiview System for Social Interaction Capture.

Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart Nabbe, Iain Matthews, Takeo Kanade, Shohei Nobuhara, Yaser Sheikh.   

Abstract

We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. Our algorithm is designed to fuse the "weak" perceptual processes in the large number of views by progressively generating skeletal proposals from low-level appearance cues, and a framework for temporal refinement is also presented by associating body parts to reconstructed dense 3D trajectory stream. Our system and method are the first in reconstructing full body motion of more than five people engaged in social interactions without using markers. We also empirically demonstrate the impact of the number of views in achieving this goal.

Entities:  

Year:  2017        PMID: 29990012     DOI: 10.1109/TPAMI.2017.2782743

Source DB:  PubMed          Journal:  IEEE Trans Pattern Anal Mach Intell        ISSN: 0098-5589            Impact factor:   6.226


  8 in total

1.  3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View.

Authors:  Marc Badger; Yufu Wang; Adarsh Modh; Ammon Perkes; Nikos Kolotouros; Bernd G Pfrommer; Marc F Schmidt; Kostas Daniilidis
Journal:  Comput Vis ECCV       Date:  2020-12-04

2.  Accuracy of Monocular Two-Dimensional Pose Estimation Compared With a Reference Standard for Kinematic Multiview Analysis: Validation Study.

Authors:  Oskar Stamm; Anika Heimann-Steinert
Journal:  JMIR Mhealth Uhealth       Date:  2020-12-21       Impact factor: 4.773

3.  Semantically Synchronizing Multiple-Camera Systems with Human Pose Estimation.

Authors:  Zhe Zhang; Chunyu Wang; Wenhu Qin
Journal:  Sensors (Basel)       Date:  2021-04-02       Impact factor: 3.576

4.  sSfS: Segmented Shape from Silhouette Reconstruction of the Human Body.

Authors:  Wiktor Krajnik; Łukasz Markiewicz; Robert Sitnik
Journal:  Sensors (Basel)       Date:  2022-01-25       Impact factor: 3.576

5.  Pose2Sim: An End-to-End Workflow for 3D Markerless Sports Kinematics-Part 2: Accuracy.

Authors:  David Pagnon; Mathieu Domalain; Lionel Reveret
Journal:  Sensors (Basel)       Date:  2022-04-01       Impact factor: 3.576

6.  Center point to pose: Multiple views 3D human pose estimation for multi-person.

Authors:  Huan Liu; Jian Wu; Rui He
Journal:  PLoS One       Date:  2022-09-13       Impact factor: 3.752

7.  A multi-camera and multimodal dataset for posture and gait analysis.

Authors:  Manuel Palermo; João M Lopes; João André; Ana C Matias; João Cerqueira; Cristina P Santos
Journal:  Sci Data       Date:  2022-10-06       Impact factor: 8.501

8.  A Baseline for Cross-Database 3D Human Pose Estimation.

Authors:  Michał Rapczyński; Philipp Werner; Sebastian Handrich; Ayoub Al-Hamadi
Journal:  Sensors (Basel)       Date:  2021-05-28       Impact factor: 3.576

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.