臺灣博碩士論文加值系統

摘要 i
ABSTRACT ii
目錄 iii
圖目錄 v
表目錄 vi
第一章 序論 1
1.1 研究動機 1
1.2 論文架構 1
第二章 文獻探討 2
2.1 姿態估計 (Pose Estimaion) 2
2.2 二維姿態估計(2D pose Estimation) 3
2.2.1 Convolutional Pose Machine 5
2.2.2 Stacked Hourglass Networks 6
2.2.3 Realtime Multi-Person 2D Pose Estimation 6
2.2.4 Realtime Multi-Person 2D Pose Estimation on CPU 7
2.3 三維姿態估計(3D Pose Estimation) 8
2.3.1 VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera 9
2.3.2 Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB 10
2.3.3 camera distance-aware top-down approach for 3d multi-person pose estimation from a single rgb image 11
第三章 研究方法 13
3.1 系統架構 13
3.1.1 Object detection 14
3.1.2 RootNet 15
3.1.3 PoseNet 16
3.2 訓練流程 17
3.2.1 訓練資料集 17
3.2.2 訓練過程與損失函數 18
第四章 實驗結果 19
4.1 實驗環境 19
4.2 評估方法 19
4.3 實驗流程及結果 20
4.3.1 Object detection 20
4.3.2 RootNet 20
4.3.3 PoseNet 21
第五章 結論 23
第六章 參考文獻 24

[1]Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, Hartwig Adam, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” CVPR, 2017.
[2]Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, Liang-Chieh Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” CVPR, 2018
[3]Qi Dang, Jianqin Yin , Bin Wang, and Wenqing Zheng. “Deep Learning Based 2D Human Pose Estimation: A Survey.” IEEE.
[4]Varun Ramakrishna, Daniel Munoz, Martial Hebert, J. Andrew Bagnell, and Yaser Sheikh. “Pose Machines: Articulated Pose Estimation via Inference Machines.” ECCV, 2014.
[5]Shih-En Wei, Varun Ramakrishna, Takeo Kanade, Yaser Sheikh, “Convolutional Pose Machines” CVPR, 2016.
[6]Zhe Cao, Gines Hidalgo, Tomas Simon, Shih-En Wei, Yaser Sheikh, “openPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields,”CVPR, 2018.
[7]Daniil Osokin, “Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose, ” CVPR, 2018.
[8]Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu. “RMPE: Regional Multi-person Pose Estimation.” ICCV, 2017.
[9]Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, Bernt Schiele. Schiele, “Deepercut: A deeper, stronger, and faster multi-person pose estimation model”, ECCV, 2016.
[10]Alejandro Newell, Kaiyu Yang, Jia Deng “Stacked Hourglass Networks for Human Pose Estimation”, CVPR, 2016
[11]A. Toshev and C. Szegedy, “Deeppose: Human pose estimation via deep neural networks,” CVPR, 2014.
[12]Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi, “You Only Look Once: Unified, Real-Time Object Detection”, CVPR, 2016.
[13]Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection”, CVPR 2020.
[14]Mykhaylo Andriluka, Leonid Pishchulin, Peter Gehler, and Bernt Schiele. “2d human pose estimation: New benchmark and state of the art analysis.” CVPR, 2014
[15]Federica Bogo, Angjoo Kanazawa, Christoph Lassner, Peter Gehler, Javier Romero, and Michael J Black. “Keep it smpl: Automatic estimation of 3d human pose and shape from a single image.” ECCV, 2016.
[16]Ju Yong Chang and Kyoung Mu Lee. “2d–3d pose consistency-based conditional random fields for 3d human pose estimation.” CVIU, 2018.
[17]Ching-Hang Chen and Deva Ramanan. “3d human pose estimation= 2d pose estimation+ matching.” CVPR, 2017.
[18]Yilun Chen, Zhicheng Wang, Yuxiang Peng, Zhiqiang Zhang, Gang Yu, and Jian Sun. “Cascaded pyramid network for multi-person pose estimation.” CVPR, 2018
[19]Hao-Shu Fang, Yuanlu Xu, Wenguan Wang, Xiaobai Liu, and Song-Chun Zhu. “Learning pose grammar to encode human body configuration for 3d pose estimation.” AAAI, 2018.
[20]Shaoli Huang, Mingming Gong, and Dacheng Tao. “A coarsefine network for keypoint localization.” ICCV, 2017.
[21]Eldar Insafutdinov, Leonid Pishchulin, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele. “Deepercut: A deeper, stronger, and faster multi-person pose estimation model.” ECCV, 2016.
[22]Catalin Ionescu, Dragos Papava, Vlad Olaru, and Cristian Sminchisescu. “Human3.6m: Large scale datasets and predictive methods for 3d human sensing in natural environments.” TPAMI, 2014.
[23]Ehsan Jahangiri and Alan L Yuille. “Generating multiple diverse hypotheses for human 3d pose consistent with 2d joint detections.” ICCV, 2017.
[24]Muhammed Kocabas, Salih Karagoz, and Emre Akbas. “Multiposenet: Fast multi-person pose estimation using pose residual network.” ECCV, 2018.
[25]Sijin Li and Antoni B Chan. “3d human pose estimation from monocular images with deep convolutional neural network.” ACCV, 2014.
[26]Julieta Martinez, Rayat Hossain, Javier Romero, and James J Little. “A simple yet effective baseline for 3d human pose estimation.” ICCV, 2017.
[27]Tsung-Yi Lin, Piotr Dollar, Ross Girshick, Kaiming He, ´ Bharath Hariharan, and Serge Belongie. “Feature pyramid networks for object detection.” CVPR, 2017.
[28]Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal Fua, Oleksandr Sotnychenko, Weipeng Xu, and Christian Theobalt. “Monocular 3d human pose estimation in the wild using improved cnn supervision.” 3DV, 2017.
[29]Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, and Christian Theobalt. “Single-shot multi-person 3d pose estimation from monocular rgb.” 3DV, 2018.
[30]Gyeongsik Moon, Ju Yong Chang, and Kyoung Mu Lee. “Multi-scale aggregation r-cnn for 2d multi-person pose estimation.” CVPRW, 2019.
[31]Gyeongsik Moon, Ju Yong Chang, and Kyoung Mu Lee. “Posefix: Model-agnostic general human pose refinement network.” CVPR, 2019.
[32]Francesc Moreno-Noguer. “3d human pose estimation from a single image via distance matrix regression.” CVPR, 2017.
[33]George Papandreou, Tyler Zhu, Nori Kanazawa, Alexander Toshev, Jonathan Tompson, Chris Bregler, and Kevin Murphy. “Towards accurate multi-person pose estimation in the wild.” CVPR, 2017.
[34]Sungheon Park, Jihye Hwang, and Nojun Kwak. “3d human pose estimation using convolutional neural networks with 2d pose information.” ECCV, 2016.
[35]Georgios Pavlakos, Xiaowei Zhou, Konstantinos G Derpanis, and Kostas Daniilidis. “Coarse-to-fine volumetric prediction for single-image 3d human pose.” CVPR, 2017.
[36]Denis Tome, Chris Russell, and Lourdes Agapito. “Lifting from the deep: Convolutional 3d pose estimation from a single image”. CVPR, 2017
[37]Bin Xiao, Haiping Wu, and Yichen Wei. “Simple baselines for human pose estimation and tracking”. ECCV, 2018.
[38]Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee. “Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image,” ICCV, 2019
[39]Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt. “VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera.” SIGGRAPH, 2017
[40]Jianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu, Wei Jiang, Hujun Bao, Xiaowei Zhou. “SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation.” ECCV 2020
[41]Timo von Marcard, Roberto Henschel, Michael Black, Bodo Rosenhahn and Gerard Pons-Moll, “Recovering Accurate 3D Human Pose in The Wild Using IMUs and a Moving Camera.” ECCV, 2018.
[42]Tianlang Chen, Chen Fang, Xiaohui Shen, Yiheng Zhu, Zhili Chen, Jiebo Luo. “Anatomy-aware 3D Human Pose Estimation with Bone-based Pose Decomposition.” IEEE Transactions on Circuits and Systems for Video Technology, 2020.
[43]Yu Cheng, Bo Wang, Bo Yang, Robby T. Tan. “Monocular 3D Multi-Person Pose Estimation by Integrating Top-Down and Bottom-Up Networks.” CVPR, 2021