Real-Time Human Skeleton Extraction Based on Video Sequences

Qing Ye; Jun Feng Dong; Yong Mei  Zhang

doi:10.4028/www.scientific.net/AMM.401-403.1410

Paper Titles

Magnetic Generator with Automatic Gain Regulation in a Wireless Tracking System for a Capsule Endoscope
p.1393

Novel Iterative Truncated Total Least Squares Algorithm for Image Restoration
p.1397

Prediction Research of Highway Traveling Passenger Volume Based on Wavelet Neural Network
p.1401

Projected Image Restoration Method Based on Genetic Algorithm for Cone-Beam CT
p.1406

Real-Time Human Skeleton Extraction Based on Video Sequences
p.1410

Research and Design of Digital Signal Processing Virtual Experiment Platform
p.1415

Research of FMCW for Perfect Binary Sequences Pairs
p.1419

Vibration Signal of Recoil Mechanism De-Noising Processing Based on Wavelet Analysis
p.1424

Time Sequence Clustering Based on Edit Distance
p.1428

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 401-403Real-Time Human Skeleton Extraction Based on Video...

Real-Time Human Skeleton Extraction Based on Video Sequences

Abstract:

Thinning algorithm is widely used in image processing and pattern recognition.In this paper we proposed an optimized thinning algorithm based on Zhan-Suen thinning and applied it to video sequences of moving human body to extract real-time body skeleton. We firstly used background subtraction method to detect moving body, then made use of adaptive threshold segmentation to gain the binary moving body image, finally we used the optimized algorithm to the binary image and got its skeleton. The skeleton not only maintains the movement geometry and body image’s topological properties, also reduces image redundancy and computation cost, and helps us clearly recognize the moving body posture.

You might also be interested in these eBooks

Frontiers of Manufacturing Science and Measuring Technology III

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 401-403)

Pages:

1410-1414

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.401-403.1410

Citation:

Cite this paper

Online since:

September 2013

Authors:

Qing Ye, Jun Feng Dong, Yong Mei Zhang

Keywords:

Body Posture, Moving Body, Skeleton Extraction, Thinning Algorithm

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Hironobu F, Alan J.L. Real-time human motion analysis by image skeletonization. Application of Computer Vision, pp: 15-21, (1998).

Google Scholar

[2] Zhang H & Xu G. Thinning algorithm for binary image based on 4 adjoint points[J]. Information Technology Informatization, (2004).

Google Scholar

[3] Zhang T. Y, Suen C.Y. A fast parallel algorithm for thinning digital pattern[J]. Comm ACM, 27(3): 236-239.

Google Scholar

[4] Hilditch C.J. Linear skeletons from square cupboards[J]. Machine Intelligence, pp: 403-420, (1969).

Google Scholar

[5] Chin R T, Wan R K, et. al. A one-pass thinning algorithm and it's parallel implementation[J]. CVGIP, 40(1): 30-40, (1987).

Google Scholar

[6] Piccardi,M. Background subtraction techniques: a review[C]. IEEE Trans, Systems, Man and Cybernetics, 4: 1-6, (2004).

Google Scholar

[7] Nobuyuki Otsu. A threshold selection method from gray-level histograms[J]. Automatic, 9(1): 1-5, (1975).

Google Scholar

[8] Keiichi Abe, Fuyuki M et. al. Thinning of gray-scale images with combined sequential and parallel conditions for pixel removal[J]. IEEE Trans, Systems, Man and Cybernetics, 24(2): 1-6, (1994).

DOI: 10.1109/21.281426

Google Scholar

[9] Longin J. L, LI Q. N et. al. Skeletonization using ssm of the distance transform[J]. ICIP, pp: 349-352, (2007).

Google Scholar