3D hypothesis clustering for cross-view matching in multi-person motion capture
Abstract We present a multiview method for markerless motion capture of multiple people. The main challenge in this problem is to determine cross-view correspondences for the 2D joints in the presence of noise. We propose a 3D hypothesis clustering technique to solve this problem. The core idea is t...
Main Authors: | Miaopeng Li, Zimeng Zhou, Xinguo Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2020-06-01
|
Series: | Computational Visual Media |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1007/s41095-020-0171-y |
Similar Items
-
Leveraging Two Kinect Sensors for Accurate Full-Body Motion Capture
by: Zhiquan Gao, et al.
Published: (2015-09-01) -
Visual Browse and Exploration in Motion Capture Data with Phylogenetic Tree of Context-Aware Poses
by: Songle Chen, et al.
Published: (2020-09-01) -
A survey on monocular 3D human pose estimation
by: Xiaopeng Ji, et al.
Published: (2020-12-01) -
Multi-View Pose Generator Based on Deep Learning for Monocular 3D Human Pose Estimation
by: Jun Sun, et al.
Published: (2020-07-01) -
Evaluation of 3D Markerless Motion Capture Accuracy Using OpenPose With Multiple Video Cameras
by: Nobuyasu Nakano, et al.
Published: (2020-05-01)