請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68269完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳炳宇(Bing-Yu Chen) | |
| dc.contributor.author | Ching-Chun Chen | en |
| dc.contributor.author | 陳靖淳 | zh_TW |
| dc.date.accessioned | 2021-06-17T02:16:13Z | - |
| dc.date.available | 2020-01-04 | |
| dc.date.copyright | 2018-01-04 | |
| dc.date.issued | 2017 | |
| dc.date.submitted | 2017-10-11 | |
| dc.identifier.citation | [1] M. Burenius, J. Sullivan, and S. Carlsson. 3d pictorial structures for multiple view articulated pose estimation. In CVPR, pages 3618–3625. IEEE Computer Society, 2013.
[2] J. Chai and J. K. Hodgins. Performance animation from low-dimensional control signals. In ACM SIGGRAPH 2005 Papers, SIGGRAPH ’05, pages 686–696, New York, NY, USA, 2005. ACM. [3] L. Chan, C.-H. Hsieh, Y.-L. Chen, S. Yang, D.-Y. Huang, R.-H. Liang, and B.-Y. Chen. Cyclops: Wearable and single-piece full-body gesture input devices. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, CHI ’15, pages 3001–3009, New York, NY, USA, 2015. ACM. [4] M. Eichner, M. Marin-Jimenez, A. Zisserman, and V. Ferrari. 2d articulated human pose estimation and retrieval in (almost) unconstrained still images. International Journal of Computer Vision, 99:190–214, 2012. [5] A. Elhayek, E. Aguiar, A. Jain, J. Tompson, L. Pishchulin, M. Andriluka, C. Bregler, B. Schiele, and C. Theobalt. Efficient convnet-based marker-less motion capture in general scenes with a low number of cameras. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2015. [6] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Comput., 9(8):1735–1780, Nov. 1997. [7] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In D. Blei and F. Bach, editors, Proceedings of the 32nd International Conference on Machine Learning (ICML-15), pages 448–456. JMLR Workshop and Conference Proceedings, 2015. [8] G. Klambauer, T. Unterthiner, A. Mayr, and S. Hochreiter. Self-normalizing neural networks. Neural Information Processing Systems, Accepted, 2017. [9] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS’12, pages 1097–1105, USA, 2012. Curran Associates Inc. [10] M. Loper, N. Mahmood, and M. J. Black. Mosh: Motion and shape capture from sparse markers. ACM Trans. Graph., 33(6):220:1–220:13, Nov. 2014. [11] S. I. Park and J. K. Hodgins. Data-driven modeling of skin and muscle deformation. In ACM SIGGRAPH 2008 Papers, SIGGRAPH ’08, pages 96:1–96:6, New York, NY, USA, 2008. ACM. [12] H. Rhodin, C. Richardt, D. Casas, E. Insafutdinov, M. Shafiei, H.-P. Seidel, B. Schiele, and C. Theobalt. Egocap: Egocentric marker-less motion capture with two fisheye cameras. ACM Trans. Graph., 35(6):162:1–162:11, Nov. 2016. [13] H. Rhodin, N. Robertini, C. Richardt, H.-P. Seidel, and C. Theobalt. A versatile scene model with differentiable visibility applied to generative pose estimation. In Proceedings of the 2015 International Conference on Computer Vision (ICCV 2015), 2015. [14] E. Shelhamer, J. Long, and T. Darrell. Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):640–651, Apr. 2017. [15] 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. In Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR ’11, pages 1297–1304, Washington, DC, USA, 2011. IEEE Computer Society. [16] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich. Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 00:1–9, 2015. [17] C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2818–2826, 2016. [18] C. Wang, Y. Wang, Z. Lin, A. L. Yuille, and W. Gao. Robust estimation of 3d human poses from a single image. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2014, Columbus, OH, USA, June 23-28, 2014, pages 2369–2376, 2014. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68269 | - |
| dc.description.abstract | 在這份研究當中我們提出了一套基於深度學習的方法用來直接從二維魚眼影像估計人體關節在三維空間中的位置，這裡的二維魚眼影像是用一種以使用者自身為中心的視角去拍攝的。我們提出的方法之核心是一個基於Inception-v3所新設計的卷積類神經網路，特色是為魚眼影像調整而較大的卷積過濾器、訓練參數減量、長短期記憶、以及將擬人論的權重引入訓練網路時的損失函數。我們也進行了四類實驗來研究在該方法上使用不同訓練設定對測試結果的影響。這份研究的內容可以為發展出有著合理的資源使用量且更為複雜的電腦視覺深度學習網路提供經驗。 | zh_TW |
| dc.description.abstract | In this study, we propose a deep learning based method to directly estimate the human joint positions in 3D space from 2D fisheye images captured in an egocentric manner. The core of our method is a new design based on Inception-v3 convolutional neural network featuring the larger convolutional filter size, the reduction of parameters, the long short-term memory module, and the anthropomorphic weights on the training loss. We also conduct four groups of experiments to study the different effects upon the testing results when using different training settings of our work. The experience of our study can be helpful to develop more complicated deep learning network in a reasonable resource requirement to deal with the computer vision problems. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T02:16:13Z (GMT). No. of bitstreams: 1 ntu-106-R04944003-1.pdf: 4048038 bytes, checksum: ba93805546be06582b2a7ceb18a6679b (MD5) Previous issue date: 2017 | en |
| dc.description.tableofcontents | 致謝 i
中文摘要 ii Abstract iii List of Figures vi List of Tables xi Chapter 1 Introduction 1 1.1 Motivation . . . . . . . . . . 1 1.2 Problem Statement . . . . . . 3 Chapter 2 Related Work 4 2.1 Motion Capture . . . . . . . . 4 2.2 Deep Learning . . . . .. . . . 8 Chapter 3 Overview 11 Chapter 4 Convolutional Filter Size 16 Chapter 5 Long Short-Term Memory 20 Chapter 6 Reduction of Parameters 24 Chapter 7 Anthropomorphic Loss 29 Chapter 8 Experimental Result 33 8.1 Experimental Environment . . . . 33 8.2 Evaluation . . . . . . . . . . . 34 Chapter 9 Conclusion 51 9.1 Limitation . . . . . . . . . . . 51 9.2 Future Work . . . . . . . . . . 52 9.3 Summary . . . . . . . . . . . . 52 Bibliography 54 | |
| dc.language.iso | en | |
| dc.subject | 卷積類神經網路 | zh_TW |
| dc.subject | 三維人體姿勢估計 | zh_TW |
| dc.subject | 魚眼影像 | zh_TW |
| dc.subject | 使用者自身為中心的視角 | zh_TW |
| dc.subject | Inception網路架構 | zh_TW |
| dc.subject | 長短期記憶 | zh_TW |
| dc.subject | SELU激發函式 | zh_TW |
| dc.subject | 擬人論的權重 | zh_TW |
| dc.subject | SELU | en |
| dc.subject | 3D Human Pose Estimation | en |
| dc.subject | Egocentric View | en |
| dc.subject | Convolutional Neural Networks | en |
| dc.subject | Inception | en |
| dc.subject | LSTM | en |
| dc.subject | Fisheye Image | en |
| dc.subject | Anthropomorphic Weights | en |
| dc.title | 用於直接從二維魚眼影像估計三維人體姿勢的一種深度學習方法 | zh_TW |
| dc.title | A Deep Learning Based Method For 3D Human Pose Estimation From 2D Fisheye Images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-1 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 徐宏民(Winston Hsu),詹力韋(Liwei Chan) | |
| dc.subject.keyword | 魚眼影像,三維人體姿勢估計,使用者自身為中心的視角,卷積類神經網路,Inception網路架構,長短期記憶,SELU激發函式,擬人論的權重, | zh_TW |
| dc.subject.keyword | Fisheye Image,3D Human Pose Estimation,Egocentric View,Convolutional Neural Networks,Inception,LSTM,SELU,Anthropomorphic Weights, | en |
| dc.relation.page | 56 | |
| dc.identifier.doi | 10.6342/NTU201704263 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2017-10-11 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-106-1.pdf 未授權公開取用 | 3.95 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。