請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88965完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 連豊力 | zh_TW |
| dc.contributor.advisor | Feng-Li Lian | en |
| dc.contributor.author | 周之蕙 | zh_TW |
| dc.contributor.author | Zhi-Hui Zhou | en |
| dc.date.accessioned | 2023-08-16T16:33:51Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-08-16 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-09 | - |
| dc.identifier.citation | [1: R.Mehran et al. 2009]Ramin Mehran, Alexis Oyama, Mubarak Shah, “Abnormal crowd behavior detection using social force model,IEEE Conference on Computer Vision and Pattern Recognition, Aug 2009
[4: Lan et al.2023]Gongjin Lan, Yu Wu, Fei Hu and Qi Hao, ”Vison-Based Pose Estimation via Deep Learning: A Survey”, IEEE Transaction on Human-Machine Systems, Vol 53, No.1 Feb, 2023 [5: Li He et al. 2020]Li He, Guoliang Liu, Guohui Tian, JianHua Zhang and Ze Ji, “Effiecient Multi-View Multi-target Tracking Using a Distributed Camera NetWork”, IEEE Sensors Journal, VOL.20,No.4,Feb, 2020 [6: Haanju Yoo et al. 2017]Haanju Yoo, Kikyung Kim, Moonsub Byeon, Younghan Jeon and Jin Young Choi, “Online Scheme for Multiple Camera Multiple Target Tracking Based on Multiple Hypothesis Tracking” IEEE Transactions on Circuits and Systems For Video Technology, VOL.27,No.3,March 2017 [7: Francois Fleuret et al.2008]F.Fleuret, J.Berclaz, R.Lengagne, and P.Fua, ”Multicamera people tracking with a probabilistic occupancy map”, IEEE Transaction Pattern Analysis and Machine Intelligence,VOL.30, NO.2, Feb, 2008 [8: Saad M.Khan et al. 2009]Saad M.Khan and Mubarak Shan, “Tracking Multiple Occluding People by Localizing on Multiple Scene Planes”, IEEE Transaction on Pattern Analysis and Machine Intelligence, VOL.31, NO.3,March 2009 [9: J.Berclaz et al. 2009]J.Berclaz, F.Fleuret and P.Fua, ”Multiple object tracking using flow linear programming”, IEEE International Workshop on Performance Evaluation of Tracking and Surveill. Dec.2009, pp.1-8 [10: J Berclaz, et al. 2011]J.Berclaz, F.Fleuret, E.Turetken, and P.F, ”Multiple Object Tracking Using K-Shortest Paths Optimization” IEEE Transactions on Pattern Analysis And Machine Intelligence VOL.33, NO.9, Sept.2011 [11:Zheng Wu et al. 2011]Zheng Wu, Thomas H.Kunz ,and Margrit Betke, ”Efficient Track Linking Methods for Track Graphs Using Network-flow and Set-cover Techniques” CVPR 2011. [12: M.Ayazoglu et al.2011]M.Ayazoglu, B.Lim, C.Dicle, M.Sznaier and O.I.Camps, ”Dynamic Subspace-Based Coordinated Multicamera Tracking”, International Coference on Computer Vision, 2011 [13: Haanju Yoo et al.2017]Haanju Yoo, Kikyung Kim, Moonsub Byeon, Young Jeon and Jin Young Choi, “Online Scheme for Multiple Camera Multiple Target Tracking Based on Multiole Hypothesis Tracking” IEEE Transaction on Circuits and Systems for Video Technology, VOL.27, No.3 March 2017 [14: L. Leal-Taixé et al, 2012]L. Leal-Taixé, G. Pons-Moll, and B. Rosenhahn, “Branch-and-price global optimization for multi-view multi-target tracking,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2012, pp. 1987–1994. [15: M.Hofmann et al. 2013]M.Hofmann, D.Wolf, G.Rigoll, ”Hypergraphs for Joint Multi-View Reconstruction and Multi-Object Tracking” CVPR 2013. [16: S.S. Blackman 2004]S.S.Blackman, ”Multiple hypothesis tracking for multiple target tracking” IEEE Aerospace and Electronic System Magazine Vol.19, Jan 2004 [17: B.Habtemarian et al.2013]B. Habtemarian, R. Tharmarasa, T. Thayaparan, M. Mallick, and T. Kirubarajan,” A Multiple-Detection Joint Probabilistic Data Association Filter”, IEEE Journal of Selected Topics in Signal Processing, VOL.7,NO.3,June 2013 [18: H.A.P. Blom et al.2002]H.A.P Blom and E. A. Bloem,” Intercting multiple model joint probabilistic data association avoiding track coalescence,”, in Proc. IEEE Conf. Decision Control, Dec.2002, vol.3, pp.3408-3415 [19: D.Musicki et al.2004]D. Musicki and R.Evans,” Joint integrated probabilistic data association: JIPDA”, IEEE Trans. Aerosp. Electron Syst. Vol.40,pp.1093-1099,Jul.2004 [20: Alex Bewley et al. 2017]Alex Bewley, Zongyuan Ge, Lionel Ott, Fabio Ramos and Upcroft, “Simple Online And Realtime Tracking”, ICIP 2016 [21: P.Dollar et al.2014]P. Dollar, R. Appel, S. BeLongie, and P.Perona, ”Fast Feature Pyramids for Object Detection”, Pattern Analysis and Machine Intelligence, vol.36, 2014 [22: Nicolai Wojke et al. 2017]Nicolai Wojke, Alex Bewley and Dietrich Paulus, “Simple online and Realtime Tracking with a Deep Association Metric”, ICIP 2017 [23: Long Chen et al.2018]Long Chen, Haizhou Ai, Zijie Zhuang, Chong Shang, “Real-Time Multiple People Tracking With Deeply Learned Candidate Selection and Person Re-Identification” ICME 2018 [24: Zhongdao Wang et al. 2020]Zhongdao Wang, Liang Zheng, Yixuan Liu and Shengjin Wang, “Towards Real-Time Multi-Object Tracking” ECCV 2020 [25: S.L.Fockstader et al.2001]S.L.Dockstader and A.M.Tekalp, “Multiple camera fusion for multi-object tracking,” in Proc.IEEE Workshop Multi-object Tracking, 2001,pp.95-102 [26: Yuanlu Xu et al. 2016]Yuanlu Xu, Xiaobai Liu, Yang Liu and Song-Chun Zhu,” Multi-view People Tracking via Hierachical Trajectory Composition, ” CVPR,2016 [27: M.Ayazoglu et al.2011]M.Ayazoglu, B.Li,C.Dicle ,M.Sznaier, and P.Camps, ”Dynamic subspace-space based coordinated multicamera tracking”. Proc, ICCV,2011 [28: S. Khan et al.2006]S. Khan and M. Shah, “A Multiview approach to tracking people in crowded scenes using a planar homography constrain”, Proc. ECCV 2006 [29: F. Fleuret et al. 2008]F. Fleuret, J. Berclaz, R. Lengagne, and P. Fua, “Multi-camera people tracking with a probabilistic occupancy map” IEEE Trans. PAMI, 30(2) [30: J. Berclaz et al. 2011]J. Berclaz, F.Fleuret, E. Turetken, and P. Fua, “ Multiple object tracking using k-shortest paths optimization”, IEEE Trans. PAMI, VOL. 33, September 2011 [31: L. Leal-Taixe et al.2012]L. Leal-Taixe, G. Pons-Moll, and B. Rosenhahn. “ Branch-and-price global optimization for multi-view multi-object tracking”, Proc. CVPR, 2012 [32: M.Hofmann et al. 2013]M. Hofmann, D. Wolf, and G. Rigoll, “Hypergraphs for joint-multi-view reconstruction and multi-object tracking”, CVPR, 2013 [33: H. Shitrit et al. 2013]H. Shitrit, J. Berclaz, F. Fleuret, and P. Fua, “Multi-commodity network flow for tracking multiple people”, IEEE Trans. PAMI, 2013 [34: T.L. Munea et al. 2020]T.L. Munea , Y.Z. Jembre, H.T.Weldegebriel, L. Chen, C. Huang, and C. Y ,”The Progress of Human Pose Estimation: A Survey and Taxonomy of Models Applied in 2D Human Pose estimation” IEEE Access July, 2020 [35: G. Lan et al.2023]G. Lan, Yu Wu, Fei Hu, and Qi Hao, “Vision-Based Human Pose Estimation via Deep Learning: A survey” IEEE Transactions on Human-Machine Systems. Vol.53, No.1, Feb. 2023 [36: Alexander Toshev et al. 2014]Alexander Toshev, Christian Szegedy, “DeepPose: Human Pose Estimation via Deep Neural Networks” CVPR 2014 [37: J. Tompson et al. 2014]J. Tompson, A. Jain, Y. LeCun, C. Bregler, “Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation”, NIPS 2014 [38: Bin Xiao et al.2018]Bin Xiao, Haiping Wu and Yichen Wei, “Simple Baselines for Human Pose Estimation and Tracking”, ECCV 2018 [39: A. Newell wt al. 2016]A. Newell, K. Yang, J. Deng, “Stacked Hourglass Networks for Human Pose Estimation”, ECCV 2016 [40: Xiao Chu et al. 2017]Xiao Chu, Wanli Ouyang, Cheng Ma, Alan L. Yuile and XiaoGang Wang, “Multi-Context Attention for Human Pose Estimation”, CVPR 2017 [41: Wei Yang 2017]Wei Yang , Shuang Li, Wanli Ouyang and HongSheng Li, Xiaogang Wang, “Learning Feature Pyramids for Human Pose Estimation” ICCV 2017 [42: K. He et al. 2017]K. He, G. Gkioxari, P. Dollar and R. Girshick, “Mask R-CNN”, ICCV 2017 [43: Hao-Shu Fang et al. 2017]Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, and Cewu Lu, “RMPE: Regional Multi-person Pose Estimation”, IEEE International Conference on Computer Vision, 2017 [44: A. Newell et al. 2016]A. Newell, Z. Huang, J. Deng, “Associative Embedding : End-to-End Learning for Joint Detection and Grouping”, NIPS 2017 [45: S. Jin et al.2020]S. Jin, W. Liu, E. Xie, W. Wang, C. Qian, W. Ouyang and P. Luo,“ Differentiable Hierarchical Graph Grouping for Multi-person Pose Estimation” ECCV 2020 [46: J. Martinez et al. 2017]J. Martinez, R. Hossain, J. Romero and J. J. Little,”A simple yet effective baseline for 3d human estimation” ,ICCV 2017 [47: D. Mehta et al. 2018]D. Mehta et al. “Single-shot multi-person 3D pose estimation from monocular RGB”, in Proc. Int. Conf. 3D human pose estimation 2018 [48: K. Iskakov et al. 2019]K. Iskakov, E. Burkov, V. Lempitsky and Y. Malkov, “Learnable Triangulation of Human Pose” , in Proc. IEEE int. Conf, Computer. Vis.2019 [49: H. Qiu et al. 2019]H. Qiu, C. Wang, J. Wang, N. Wang and W. Zeng, “Cross View Fusion for 3D Human Pose Estimation”, ICCV 2019 [50: Y. He et al. 2020]Y. He, R. Yan and K. Fragkiadaki, “Epipolar Transformers”, CVPR 2020 [51: J. Dong et al.2019]J. Dong, W. Jiang, Q. Huang, H. Bao and X. Zhou, “Fast and Robust Multi-person 3D Pose Estimation from Multiple Views” CVPR 2019 [52: A. Elmi et al. 2020]A. Elmi, D. Mazzini, P. Tortella, “Light3DPose: Real-time Multi-Person 3D Pose Estimation from Multiple Views”, ICPR 2020 [53: Hao-Shu Fang et al. 2020]Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai and Cewu Lu, “RMPF: Regional Multi-Person Pose Estimation”, ICCF, 2020 [54: J. Redmon et al.2018]J. Redmon and A. Farhadi, ” Yolov3: An incremental improvement,” arXiv preprint arXiv: 1804.02767, 2018 [55: M.Tan et al. 2020]M. Tan, R. Pang, and Q. V. Le, “Effecientdet: Scalable and efficient object detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020 [56: Hao-Shu Fang et al.2022]Hao-Shu Fang, Jiefeng Li, Hongyang Tang, Chao Xu, Haoyi Zhu, Yuliang Xiu, Yong-Lu Li, and Cewu Lu, “AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time” IEEE Transaction on Pattern Analysis And Machine Intelligence, 2022 [57: M. Jaderberg et al. 2015]M. Jaderberg, K. Simonyan, A. Zisserman, ”Spatial transformer networks”, Conference on Neural Information Processing Systems, pages 2017-2025, 2015. [58: Szeliski 2011]Richard Szeliski, “Computer Vision: Algorithms and Applications,” 1st ed., Editors: David Gries and F. B. Schneider, London: Springer, 2011. [59: Z.Zhang 2000]Z. Zhang,”A flexible new technique for camera calibration”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Nov, 2000 [60: Ahmed.T.Kamal et al. 2013]A.T.Kamal, J.A.Farrell, A.K.Roy-Chowdhury, “Information Weighted Consensus Filters and Their Application in Distributed Camera Networks”, IEEE Transaction on Automatic Control, VOL.58, No.12, Dec.2013 [61: P. C. Mahalanobis 1936]P.C.Mahalanobis, “On the Generalized Distance in Statistics”, Jan, 1936. [62: H.W. Kuhn 1995]H.W. Kuhn, “The Hungarian Method For The Assignment Problem”, Naval Research Logistics Quarterly Vol.2, Issue 1-2 [63: S.Zhu 2015]S.Zhu, Y.C.Soh, L. Xie, “Distributed Parameter Estimation with Quantized Communication via Running Average”, IEEE Transactions on Signal Processing, 2015 [68: Chiao Lai 2022]Chiao Lai, “A Markerless Multi-view 3D Human Motion Estimation System for Single Person with Modified Unscented Kalman Filter and iteractive LQR tracking”, National Taiwan University Master Thesis. [2: zhihu 2021]Zhihu“如何看待中國跳水隊使用3D AI技術訓練”August 2021. [Online]. Available: https://www.zhihu.com/question/478617195 [3: yahoo!新聞 2020]Yahoo!新聞 “放任競速滑冰隊？小巨蛋一堆人被撞倒“ September 2020.[Online] Available:https://tw.news.yahoo.com/放任競速滑冰隊-小巨蛋-堆人被撞倒--081545881.html?guccounter=1 [64: Hungarian algorithm]Available: https://en.wikipedia.org/wiki/Hungarian_algorithm [65: Epipolar geometry]Available: https://en.wikipedia.org/wiki/Epipolar_geometry [66: GigE industrial cameras]Available:https://www.theimagingsource.com/en-us/product/industrial/33g/ [67: COCO]Available: http://mscoco.org/dataset/#keypoints-leaderboard, 2016 | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88965 | - |
| dc.description.abstract | 近年來，隨著生活品質的提升，許多娛樂項目也越來越大衆化，例如冰上滑冰或者輪滑等。但是在人員較繁雜的環境中，一些行爲會對自身或者周圍人造成威脅。在這種情況下就需要工作人員去提醒，但是往往場館較大人員密集，工作人員沒辦法在每個區域内都能進行即時的檢測。而在這些大型場館内又存在不同角度和位置的相機，如何使用監控相機所獲取的影像流進行場館内各目標的追蹤和對其行爲進行分析，便是本文所想要討論的部分。
在本論文中，想要解決的主要問題是如何使用多臺相機中的數據，在三維空間中達成一個共識，并且在三維空間中構建姿態估測結果，以在未來能夠精準地對一些動作進行分析。 於是在本論文中，提出了一個使用信息共識濾波器進行信息融合和追蹤的系統。首先使用二維的姿態估測結果進行追蹤以及匹配每個目標的觀測值。然後在三維空間中進行重建以及再一次的信息融合。獲取準確的姿態估測位置。然後進行行爲分析所相關的計算。在該方法中，并不直接使用三維姿態估測的方法，以減少使用三維追蹤和構建估測結果的計算量以及減小對設備算力的要求。 最後，本篇論文展示了實驗結果來討論所提出的方法的有效性。 | zh_TW |
| dc.description.abstract | In recent years, with the improvement of the quality of life, many entertainment projects have become more and more popular, such as skating or roller skating. However, in these cases with a large number of people, some behaviors will pose a threat to themselves or the people around them. In these cases, the staff in venue needs to remind and forbid these actions. However, the scalers of these activities are often big and staffs can’t carry out real-time detection in every area. In these large venues, usually, contain many cameras of different angles and positions to picture the frame in the venues. How to use these images obtained by the surveillance cameras around the venues to track and analyze the behaviors of each target in the venue is the part that this thesis wants to discuss.
In this thesis, the main problem to be solved is how to use data from camera network to reach a consensus in 3D space, and construct pose estimation results from 2D to 3D space, so as to accurately perform some actions in the future analysis. So in this thesis, a system using information consensus filters for information fusion and tracking is proposed. The 2D pose estimation method is used firstly. And then using the filters to track and match the observations of each target. Reconstruction and information fusion again are then carried out in 3D space. Get an accurate pose estimation position. The calculations associated with the behavioral analysis are then performed. In this method, the method of 3D pose estimation is not directly used, so as to reduce the calculation amount of using 3D tracking. Moreover, without using 3D pose estimation method also can reduce the requirement on the computing power of the device. Finally, this thesis presents experimental results to discuss the effectiveness of the proposed method | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-16T16:33:51Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-08-16T16:33:51Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 摘要 i
ABSTRACT iii CONTENTS v LIST OF FIGURES ix LIST OF TABLES xiii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Problem Formulation 4 1.3 Contributions 8 1.4 Organization of the Thesis 11 Chapter2 Background and Literature Survey 13 2.1 Human Pose Estimation (HPE) 13 2.1.1 Monocular Human Pose Estimation 14 2.1.2 Multi-view Human Pose Estimation 16 2.2 Moving Object Tracking with Images 17 2.2.1 Multi-target Tracking 17 2.2.2 Multi-view Tracking 19 2.2.3 Multiple Camera Multiple Target Tracking 20 Chapter3 Related Algorithm 23 3.1 AlphaPose 23 3.2 Camera Model and Epipolar Geometry 25 3.3 Information Consensus Filter 29 3.4 Mahalanobis Distance 33 Chapter 4 System Overview 37 4.1 System Structure of Camera Network 37 4.2 Coordinate Frames 40 4.3 System Architecture 41 4.3.1 3D Multi-target Tracking 41 4.3.2 Motion Analysis 42 Chapter 5 3D Multi-target Tracking 45 5.1 Camera Calibration 45 5.2 3D Multi-target Tracking and Reconstruction 47 5.2.1 Data Processing 49 5.2.2 Measurement Matching 56 5.2.3 Information Consensus Filter 57 5.2.4 3D Skeleton Reconstruction 62 Chapter 6 Motion Analysis 65 6.1 Speeding 65 6.2 Direction and Reverse 69 6.3 Side-by-side 71 Chapter 7 Experimental Results and Analysis 73 7.1 Single Target Tracking 73 7.1.1 Experiments Setups 74 7.1.2 Overview of Experiments and Tested Cases 78 7.1.3 Parameters Setting 82 7.1.4 Normal Cases Experimental Results 84 7.1.5 Noise Cases Experimental Results 104 7.1.6 Summary of the Single Target Tracking Results 126 7.2 Multi-target Tracking and Motion Analysis 128 7.2.1 Experiments Setups 128 7.2.2 Overview of Experiments and Test Cases 131 7.2.3 Experimental Results 134 7.2.4 Summary of the Multi-target Experiments 150 Chapter 8 Conclusion and Future Works 153 8.1 Conclusion 153 8.2 Future Works 154 References 157 | - |
| dc.language.iso | en | - |
| dc.subject | 姿態估測 | zh_TW |
| dc.subject | 影像處理 | zh_TW |
| dc.subject | 信號分析 | zh_TW |
| dc.subject | 信息融合 | zh_TW |
| dc.subject | 多目標追蹤及定位 | zh_TW |
| dc.subject | Image processing | en |
| dc.subject | multi-target tracking and positioning | en |
| dc.subject | signal processing | en |
| dc.subject | information fusion | en |
| dc.subject | multi-camera system | en |
| dc.subject | pose estimation | en |
| dc.title | 基於信息共識濾波器之多相機多目標追蹤及行爲分析系統 | zh_TW |
| dc.title | A Multi-target Tracking and Motion Analysis System with Camera Network with Information Consensus Filter | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 林沛群;顏炳郎 | zh_TW |
| dc.contributor.oralexamcommittee | Pei-Chun Lin;Ping-Lang Yen | en |
| dc.subject.keyword | 影像處理,信號分析,信息融合,多目標追蹤及定位,姿態估測, | zh_TW |
| dc.subject.keyword | Image processing,signal processing,information fusion,multi-target tracking and positioning,pose estimation,multi-camera system, | en |
| dc.relation.page | 163 | - |
| dc.identifier.doi | 10.6342/NTU202303120 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2023-08-10 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電機工程學系 | - |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 9.05 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。