Panoptic Studio: A Massively Multiview System for Social Interaction Capture

12/09/2016
by   Hanbyul Joo, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 6

page 9

page 12

page 14

research
01/05/2018

Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies

We present a unified deformation model for the markerless capture of mul...
research
04/13/2016

Learning Social Affordance for Human-Robot Interaction

In this paper, we present an approach for robot learning of social affor...
research
12/14/2021

EgoBody: Human Body Shape, Motion and Social Interactions from Head-Mounted Devices

Understanding social interactions from first-person views is crucial for...
research
09/30/2021

HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge

This paper presents a new large multiview dataset called HUMBI for human...
research
06/15/2023

Generative Proxemics: A Prior for 3D Social Interaction from Images

Social interaction is a fundamental aspect of human behavior and communi...
research
07/26/2022

Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation

Body language is an eye-catching social signal and its automatic analysi...
research
04/04/2023

Random graphical model of microbiome interactions in related environments

The microbiome constitutes a complex microbial ecology of interacting co...

Please sign up or login with your details

Forgot password? Click here to reset