Digitize Your Body and Action in 3-D at Over 10 FPS: Real Time Dense Voxel Reconstruction and Marker-less Motion Tracking via GPU Acceleration

by   Jian Song, et al.

In this paper, we present an approach to reconstruct 3-D human motion from multi-cameras and track human skeleton using the reconstructed human 3-D point (voxel) cloud. We use an improved and more robust algorithm, probabilistic shape from silhouette to reconstruct human voxel. In addition, the annealed particle filter is applied for tracking, where the measurement is computed using the reprojection of reconstructed voxel. We use two different ways to accelerate the approach. For the CPU only acceleration, we leverage Intel TBB to speed up the hot spot of the computational overhead and reached an accelerating ratio of 3.5 on a 4-core CPU. Moreover, we implement an intensively paralleled version via GPU acceleration without TBB. Taking account all data transfer and computing time, the GPU version is about 400 times faster than the original CPU implementation, leading the approach to run at a real-time speed.



There are no comments yet.


page 6

page 12

page 13

page 15


Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction

State-of-the-art methods for large-scale 3D reconstruction from RGB-D se...

Real-time Crowd Tracking using Parameter Optimized Mixture of Motion Models

We present a novel, real-time algorithm to track the trajectory of each ...

GPU Accelerated Voxel Grid Generation for Fast MAV Exploration

Voxel grids are a minimal and efficient environment representation that ...

3D Fluid Flow Estimation with Integrated Particle Reconstruction

The standard approach to densely reconstruct the motion in a volume of f...

Computer methods for 3D motion tracking in real-time

This thesis is devoted to marker-less 3D human motion tracking in calibr...

GPU-accelerated machine learning inference as a service for computing in neutrino experiments

Machine learning algorithms are becoming increasingly prevalent and perf...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.