Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos

Xiaohui Yuan; Longbo Kong; Dengchao Feng; Zhenchun Wei

doi:10.1109/JAS.2017.7510625

Volume 4 Issue 4

Oct. 2017

IEEE/CAA Journal of Automatica Sinica

JCR Impact Factor: 11.8, Top 4% (SCI Q1)

CiteScore: 17.6, Top 3% (Q1)
Google Scholar h5-index: 77， TOP 5

Turn off MathJax

Article Contents

Article Navigation > IEEE/CAA Journal of Automatica Sinica > 2017 > 4(4): 677-685

Xiaohui Yuan, Longbo Kong, Dengchao Feng and Zhenchun Wei, "Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos," IEEE/CAA J. Autom. Sinica, vol. 4, no. 4, pp. 677-685, Oct. 2017. doi: 10.1109/JAS.2017.7510625

Citation:

Xiaohui Yuan, Longbo Kong, Dengchao Feng and Zhenchun Wei, "Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos," IEEE/CAA J. Autom. Sinica, vol. 4, no. 4, pp. 677-685, Oct. 2017. doi: 10.1109/JAS.2017.7510625

Citation:

PDF( 21557 KB)

Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos

doi: 10.1109/JAS.2017.7510625

Xiaohui Yuan^{1, 2
,},
Longbo Kong^2
,,
Dengchao Feng^2
,,
Zhenchun Wei^{3
,
,}

1.
China University of Geosciences(Wuhan), Wuhan 430074, China
2.
University of North Texas, Texas 76203-1277, USA
3.
Hefei University of Technology, Hefei 230009, China

More Information

Author Bio:
Xiaohui Yuan received the B.S. degree in electrical engineering from Hefei University of Technology, China in 1996 and the Ph.D. degree in computer science from Tulane University in 2004. He is an Associate Professor at the University of North Texas and a visiting Professor at the China University of Geosciences. He is the director of the Computer Vision and Intelligent Systems Laboratory at the University of North Texas. His research interests include computer vision, machine learning, image processing, data mining, and artificial intelligence. His research findings have been reported in over 100 peer-reviewed papers. He is a recipient of Ralph E. Powe Faculty award. (e-mail: xiaohui.yuan@unt.edu)

Longbo Kong received the bachelor of science degree in computer science in 2010 from Dalian University of Technology, China and received the master degree in computer science at the University of North Texas (UNT), USA. in 2013. He is currently the Ph.D. candidate at UNT. He is a member of the Computer Vision and Intelligent Systems Laboratory, and is working as a teaching assistant. His research interests include computer vision, data mining, and artificial intelligence. (e-mail: longbokong@my.unt.edu)

Dengchao Feng graduated from Taiyuan University of Technology, China, in 1999. He received the M.S. degree from Taiyuan University of Technology in 2004 and the Ph.D. degree from Tianjin University, China, in 2008. He is currently an Associate Professor at the Laboratory of Remote Sensing, GNSS, GIS (3 S Lab) in North China Institute of Aerospace Engineering. His research interests include flight safety in low altitude airspace and intelligent information process. (e-mail: df0158@unt.edu)

Zhenchun Wei graduated from the Hefei University of Technology, China with a bachelor of science degree in computer science in 2000 and received the Ph.D. degree from the Hefei University of Technology, China in 2007. He is currently an Associate Professor with the School of Computer and Information at the Hefei University of Technology. His research interests include Internet of things, wireless sensor networks, machine learning, and distributed system. (e-mail: weizc@hfut.edu.cn)
Corresponding author: Zhenchun Wei, e-mail:weizc@hfut.edu.cn
Received Date: 2016-06-07
Accepted Date: 2016-10-28

Abstract

Abstract

Detecting feature points on the human body in video frames is a key step for tracking human movements. There have been methods developed that leverage models of human pose and classification of pixels of the body image. Yet, occlusion and robustness are still open challenges. In this paper, we present an automatic, model-free feature point detection and action tracking method using a time-of-flight camera. Our method automatically detects feature points for movement abstraction. To overcome errors caused by miss-detection and occlusion, a refinement method is devised that uses the trajectory of the feature points to correct the erroneous detections. Experiments were conducted using videos acquired with a Microsoft Kinect camera and a publicly available video set and comparisons were conducted with the state-of-the-art methods. The results demonstrated that our proposed method delivered improved and reliable performance with an average accuracy in the range of 90%. The trajectorybased refinement also demonstrated satisfactory effectiveness that recovers the detection with a success rate of 93.7%. Our method processed a frame in an average time of 71.1 ms.
- Feature point,
- human pose detection,
- joint detection,
- time-of-flight (ToF) videos

FullText(HTML)

References(14)

References

[1]	T. B. Moeslund, A. Hilton, and V. Krüger, "A survey of advances in vision-based human motion capture and analysis, " Comp. Vis. Image Underst. , vol. 104, no. 2-3, pp. 90-126, Nov. -Dec. 2006.
[2]	J. X. Chen, S. Q. Nie, and Q. Ji, "Data-free prior model for upper body pose estimation and tracking, " IEEE Trans. Image Process. , vol. 22, no. 12, pp. 4627-4639, Dec. 2013. http://www.ncbi.nlm.nih.gov/pubmed/23893728
[3]	A. Baak, M. Müller, G. Bharaj, H. P. Seidel, and C. Theobalt, "A data-driven approach for real-time full body pose reconstruction from a depth camera, " in Proc. IEEE Int. Conf. Computer Vision, Barcelona, Spain, 2011, pp. 1092-1099. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6126356
[4]	C. Plagemann, V. Ganapathi, D. Koller, and S. Thrun, "Real-time identification and localization of body parts from depth images, " in Proc. IEEE Int. Conf. Robotics and Automation, Anchorage, AK, USA, 2010, pp. 3108-3113. http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=5509559
[5]	S. Handrich and A. Al-Hamadi, "A robust method for human pose estimation based on geodesic distance features, " in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, Manchester, UK, 2013, pp. 906-911. http://dl.acm.org/citation.cfm?id=2572058
[6]	L. A. Schwarz, A. Mkhitaryan, D. Mateus, and N. Navab, "Estimating human 3D pose from time-of-flight images based on geodesic distances and optical flow, " in Proc. IEEE Int. Conf. Automatic Face & Gesture Recognition and Workshops, Santa Barbara, CA, USA, 2011, pp. 700-706. http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=5771333
[7]	P. C. Huang and S. K. Jeng, "Human body pose recognition from a single-view depth camera, " in Proc. IEEE Int. Conf. Systems, Man, and Cybernetics, Seoul, Korea, 2012, pp. 2144-2149. http://ieeexplore.ieee.org/document/6378057/
[8]	V. Ganapathi, C. Plagemann, D. Koller, and S. Thrun, "Real time motion capture using a single time-of-flight camera, " in Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010, pp. 755-762. http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=5540141
[9]	X. L. Wei, P. Z. Zhang, and J. X. Chai, "Accurate realtime full-body motion capture using a single depth camera, " ACM Trans. Graph. Proc. ACM SIGGRAPH Asia, vol. 31, no. 6, pp. Article ID 188, Nov. 2012. http://dl.acm.org/citation.cfm?id=2366207
[10]	J. Shotton, R. Girshick, A. Fitzgibbon, T. Sharp, M. Cook, M. Finocchio, R. Moore, P. Kohli, A. Criminisi, A. Kipman, and A. Blake, "Efficient human pose estimation from single depth images, " IEEE Trans. Pattern Anal. Mach. Intell. , vol. 35, no. 12, pp. 2821-2840, Dec. 2013. doi: 10.1007/978-1-4471-4929-3_13
[11]	E. J. Weng and L. C. Fu, "On-line human action recognition by combining joint tracking and key pose recognition, " in IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Vilamoura, Portugal, 2012, pp. 4112-4117. http://ieeexplore.ieee.org/xpls/icp.jsp?arnumber=6385863
[12]	K. Greff, A. Brandão, S. Krauß, D. Stricker, and E. Clua, "A comparison between background subtraction algorithms using a consumer depth camera, " in Proc. Int. Conf. Computer Vision Theory and Applications, Rome, Italy, 2012, pp. 431-436. http://www.zentralblatt-math.org/ioport/en/search/?q=an%3A11821860
[13]	M. K. Hu, "Visual pattern recognition by moment invariants, " IRE Trans. Inf. Theory, vol. 8, no. 2, pp. 179-187, Feb. 1962.
[14]	Y. Kim and D. Kim, "Efficient body part tracking using ridge data and data pruning, " in Proc. IEEE-RAS 15th Int. Conf. Humanoid Robots, Seoul, Korea, pp. 114-120, 2015. http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7363523

Supplements(0)

Cited By

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Figures(15) / Tables(3)

Get Citation

PDF

XML

Article Metrics

Article views (1396) PDF downloads(133)

Automatic Feature Point Detection and Tracking of Human Actions in Time-of-flight Videos

doi: 10.1109/JAS.2017.7510625

Abstract

References

Proportional views

Catalog

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Export File

Citation

Format

Content