Marker-Less 3D Human Motion Capture in Real-Time Using Particle Swarm Optimization with GPU-Accelerated Fitness Function

@inproceedings{Kwolek2017MarkerLess3H,
  title={Marker-Less 3D Human Motion Capture in Real-Time Using Particle Swarm Optimization with GPU-Accelerated Fitness Function},
  author={Bogdan Kwolek and Boguslaw Rymut},
  booktitle={ICIG},
  year={2017}
}
In model-based 3D motion tracking the most computationally demanding operation is evaluation of the objective function, which expresses similarity between the projected 3D model and image observations. In this work, marker-less tracking of full body has been realized in a multi-camera system using Particle Swarm Optimization. In order to accelerate the calculation of the fitness function the rendering of the 3D model in the requested poses has been realized using OpenGL. The experimental… 
Reconstruction of 3D human motion in real-time using particle swarm optimization with GPU-accelerated fitness function
TLDR
A novel framework for acceleration of 3D model-based, markerless visual tracking in multi-camera videos is proposed that effectively utilizes the rendering power of OpenGL to render the 3D models in the predicted poses, whereas the CUDA threads are used to match such rendered models with the image observations and to perform particle swarm optimization-based tracking.

References

SHOWING 1-10 OF 23 REFERENCES
Real-Time Multi-view Human Motion Tracking Using Particle Swarm Optimization with Resampling
TLDR
A particle swarm optimization with resampling for marker-less body tracking with robustness and accuracy and the algorithm better copes with noise and reduces the premature stagnation.
GPU-Accelerated Tracking of the Motion of 3D Articulated Figure
TLDR
Methods that utilize the advantages of modern graphics card hardware for real-time full body tracking with a 3D body model using a single low-cost moderately-priced graphics card and images from single camera are presented.
GPU-Accelerated Real-Time Tracking of Full-Body Motion With Multi-Layer Search
TLDR
A pose search method is proposed by introducing a new generative sampling algorithm with a refinement step of local optimization that generalizes well to general human motions and is capable of tracking full body movements with a maximum speed of 9 fps.
Swarm Intelligence Based Searching Schemes for Articulated 3D Body Motion Tracking
TLDR
This work proposes a global-local annealed particle swarm optimization to alleviate the inconsistencies between the observed human pose and the estimated configuration of the 3D model.
Parallelization strategies for markerless human motion capture
TLDR
An efficient approach to parallelize the evaluation of the solutions in CPUs and GPUs forMarkerless motion capture (MMOCAP) is presented and is experimentally compared on six sequences of the HumanEva-I dataset using the CMAES algorithm.
A comparison of 3d model-based tracking approaches for human motion capture in uncontrolled environments
TLDR
This work addresses the problem of tracking humans with skeleton-based shape models where video footage is acquired by multiple cameras where the shape deformations are parameterized by the skeleton and provides a guidance on algorithm design for different applications related to human motion capture.
Performance evaluation of a 3D multi-view-based particle filter for visual object tracking using GPUs and multicore CPUs
TLDR
A deep and extensive performance analysis of the particle filter (PF) algorithm for a very compute intensive 3D multi-view visual tracking problem and demonstrates that hybrid CPU/GPU implementations can run almost as fast as only GPU solutions.
A Review on Particle Swarm Optimization Algorithm and Its Variants to Human Motion Tracking
TLDR
An attempt is made to provide a guide for the researchers working in the field of PSO based human motion tracking from video sequences and the performance of various model evaluation search strategies within PSO tracking framework for 3D pose tracking is presented.
A Quantitative Evaluation of Video-based 3D Person Tracking
TLDR
The Bayesian estimation of 3D human motion from video sequences is quantitatively evaluated using synchronized, multi-camera, calibrated video and 3D ground truth poses acquired with a commercial motion capture system to suggest that in constrained laboratory environments, current methods perform quite well.
HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion
TLDR
There is a need for common datasets that allow fair comparison between different methods and their design choices to establish the current state of the art, and it is argued that HumanEva-I will become a standard dataset for the evaluation of articulated human motion and pose estimation.
...
...