臺灣博碩士論文加值系統

目前取得人體骨架的技術依賴在OpenNI框架和NITE的中間套件。使用此技術，一旦人體的位置被辨識，人體骨架可以被即時的追蹤。然而，當人體手上持有物件或目標受到相對深度值影像所造成的影響，會發生不正確的骨架辨識。在此論文，我們提出一種方法可以減少這類問題，甚至是提高骨架精確度。我們偵測人手上的物件，並且利用相對深度圖過濾掉此物件，之後，人體骨架辨識可以透過NITE的中間套件取得正確的人體資訊。同時，透過此過濾方法可以輸出正確的人體資訊包含15個節點、方向及相對的信任。實驗結果顯示，當人手持有物件，透過此過濾方法可以減少影響，並且開發者可以持續保持即時的人體追蹤。

The currently accepted human skeleton extraction techniques depend on OpenNI framework and NITE middleware. By using this technique, the human skeleton can be tracked with a real time process while human position was recognized at the beginning. However, the incorrect skeleton detection may happen when human holds an object and corresponding depth image is affected by this object. In this thesis, we propose a method to reduce this kind of problem and increase the human skeleton detection accuracy. We detect the object when human holds an object and then filter the object from corresponding depth map. After filtering the object in depth map, the human skeleton detection technique of NITE middleware will get the correct skeleton information. Meanwhile, we can obtain the human skeleton information include 15 joints positions, orientations and corresponding confidents. Experimental results show that human skeleton obtained from the proposed method can reduce the effect when human holds an object, and the process of tracking skeleton is still real time for developer.

Table of Contents
Recommendation Form
Committee Form
Chinese Abstract
English Abstract
Acknowledgements
Table of Contents
List of Tables
List of Figures
1 Introduction
1.1 Introduction to Motion Sensing
1.2 Motivation
1.3 Organization of This Thesis
2 Related Works
2.1 Background Subtraction
2.2 Σ-Δ Estimation
2.3 Skin Detection
3 Research Platform
3.1 Architecture of Xtion Pro Live
3.2 Xtion Software Tools
3.3 Capabilities of The OpenNI Tools
3.4 Human Skeleton Analysis
4 Proposed method
4.1 The Architecture of The Proposed Method
4.2 Correction of depth generator
4.3 Refinement of hand generator
4.4 Skin detection
4.5 Boundary check
5 Experimental Results
5.1 Qualitative measurement
5.2 Quantitative metrics
5.3 Quantitative measurement
6 Conclusions
References
Copyright Form

[1] J. Han, L. Shao, D. Xu, and J. Shotton, “Enhanced computer vision with Microsoft kinect sensor: A review," IEEE Trans. Cybern., vol. 43, no. , pp. 1318-1334, Oct.2013.
[2] L. Xia, C.-C. Chen, and J. K. Aggarwal, “Human detection using depth information by Kinect," IEEE Conf. Comput. Vision Pattern Recognit. Workshops, pp. 15-22, June 2011.
[3] J. Han, E. J. Pauwels, P. M. de Zeeuw, and P. H. de With,“Employing a RGB-D sensor for real-time tracking of humans across multiple re-entries in a smart environment," IEEE Trans. Consumer Electron., vol. 58, no. , pp. 255-263, May 2012.
[4] X. Ren, L. Bo, and D. Fox, “RGB-(D) scene labeling: Features and algorithms," IEEE Conf. Comput. Vision Pattern Recognit., pp. 2759-2766, June 2012.
[5] J. Shotton, A. Fitzgibbon, M. Cook, T. Sharp, M. Finocchio, R. Moore, A. Kipman, and A. Blake,“Real-time human pose recognition in parts from single depth images," IEEE Conf. Comput. Vision Pattern Recognit., pp. 1297-1304, June 2011.
[6] W. Shen, K. Deng, X. Bai, T. Leyvand, B. Guo, and Z. Tu, “Exemplar-based human action pose correction and tagging," IEEE Conf. Comput. Vision Pattern Recognit., pp. 2759-2766, June 2012.
[7] L. Xia, C.-C. Chen, and J. K. Aggarwal, “View invariant human action recognition using histograms of 3D joints," IEEE Conf. Comput. Vision Pattern Recognit. Workshops, pp. 20-27, June 2012.
[8] G. Hackenberg, R. McCall, and W. Broll, “Lightweight palm and finger tracking for real-time 3D gesture control," IEEE Conf. Virtual Reality, pp. 19-26, March 2011.
[9] L. M. Paz, P. Pinies, J. D. Tardos, and J. Neira, “Large-Scale 6-DOF SLAM With Stereo-in-Hand," IEEE Trans. Robot., vol. 24, no. , pp. 946-957, Oct. 2008.
[10] P. Henry, M. Krainin, E. Herbst, X. Ren, and D. Fox, “RGB-D mapping: Using Kinect-style depth cameras for dense 3-D modeling of indoor environments," Int. J. Robot. Res., vol. 31, no. 5, pp. 647-663, 2012.
[11] S. Izadi, D. Kim, O. Hilliges, D. Molyneaux, R. Newcombe, P. Kohli, J. Shotton, S. Hodges, D. Freeman, A. Davison, and A. Fitzgibbon, “KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera," ACM Symp. User Interface Software Technol., pp. 559-568, 2011.
[12] W. Wang, L. Yang, W. Gao,“Modeling background and segmenting moving objects from compressed video," IEEE Trans. Circuits Syst. Video Technol., vol. 18, no. 5, pp. 670-681, May 2008.
[13] M. Piccardi, “Background subtraction techniques: a review," IEEE Int. Conf. Systems, Man, Cybernetics, pp. 3099-3104, Oct. 2004.
[14] B. Tamersoy, “Background subtraction - lecture notes," The University of Texas at Austin, September 29, 2009.
[15] A. Manzanera and J. C. Richefeu, “A new motion detection algorithm based on R–D background estimation," Pattern Recognition Letter, vol. 28, pp. 946-957, Oct. 2008.
[16] C. Garcia, and G.Tziritas,“Face detection using quantized skin color regions merging and wavelet packet analysis," IEEE Trans. Multimedia, vol. 1, no. 3, pp. 264-277, September 1999.
[17] D. Chai and K. N. Ngan, “Face segmentation using skin-color map in videophone applications," IEEE Trans. Circuits Syst. Video Technol., vol. 9, no. 4, pp.551-564, June 1999.