.png){kind=icon}
Return
Real-time three-dimensional skeletonisation using general-purpose computing on graphics processing units applied to computer vision-based human pose estimation
.png){kind=icon}
PRE
AI
DOI：10.1177/1094342014566289.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Human pose estimation is the process of approximating the configuration of the body's underlying skeletal articulation in one or more frames. The curve-skeleton of an object is a line-like representation that preserves topology and geometrical information. Finding the curve-skeleton of a volume corresponding to the person is a good starting point for approximating the underlying skeletal structure. In this paper, a GPU implementation of a fully parallel thinning algorithm based on the critical kernel framework is presented. The algorithm is compared to three other state-of-the-art skeletonisation methodstwo CPU and one GPU implementationusing both real and synthetic data. It is demonstrated that all four achieve close to real-time frame rates, however, the proposed algorithm yields superior accuracy and robustness when used in a pose estimation context. The GPU implementation is>8x faster than a CPU implementation of the same algorithm, and the positions of the 4 extremities are estimated with rms error approximate to 6cm and approximate to 98% of frames correctly labelled for some sequences.
Keywords:
Skeletonisation
GPGPU
real-time
human motion analysis
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.5
Papers:
1.1K
Citations:
1.3K
Organization
No organization information available
Cited Papers
ShareSave
ShareSaveCharacterization of a major tandemly repeated DNA sequence (RBMII) prevalent among many species of waterfowl (Anatidae).png)
Genome
GenomeIF0
PREAI
ShareSaveShareSaveShareSaveShareSave
View more