跳到主要內容

臺灣博碩士論文加值系統

(44.192.44.30) 您好!臺灣時間:2024/07/25 08:52
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳穎劭
研究生(外文):Chen, Yin-Shao
論文名稱:使用頂照攝影機網路的多人物追蹤
論文名稱(外文):Tracking Multiple Persons with a Network of Ceiling-Mounted Cameras
指導教授:王才沛
指導教授(外文):Wang, Tsai-Pei
口試委員:莊政宏王才沛黃敬群
口試委員(外文):Chuang, Cheng-HungWang, Tsai-PeiHuang, Ching-Chun
口試日期:2020-12-24
學位類別:碩士
校院名稱:國立交通大學
系所名稱:資訊科學與工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:109
語文別:中文
論文頁數:31
中文關鍵詞:樹莓派多目標追蹤攝影機網路
外文關鍵詞:Raspberry Picamera networkmulti-target tracking
相關次數:
  • 被引用被引用:1
  • 點閱點閱:256
  • 評分評分:
  • 下載下載:15
  • 收藏至我的研究室書目清單書目收藏:0
多目標追蹤相關研究已發展多年,也開始有許多實際應用。本篇研究使用頂照式樹莓派攝影機在無人商店中進行人物多目標追蹤。頂照式攝影機相較一般投射式擁有較大視野,並且不易被障礙物遮擋,可以有較佳的追蹤效果。樹莓派也擁有計算能力,可以在拍攝影像同時進行追蹤運算。本篇論文在樹莓派上拍攝影像並做人物偵測,進行初步的多目標追蹤,最後整合無人商店中多台樹莓派攝影機的追蹤結果。
本研究中也加入使用深度學習模型的人物偵測與人物特徵提取,與傳統多目標追蹤方式做比較。
Research on multi-target tracking has been developed for many years, and it has begun to have many practical applications. In this thesis, a top-view Raspberry Pi camera was used for multi-target tracking of people in checkout-free shops. Top-view cameras have larger coverage than common projective cameras and have less mutual occlusion, which can lead to better tracking results. Raspberry Pi also has computing ability, which can perform multi-target tracking operations while filming. In this thesis, Raspberry Pi cameras take images and perform multi-target tracking. After that, the tracking results of multiple Raspberry Pi cameras in the checkout-free shops will be integrated and calculate the trajectories.
This research also adds person detection and person feature extraction using deep learning models to compare with traditional multi-target tracking methods.
摘要 i
Abstract ii
誌謝 iii
目錄 iv
圖目錄 vi
表目錄 vii
第一章 緒論 1
1.1 研究背景 1
1.2 研究目的 1
1.3 論文架構 3
第二章 文獻探討 4
2.1 多目標追蹤 4
2.2 多相機追蹤 4
第三章 研究方法 6
3.1 實驗場景 6
3.1.1 樹莓派設置 6
3.1.2 相機校正 6
3.1.3 實驗資料蒐集 7
3.1.4 Ground truth標記 8
3.2 實驗架構 9
3.3 樹莓派分散式人物偵測 9
3.3.1 前後景分離與人物位置計算 9
3.3.2 YOLOv3與VPTZ 10
3.4 樹莓派上的人物追蹤 12
3.4.1 人物追蹤軌跡 13
3.4.2 基於顏色的人物特徵提取 14
3.4.3 Mobilenet的人物特徵提取 14
3.3.3 混和YOLOv3與前後景分離的人物追蹤 15
3.5 世界座標追蹤軌跡 16
第四章 實驗結果 18
4.1 追蹤之準確度的標準 18
4.2 實驗結果 19
4.3.1 不同人物偵測方式之實驗 19
4.3.2 不同攝影機配置對追蹤結果的影響 22
4.3.3 人物外觀相似度實驗 25
4.3.4 樹莓派追蹤配對成本計算實驗 26
4.3.5 世界座標追蹤配對成本計算實驗 27
第五章 結論與未來展望 29
參考文獻 30
[1] W. Luo, J. Xing, A. Milan, X. Zhang, W. Liu, X. Zhao, and T.-K. Kim, “Multiple object tracking: A literature review,” arXiv: 1409.7618v4, pp. 1–18, 2017.
[2] J. Krumm, S. Harris, B. Meyers, B. Brumitt, M. Hale and S. Shafer, "Multi-camera multi-person tracking for EasyLiving," Proceedings Third IEEE International Workshop on Visual Surveillance, Dublin, Ireland, 2000, pp. 3-10, doi: 10.1109/VS.2000.856852.
[3] K. Kim and L. Davis, “Multi-Camera Tracking and Segmentation of Occluded People on Ground Plane Using Search-Guided Particle Filtering,” Proc. Ninth European Conf. Computer Vision, 2006.
[4] W. Du and J. Piater, “Multi-Camera People Tracking by Collaborative Particle Filters and Principal Axis-Based Integration,” Proc. Asian Conf. Computer Vision, pp. 365-374, 2007
[5] M. C. Liem and D. M. Gavrila, “Joint multi-person detection and tracking from overlapping cameras,” Comput. Vis. Image Understand., vol. 128, pp. 36–50, Nov. 2014.
[6] H. Possegger, S. Sternig, T. Mauthner, P. M. Roth, and H. Bischof, “Robust real-time tracking of multiple objects by volumetric mass densities,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jun. 2013, pp. 2395–2402.
[7] T. -. Chang and S. Gong, "Tracking multiple people with a multi-camera system," Proceedings 2001 IEEE Workshop on Multi-Object Tracking, Vancouver, BC, Canada, 2001, pp. 19-26, doi: 10.1109/MOT.2001.937977.
[8] E. Ristani and C. Tomasi, “Features for multi-target multi-camera tracking and re-identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2018, pp. 6036–6046.
[9] Y. Xu, X. Liu, Y. Liu,and S. C. Zhu, “Multi-view people tracking via hierarchical trajectory composition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recogn., pp. 4256-4265, 2016.
[10] B. Li, “People Tracking with a Network of Top-View Raspberry-Pi Camera Network” 2019.
[11] L. Meinel, M. Findeisen, M. Heß, A. Apitzsch and G. Hirtz, "Automated real-time surveillance for ambient assisted living using an omnidirectional camera," 2014 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, 2014, pp. 396-399, doi: 10.1109/ICCE.2014.6776056.
[12] J. Bromley, J. W. Bentz, L. bottou, I. Guyon, Y. LeCun, C. Moore, E. S¨ackinger, and R. Shah, “Signature verification using a siamese time delay neural network,” Int. J. Pattern Recognit. Artificial Intell., vol. 7, no. 4, pp. 669–687, Aug. 1993.
[13] A. Bewley, Z. Ge, L. Ott, F. Ramos and B. Upcroft, "Simple online and realtime tracking," 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 2016, pp. 3464-3468, doi: 10.1109/ICIP.2016.7533003.
[14] N. Wojke, A. Bewley and D. Paulus, "Simple online and realtime tracking with a deep association metric," 2017 IEEE International Conference on Image Processing (ICIP), Beijing, 2017, pp. 3645-3649, doi: 10.1109/ICIP.2017.8296962.
[15] S. Tang, B. Andres, M. Andriluka, and B. Schiele. Multiperson tracking by multicut and deep matching. In ECCV Workshops, 2016.
[16] N. Wingfield. “Inside Amazon Go, a Store of the Future”, The New York Times, Jan. 21, 2018, [Online]. Available: https://www.nytimes.com/2018/01/21/technology/inside-amazon-go-a-store-of-the-future.html. [Accessed Dec. 7 2020].
[17] F. Weng, “Human detection and attribute recognition on fisheyes images using deep learning” 2019.
[18] N. Wojke and A. Bewley, "Deep Cosine Metric Learning for Person Re-identification," 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, 2018, pp. 748-756, doi: 10.1109/WACV.2018.00087.
[19] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top