This research only briefly investigated some possibilities of related applications. In the future, researchers from other areas who need to incorporate with 3D motion tracking systems may consider introducing the proposed magnetic 3D motion tracking system to deal with their problems.
As an instance, in biology, proposed system can be used for observation of creatures such as insects, small animals, or plants, to study their behavior.
Chapter 7 Conclusion
This research mainly focused on developing and improving a magnetic 3D motion tracking system with novel and practical processing techniques.
Based on that, it extends the application area of the proposed system to a wide range, including dexterous motion capture for computer animation, fluid tracing and observation, organisms observation, and human computer interaction.
This manuscript described the evolution of the proposed tracking sys-tem throughout these years. At the beginning, it was a naive implementation of the tracking principle, defined as IM3D. By introducing different solution/
algorithms, the tracking result is refined. IM6D designs 3-axis marker to solve the dead-angle problem, while IM3D+ combines multiple process-ing techniques to achieve high quality trackprocess-ing result and reconstruct lost frames.
To achieve this goal, several key processing techniques were proposed.
For the inverse problem optimization, a DNN solver can be used to greatly increase the speed and address the initialization issue. Or, the Random-Forest-based initializer can be incorporated with numerical method to re-move initialization issue. To address the dead-angle problem indicated by the tracking principle, a structure-aware bilateral temporal filter can be used to reconstruct the captured motion, and recover the lost frames due to dead-angle problem.
Furthermore, several practical applications were implemented as tested as examples of the proposed system in actual use. From these applications, it is proved that the proposed motion tracking system can be applied with a variety of motion tracking tasks and scenarios. Especially, for where optical approaches don’t give satisfactory results, the proposed system, as being based on magnetic tracking principle, can be a good candidate.
Acknowledgments
When I graduated as a master from Tohoku University, I did not really expect that I could have a chance continue my Ph.D. here. I could never give enough thanks to my supervisor, Prof. Yoshifumi Kitamura, who makes all these happen. During my years in Interactive Content Design Lab (the ICD lab), Prof. Kitamura shows his great energy and passion towards research, and has become my model of researcher.
My research is sponsored by JSPS’s DC.1 program, which provides a great environment for me to focus on the research without caring much about my financial situation. I appreciate such a great program and some-times feel regret for not achieving enough results to meet with their expec-tation. However, for now, let us hold this regret and try to continue the research.
I cannot finish this research without help of my colleagues, they are Ryo Sugawara, Tsuyoshi Mori, Kin-fung Chu. I would express my thanks specially towards Ryo. Also, during my composition of this dissertation, I received great comments from Prof. Ishiyama, Prof. Hashi, Prof. Sakamoto, and Dr. Takashima.
I would also express my grace to my wife, my parents, and all my families. Their consistent support has become my biggest motivation.
After all, I would thank all the researchers in this world, for expanding the boundary of human knowledge. Without it I will never be able to study, to understand, to create.
Publications
In Chapter 3:
[1] Ryo Sugawara, Jiawei Huang, Kazuki Takashima, Taku Komura, Yoshi-fumi Kitamura,Random-Forest-Based Initializer for Solving Inverse Prob-lem in 3D Motion Tracking SystemsProceeding VRST ’18 Proceedings of the 24th ACM Symposium on Virtual Reality Software and Technology Article No. 116.
[2] Jiawei Huang, Ryo Sugawara, Taku Komura, Yoshifumi Kitamura, Random-Forest-Based Initializer for Real-time Optimization-based 3D Motion Tracking ProblemsICAT-EGVE 2019 - International Conference on Artificial Reality and Telexistence and Eurographics Symposium on Virtual Environments.
[3] 黄佳維, 森健, 高嶋和毅, 枦修一郎, 北村喜文, 磁気式３次元トラッキ ングシステムにおけるLCコイル,マーカの設計と評価 第21 回日本バ ーチャルリアリティ学会大会論文集.
In Chapter 4:
[4] Jiawei Huang, Kazuki Takashima, Shuichiro Hashi, Yoshifumi Kitamura, IM3D: Magnetic Motion Tracking System for Dexterous 3D Interactions ACM SIGGRAPH Emerging Technologies, Vancouver, Canada, August 2014.
[5] Jiawei Huang, Tsuyoshi Mori, Kazuki Takashima, Shuichiro Hashi, Yoshi-fumi Kitamura, IM6D: Magnetic Tracking System with 6-DOF Passive
Markers for Dexterous 3D Interaction and Motion ACM Transactions on Graphics (TOG) , ACM, Volume 34, Issue 6 (Proceedings of ACM SIGGRAPH Asia), pp. 217:1-217:10, November 2015. (Impact Factor:
4.09)
[6] Jiawei Huang, Tsuyoshi Mori, Kazuki Takashima, Shuichiro Hashi, Yoshi-fumi Kitamura,6-DOF computation and marker design for magnetic 3D dexterous motion-tracking system In Proceedings of the 22nd ACM Con-ference on Virtual Reality Software and Technology (VRST ’16).
Jiawei Huang, Ryo Sugawara, Taku Komura, Yoshifumi Kitamura, Recon-struction of Dexterous 3D Motion Data from a Flexible Magnetic Sensor with Deep Learning and Structure-Aware FilteringSubmitted to Transac-tion on VisualizaTransac-tion and Computer Graphics (Under review).
[7] 黄佳維, 森健, 高嶋和毅, 枦修一郎, 北村喜文, 複雑な 3D インタ
ラクションとモーションのための 6 自由度パッシブマーカーによ る磁気式トラッキングシステム,情報処理学会グラフィクスと CAD 研究会(GCAD)・コンピュータビジョンとイメージメディア研究 会(CVIM)合同研究会,2015年11月6日.
In Chapter 5:
[8] 菅原諒,黄佳維,高嶋和毅,北村喜文,磁気式モーションセンサとCNN を用いたオクルージョンに強い非グローブ型手形状,位置,姿勢推定手 法,第23回日本バーチャルリアリティ学会大会論文集
[9] Kasim Ozacar, Takuma Hagiwara, Jiawei Huang, Kazuki Takashima, and Yoshifumi Kitamura,Coupled-Clay: Physical-Virtual 3D Collaborative Interaction Environment Proceedings of IEEE Virtual Reality, pp. 255-256, Arles, France, March 2015.
[10] Mannnone Maria, Eri Kitamura, Jiawei Huang, Ryo Sugawara, Yoshi-fumi Kitamura, Cubeharmonic: A New Interface from a Magnetic 3D Motion Tracking System to Music PerformanceProceedings of the Inter-national Conference on New Interfaces for Musical Expression, 350-351
[11] Shunsuke Yoshida, Ryo Sugawara, Jiawei Huang, Yoshifumi Kitamura, Interacting with 3D Images on a Rear-projection Tabletop 3D Display Using Wireless Magnetic Markers and an Annular Coil Array, Proceeding of IEEE Conference on Virtual Reality and 3D User Interfaces 2019 Poster
Bibliography
[1] S. Yabukami, S. Hashi, Y. Tokunaga, K. Arai, and Y. Okazaki, “Devel-opment of a position-sensing system for a wireless magnetic marker.,”
Journal of the Magnetics Society of Japan, vol. 28, pp. 877–885 (in Japanese), 2004.
[2] I. Sutherland, “A head-mounted three dimensional display,” in Pro-ceedings of 1968 Fall Joint Computer Conference, vol. 33, pp. 757–764, 1968.
[3] T. G. Zimmerman, J. Lanier, C. Blanchard, S. Bryson, and Y. Harvill,
“A hand gesture interface device,” in Proceedings of the Conference on Human Factors in Computing Systems and Graphics Interface, pp.
189–192, 1987.
[4] R. Y. Wang and J. Popovic, “Real-time hand-tracking with a color glove,”
ACM Transactions on Graphics (TOG), vol. 28, no. 63, pp. 63:1–63:8, 2009.
[5] Y. Wang, J. Min, J. Zhang, Y. Liu, F. Xu, Q. Dai, and J. Chai, “Video-based hand manipulation capture through composite motion control,”
inProceedings of SIGGRAPH, no. 63, pp. 43:1–43:13, 2013.
[6] F. Raab, E. Blood, T. Steiner, and H. Jones, “Magnetic position and orientation tracking system,”IEEE Transactions on Aerospace and Elec-tronic Systems, vol. AES-15, pp. 709–718, Sept. 1979.
[7] T. Nakagawa and Y. Koyanagi,Experimental Data Analysis by the Least Square Method. The University of Tokyo Press, 1982.
[8] S. Hashi, M. Toyoda, S. Yabukami, K. Ishiyama, Y. Okazaki, K. I. Arai, and H. Kanetaka, “Wireless magnetic motion capture system using multiple LC resonant magnetic markers with high accuracy,”Sensors and Actuators A: Physical, vol. 142, no. 2, pp. 520–527, 2008.
[9] Polhemus, “http://polhemus.com/,”
[10] E. Foxlin, M. Harrington, and G. Pfeifer, “Constellation: a wide-range wireless motion-tracking system for augmented reality and virtual set applications,” in Proceedings of SIGGRAPH, pp. 371–378, 1998.
[11] E. Foxlin and N. Durlach, “An inertial head-orientation tracker with automatic drift compensation for use with hmd’s,” inProceedings of Virtual Reality Software and Technology, pp. 159–174, Aug. 1994.
[12] M. Ribo, A. Pinz, and A. L. Fuhrmann, “A new optical tracking sys-tem for virtual and augmented reality applications,” inProceedings of the IEEE Instrumentation and Measurement Technology Conference, pp.
1932–1936, 2001.
[13] 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,” inProceedings of IEEE Computer Vision and Pattern Recognition (CVPR), pp. 1297–1304, 2011.
[14] T. Shiratori, H. S. Park, L. Sigal, Y. Sheikh, and J. K. Hodgins, “Motion capture from body-mounted cameras,”ACM Trans. Graph., vol. 30, pp.
31:1–31:10, July 2011.
[15] G. V. J. B. M. G. W. M. Daniel Vlasic, Rolf Adelsberger and J. Popovic,
“Practical motion capture in everyday surroundings,” in ACM SIG-GRAPH 2007 papers, pp. 1932–1936, 2007.
[16] P. Zhang, K. Siu, J. Zhang, C. K. Liu, and J. Chai, “Leveraging depth cameras and wearable pressure sensors for full-body kinematics and dynamics capture,”ACM Trans. Graph., vol. 33, pp. 221:1–221:14, Nov.
2014.
[17] T. Sharp, C. Keskin, D. Robertson, J. Taylor, J. Shotton, D. Kim, C.
Rhemann, I. Leichter, A. Vinnikov, Y. Wei, D. Freedman, P. Kohli, E.
Krupka, A. Fitzgibbon, and S. Izadi, “Accurate, robust, and flexible real-time hand tracking,” inProceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI ’15, (New York, NY, USA), pp. 3633–3642, ACM, 2015.
[18] Ascension, “http://www.ascension-tech.com/,”
[19] S. Yabukami, K. Ogasawara, H. Saitoh, S. Hashi, M. Toyoda, Y. Okazaki, and K. Arai, “Development of a fingertip position-sensing system using LC resonated markers,”Journal of the Magnetics Society of Japan, vol.
31, pp. 439–444 (in Japanese), 2007.
[20] T. Sharp, C. Keskin, D. Robertson, J. Taylor, J. Shotton, D. Kim, C.
Rhemann, I. Leichter, A. Vinnikov, Y. Wei,et al., “Accurate, robust, and flexible real-time hand tracking,” in Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pp. 3633–
3642, ACM, 2015.
[21] J. Tompson, M. Stein, Y. Lecun, and K. Perlin, “Real-time continuous pose recovery of human hands using convolutional networks,” ACM Transactions on Graphics (ToG), vol. 33, no. 5, p. 169, 2014.
[22] P. Molchanov, X. Yang, S. Gupta, K. Kim, S. Tyree, and J. Kautz, “Online detection and classification of dynamic hand gestures with recurrent 3d convolutional neural network,” inThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
[23] T. Simon, H. Joo, I. A. Matthews, and Y. Sheikh, “Hand keypoint detection in single images using multiview bootstrapping.,” inCVPR, vol. 1, p. 2, 2017.
[24] C. Wan, T. Probst, L. Van Gool, and A. Yao, “Crossing nets: Combining gans and vaes with a shared latent space for hand pose estimation,”
in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2017.
[25] F. Mueller, F. Bernard, O. Sotnychenko, D. Mehta, S. Sridhar, D. Casas, and C. Theobalt, “Ganerated hands for real-time 3d hand tracking from monocular rgb,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49–59, 2018.
[26] Y. Ye and C. K. Liu, “Synthesis of detailed hand manipulations using contact sampling,”ACM Transactions on Graphics (TOG), vol. 31, no.
4, p. 41, 2012.
[27] W. Zhao, J. Zhang, J. Min, and J. Chai, “Robust realtime physics-based motion control for human grasping,” ACM Trans. Graph., vol. 32, pp.
207:1–207:12, Nov. 2013.
[28] S. Jörg, J. Hodgins, and A. Safonova, “Data-driven finger motion synthesis for gesturing characters,” ACM Trans. Graph., vol. 31, pp.
189:1–189:7, Nov. 2012.
[29] J. Romero, D. Tzionas, and M. J. Black, “Embodied hands: Model-ing and capturModel-ing hands and bodies together,” ACM Transactions on Graphics (TOG), vol. 36, no. 6, p. 245, 2017.
[30] S. Han, B. Liu, R. Wang, Y. Ye, C. D. Twigg, and K. Kin, “Online optical marker-based hand tracking with deep labels,”ACM Trans. Graph., vol.
37, pp. 166:1–166:10, July 2018.
[31] D. Holden, “Robust solving of optical motion capture data by denois-ing,”ACM Trans. Graph., vol. 37, pp. 165:1–165:12, July 2018.
[32] L. Ljung, “Asymptotic behavior of the extended kalman filter as a pa-rameter estimator for linear systems,”IEEE Transactions on Automatic Control, vol. 24, pp. 36–50, February 1979.
[33] E. A. Wan and R. Van Der Merwe, “The unscented kalman filter for nonlinear estimation,” in Adaptive Systems for Signal Processing, Com-munications, and Control Symposium 2000. AS-SPCC. The IEEE 2000, pp. 153–158, Ieee, 2000.
[34] G. Ligorio and A. M. Sabatini, “A novel kalman filter for human motion tracking with an inertial-based dynamic inclinometer,”IEEE Transac-tions on Biomedical Engineering, vol. 62, no. 8, pp. 2033–2043, 2015.
[35] R. Antonello, K. Ito, and R. Oboe, “Acceleration measurement drift rejection in motion control systems by augmented-state kinematic kalman filter,”IEEE Transactions on Industrial Electronics, vol. 63, pp.
1953–1961, March 2016.
[36] H. J. Shin, J. Lee, S. Y. Shin, and M. Gleicher, “Computer puppetry:
An importance-based approach,”ACM Transactions on Graphics (TOG), vol. 20, no. 2, pp. 67–94, 2001.
[37] C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), pp. 839–846, Jan 1998.
[38] H. Dammertz, D. Sewtz, J. Hanika, and H. Lensch, “Edge-avoiding à-trous wavelet transform for fast global illumination filtering,” in Proceedings of the Conference on High Performance Graphics, pp. 67–75, Eurographics Association, 2010.
[39] A. Buades, B. Coll, and J. . Morel, “A non-local algorithm for image denoising,” in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol. 2, pp. 60–65 vol. 2, June 2005.
[40] T. Schubert, K. Eggensperger, A. Gkogkidis, F. Hutter, T. Ball, and W.
Burgard, “Automatic bone parameter estimation for skeleton tracking in optical motion capture,” in 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 5548–5554, May 2016.
[41] A. G. Kirk, J. F. O’Brien, and D. A. Forsyth, “Skeletal parameter estima-tion from optical moestima-tion capture data,” in2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), vol.
2, pp. 1185 vol. 2–, June 2005.
[42] J. F. O’Brien, R. E. Bodenheimer, G. J. Brostow, and J. K. Hodgins,
“Automatic joint parameter estimation from magnetic motion capture data,” inProceedings of Graphics Interface 2000, pp. 53–60, May 2000.
[43] G. Liu, J. Zhang, W. Wang, and L. McMillan, “Human motion estimation from a reduced marker set,” inProceedings of the 2006 Symposium on Interactive 3D Graphics and Games, I3D ’06, (New York, NY, USA), pp.
35–42, ACM, 2006.
[44] P. Cerveri, E. De Momi, N. Lopomo, G. Baud-Bovy, R. M. L. Barros, and G. Ferrigno, “Finger kinematic modeling and real-time hand motion estimation,”Annals of Biomedical Engineering, vol. 35, pp. 1989–2002, Nov 2007.
[45] P. Cerveri, N. Lopomo, A. Pedotti, and G. Ferrigno, “Derivation of cen-ters and axes of rotation for wrist and fingers in a hand kinematic model: Methods and reliability results,”Annals of Biomedical Engineer-ing, vol. 33, pp. 402–412, Jan 2005.
[46] X. Zhang, S.-W. Lee, and P. Braido, “Determining finger segmental centers of rotation in flexion–extension based on surface marker mea-surement,”Journal of Biomechanics, vol. 36, no. 8, pp. 1097 – 1102, 2003.
[47] L. Hoyet, K. Ryall, R. McDonnell, and C. O’Sullivan, “Sleight of hand:
Perception of finger motion from reduced marker sets,” inProceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D ’12, (New York, NY, USA), pp. 79–86, ACM, 2012.
[48] A. Aristidou and J. Lasenby, “Motion capture with constrained inverse kinematics for real-time hand tracking,” in2010 4th International Sym-posium on Communications, Control and Signal Processing (ISCCSP), pp. 1–5, March 2010.
[49] M. Schröder, J. Maycock, and M. Botsch, “Reduced marker layouts for optical motion capture of hands,” in Proceedings of the 8th ACM
SIGGRAPH Conference on Motion in Games, MIG ’15, (New York, NY, USA), pp. 7–16, ACM, 2015.
[50] N. Wheatland, S. Jörg, and V. Zordan, “Automatic hand-over anima-tion using principle component analysis,” inProceedings of Motion on Games, MIG ’13, (New York, NY, USA), pp. 175:197–175:202, ACM, 2013.
[51] D. J. Tan, T. Cashman, J. Taylor, A. Fitzgibbon, D. Tarlow, S. Khamis, S. Izadi, and J. Shotton, “Fits like a glove: Rapid and reliable hand shape personalization,” in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5610–5619, June 2016.
[52] A. Tkach, A. Tagliasacchi, E. Remelli, M. Pauly, and A. Fitzgibbon,
“Online generative model personalization for hand tracking,” ACM Transactions on Graphics, vol. 36, no. 6, pp. 1–11, 2017.
[53] J. Taylor, V. Tankovich, D. Tang, C. Keskin, D. Kim, P. Davidson, A.
Kowdle, and S. Izadi, “Articulated distance fields for ultra-fast tracking of hands interacting,”ACM Trans. Graph., vol. 36, pp. 244:1–244:12, Nov. 2017.
[54] X. Zhou, Q. Wan, W. Zhang, X. Xue, and Y. Wei, “Model-based deep hand pose estimation,” in Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, pp. 2421–2427, AAAI Press, 2016.
[55] J. Taylor, L. Bordeaux, T. Cashman, B. Corish, C. Keskin, T. Sharp, E.
Soto, D. Sweeney, J. Valentin, B. Luff, A. Topalian, E. Wood, S. Khamis, P. Kohli, S. Izadi, R. Banks, A. Fitzgibbon, and J. Shotton, “Efficient and precise interactive hand tracking through joint, continuous opti-mization of pose and correspondences,”ACM Trans. Graph., vol. 35, pp. 143:1–143:12, July 2016.
[56] F. Mueller, D. Mehta, O. Sotnychenko, S. Sridhar, D. Casas, and C.
Theobalt, “Real-time hand tracking under occlusion from an egocentric
rgb-d sensor,” in2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pp. 1284–1293, Oct 2017.
[57] L. Ge, Y. Cai, J. Weng, and J. Yuan, “Hand pointnet: 3d hand pose estimation using point sets,” inThe IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018.
[58] T. Grossman, D. Wigdor, and R. Balakrishnan, “Multi-finger gestural in-teraction with 3D volumetric displays,” inProceedings of the Symposium on User Interface Software and Technology, pp. 61–70, 2004.
[59] P. Song, H. Yu, and S. Winkler, “Vision-based 3D finger interactions for mixed reality games with physics simulation,” inProceedings of The ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry, pp. 7:1–7:6, 2008.
[60] O. Hilliges, S. I. D. Kim, M. Weiss, and A. Wilson, “Holodesk: direct 3D interactions with a situated see-through display,” inProceedings of the Conference on Human Factors in Computing Systems, pp. 2421–2430, 2012.
[61] J. Tompson, M. Stein, Y. Lecun, and K. Perlin, “Real-time continuous pose recovery of human hands using convolutional networks,” ACM Trans. Graph., vol. 33, pp. 169:1–169:10, Sept. 2014.
[62] W. Zhao, J. Chai, and Y.-Q. Xu, “Combining marker-based mocap and rgb-d camera for acquiring high-fidelity hand motion data,” in Proceedings of the SIGGRAPH/Eurographics Symposium on Computer Animation, pp. 33–42, Eurographics Association, 2012.
[63] D. Tang, T.-H. Yu, and T.-K. Kim, “Real-time articulated hand pose estimation using semi-supervised transductive regression forests,” in Proceedings of the 2013 IEEE International Conference on Computer Vision, ICCV ’13, (Washington, DC, USA), pp. 3224–3231, IEEE Com-puter Society, 2013.
[64] Virtual Realities, “http://www.vrealities.com/,”
[65] CyberGlove, “http://www.cyberglovesystems.com/,”
[66] 5DT, “http://www.5dt.com/,”
[67] Y. Wang and M. Neff, “Data-driven glove calibration for hand motion capture,” inProceedings of the Symposium on Computer Animation, pp.
15–24, ACM, 2013.
[68] K.-Y. Chen, K. Lyons, S. White, and S. Patel, “utrack: 3d input using two magnetic sensors,” inProceedings of the Symposium on User Interface Software and Technology, pp. 237–244, ACM, 2013.
[69] C. Harrison and S. E. Hudson, “Abracadabra: Wireless, high-precision, and unpowered finger input for very small mobile devices,” in Proceed-ings of the Symposium on User Interface Software and Technology, pp.
121–124, ACM, 2009.
[70] L. Chan, R.-H. Liang, M.-C. Tsai, K.-Y. Cheng, C.-H. Su, M. Y. Chen, W.-H. Cheng, and B.-Y. Chen, “Fingerpad: Private and subtle interaction using fingertips,” in Proceedings of the Symposium on User Interface Software and Technology, pp. 255–260, ACM, 2013.
[71] C. M. Bishop,Pattern recognition and machine learning. springer, 2006.
[72] J. Huang, K. Takashima, S. Hashi, and Y. Kitamura, “IM3D: Mag-netic Motion Tracking System for Dexterous 3D Interactions,” inACM SIGGRAPH 2014 Emerging Technologies, (New York, NY, USA), pp.
12:1–12:1, ACM, 2014.
[73] A. Criminisi and J. Shotton, Decision forests for computer vision and medical image analysis. Springer Science & Business Media, 2013.
[74] J. Huang, T. Mori, K. Takashima, S. Hashi, and Y. Kitamura, “IM6D:
Magnetic Tracking System with 6-DOF Passive Markers for Dexterous 3D Interaction and Motion,”ACM Trans. Graph., vol. 34, pp. 217:1–
217:10, Oct. 2015.
[75] F. Cholletet al., “Keras.”https://github.com/fchollet/keras, 2015.
[76] M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S.
Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. J. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Józefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mané, R. Monga, S. Moore, D. G. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. A. Tucker, V. Vanhoucke, V. Vasudevan, F. B. Viégas, O. Vinyals, P. Warden, M.
Wattenberg, M. Wicke, Y. Yu, and X. Zheng, “Tensorflow: Large-scale machine learning on heterogeneous distributed systems,”CoRR, vol.
abs/1603.04467, 2016.
[77] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,”
CoRR, vol. abs/1412.6980, 2014.
[78] D. Holden, J. Saito, T. Komura, and T. Joyce, “Learning motion mani-folds with convolutional autoencoders,” inSIGGRAPH Asia 2015 Tech-nical Briefs, p. 18, ACM, 2015.
[79] Y. Kitamura, T. Konishi, S. Yamamoto, and F. Kishino, “Interactive stereoscopic display for three or more users,” inProceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’01, (New York, NY, USA), pp. 231–240, ACM, 2001.
[80] S. Yoshida, “fvision: 360-degree viewable glasses-free tabletop 3d display composed of conical screen and modular projector arrays,”Opt.
Express, vol. 24, pp. 13194–13203, Jun 2016.
[81] V. Iyer, R. Nandakumar, A. Wang, S. Fuller, and S. Gollakota, “Liv-ing iot: A fly“Liv-ing wireless platform on live insects,” arXiv preprint arXiv:1812.09419, 2018.
[82] J. D. Crall, C. M. Switzer, R. L. Oppenheimer, A. N. F. Versypt, B.
Dey, A. Brown, M. Eyster, C. Guérin, N. E. Pierce, S. A. Combes, et al., “Neonicotinoid exposure disrupts bumblebee nest behavior, social networks, and thermoregulation,” Science, vol. 362, no. 6415, pp.
683–686, 2018.