請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85150完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 韓仁毓(Jen-Yu Han) | |
| dc.contributor.author | Chun-Ting Chen | en |
| dc.contributor.author | 陳俊廷 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:46:43Z | - |
| dc.date.copyright | 2022-08-26 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-09 | |
| dc.identifier.citation | Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934. Bureau of police research and development. (2019). Data of police organizations. India. VSK Kaumudl. Cao, Z., Simon, T., Wei, S. E., & Sheikh, Y. (2017). Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7291-7299). Criminisi, A., Reid, I., & Zisserman, A. (2000). Single view metrology. International Journal of Computer Vision, 40(2), 123-148. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 2961-2969). Ji, T., & Pachi, A. (2005). Frequency and velocity of people walking. Struct. Eng, 84(3), 36-40. Jung, J., Yoon, I., Lee, S., & Paik, J. (2016). Object detection and tracking-based camera calibration for normalized human height estimation. Journal of Sensors, 2016. Lee, D. S., Kim, J. S., Jeong, S. C., & Kwon, S. K. (2020). Human height estimation by color deep learning and depth 3D conversion. Applied Sciences, 10(16), 5531. Ljungberg, J., & Sönnerstam, J. (2008). Estimation of human height from surveillance camera footage-a reliability study. Lv, F., Zhao, T., & Nevatia, R. (2006). Camera calibration from video of a walking human. IEEE transactions on pattern analysis and machine intelligence, 28(9), 1513-1518. Ohashi, T., Ikegami, Y., & Nakamura, Y. (2020). Synergetic reconstruction from 2d pose and 3d motion for wide-space multi-person video motion capture in the wild. Image and Vision Computing, 104, 104028. Park, S., Hwang, J., & Kwak, N. (2016, October). 3d human pose estimation using convolutional neural networks with 2d pose information. In European Conference on Computer Vision (pp. 156-169). Springer, Cham. Rogez, G., Weinzaepfel, P., & Schmid, C. (2017). Lcr-net: Localization-classification-regression for human pose. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 3433-3441). Tang, Z., Lin, Y. S., Lee, K. H., Hwang, J. N., Chuang, J. H., & Fang, Z. (2016, December). Camera self-calibration from tracking of moving persons. In 2016 23rd International Conference on Pattern Recognition (ICPR) (pp. 265-270). IEEE. Tang, Z., Gu, R., & Hwang, J. N. (2018, July). Joint multi-view people tracking and pose estimation for 3D scene reconstruction. In 2018 IEEE International Conference on Multimedia and Expo (ICME) (pp. 1-6). IEEE. Tekin, B., Katircioglu, I., Salzmann, M., Lepetit, V., & Fua, P. (2016). Structured prediction of 3d human pose with deep neural networks. arXiv preprintarXiv:1605.05180. Viswanath, P., Kakadiaris, I. A., & Shah, S. K. (2009, September). A simplified error model for height estimation using a single camera. In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops (pp. 1259-1266). IEEE. Wolf, P. R., Dewitt, B. A., & Wilkinson, B. E. (2014). Elements of Photogrammetry with Applications in GIS. McGraw-Hill Education. 許舜翔，(2019)。以跨鏡頭多目標追蹤分析建築內使用者行為，國立台灣大學土木工程學研究所碩士論文，台北市。 沈禮文、邱釗、彭貴超、黃萍、李超、蔡金曄，(2020)。監控視頻密集人群的人數統計系統設計，海南大學計算機與網路空間安全學院,圖像與信號處理-漢斯出版社，9(4):202-210。 鄒芳諭、史天元，(2009)。以非量測性相機進行近景攝影測量探討，交通大學土木工程學系碩士論文，新竹市。 劉立文、杜信宏，(2014)。我國勞工人體計測調查研究，勞動部勞動及職業安全衛生研究所。 | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85150 | - |
| dc.description.abstract | 基於統計顯示，監視器數量隨著年代開始成倍數成長，全球已超過1億支監視器被安裝與使用，然而影像紀錄內容仍需要仰賴人力介入辨識，才能夠達到監測之目的。本研究藉由單影像監視器進行室內影像的收集，並運用目前精準且快速的深度學習模型，如Yolov4、Openpose協助快速抓取行人影像。基於攝影測量學理建立嚴謹物像關係，以及套用最小二乘法推算行人於物空間坐標位置和精度指標作為後續評估分析。最後所萃取行人行走時多樣性指標，如行走的頻率、速度以及行人的幾何資訊來建立行人特有的特徵向量，並分析跨監視器影像之特徵向量相似性，藉以實現跨監視器之行人追蹤。 研究成果論證應用深度學習能自動準確偵測欲追蹤影像目標資訊，每幀影像耗費1~1.5秒辨識行人於影像中位置。萃取行走指標中行人幾何資訊，結合誤差傳播模型所得精度指標做加權分析來提高成果的可靠度。本研究結果獲取誤差落在±1公分幾何資訊，並利用單相中影像變化，萃取該行人於場景中行走頻率，成功辨識跑步的行人落在1.91Hz頻率，與慢走的行人使用0.92Hz進行慢走。藉由多樣化的行人特徵，強化跨影像追蹤之可靠度。未來進行室內場域管理，能夠基於本研究實現行人資訊的萃取與追蹤。延伸可應用於警方查緝犯人逃跑軌跡，或是即時監測場域內行人意外等即時探測，提升監視器影像於空間管理應用與價值。 | zh_TW |
| dc.description.abstract | According to statistics, there are around 1 billion surveillance have been installed and used. However, the content of video still needs to be identified by human intervention in order to achieve the purpose of monitoring. This research will collect indoor surveillance’s image. The current accurate and fast deep learning models, such as Yolov4, Openpose, etc., are used to quickly capture human in the image. A rigorous object-image relationship constructs based on the collinear of photogrammetry and least squares method. Then calculate the geometric information of the pedestrian. And it will extract more information from walking human, such as the frequency of walking and the speed of walking. Finally, the unique feature vector of the pedestrian is established, and applied to achieve cross-image pedestrian trajectory tracking. From the research results, it applies deep learning models to automatically and accurately capture image information. And calculate the spatial information of pedestrians by rigorous relationship. Moreover, the pedestrian geometric information could be combined with the accuracy indicators. These indicators obtained through the error propagation model for weighted analysis, and provided to improve the reliability of the results. The results of this study obtained the geometric information with an error of ±1 cm. Then extract the walking frequency of the pedestrian in the scene. It successfully identified running human using a frequency of 1.91Hz and walking slowly using a frequency of 0.92Hz. The reliability of cross-image tracking is going to enhance with diverse pedestrian features. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:46:43Z (GMT). No. of bitstreams: 1 U0001-1206202221063400.pdf: 8306295 bytes, checksum: 2d78aa26e09e80cf8a916f02a6c0bc53 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | 摘要 i ABSTRACT ii 目錄 iii 圖目錄 v 表目錄 vii 第一章 緒論 1 1.1 研究背景 1 1.2 研究目的 2 1.3 研究流程 2 1.4 論文架構 2 第二章 文獻回顧 4 2.1 應用深度學習偵測與捕捉人體動作 4 2.2 運用攝影測量重建三維場景與整合人體姿態 7 2.3 透過單張相片進行幾何資訊判斷與行人追蹤 8 2.4 統計行人行走頻率與身體幾何資訊 10 2.5 小節 12 第三章 研究方法 13 3.1 率定相機內方位參數與解算外方位參數 13 3.2 深度學習模型之使用與分析 17 3.2.1 Yolov4測試 17 3.2.2 Openpose測試 18 3.2.3 結合Yolov4與Openpose萃取資訊整合 18 3.3萃取人體幾何資訊 19 3.4精化外方位參數與校正幾何資訊 20 3.5追蹤人體資訊與姿態分析 22 3.6整合資訊與進行跨場景行人追蹤 24 3.7小節 25 第四章 研究成果及討論 26 4.1 驗證用監視器與測試環境 26 4.2 率定監視器內外方位參數 27 4.3 推算一次率定後行人幾何資訊 31 4.3.1行人身高與肩高解算成果比較 31 4.3.2不同行人率定外方位參數對幾何推算影響 32 4.4 相機二次率定後校正行人幾何資訊 36 4.4.1 應用最小二乘法修正假設平面 37 4.4.2 擬合假設平面並較正一次率定解算的幾何資訊 38 4.5 應用傅立葉轉換推算行人行走頻率 40 4.6 建立特徵向量實現行人跨場域辨識與追蹤 44 第五章 結論及未來工作 49 5.1結論 49 5.2建議與未來工作 49 參考資料 51 | |
| dc.language.iso | zh-TW | |
| dc.subject | 影像三維重建 | zh_TW |
| dc.subject | 智慧化監視器 | zh_TW |
| dc.subject | 行人姿態分析 | zh_TW |
| dc.subject | 人體幾何資訊萃取 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 3D Reconstruct | en |
| dc.subject | Intellectual surveillance | en |
| dc.subject | Human pose analysis | en |
| dc.subject | Human geometry information | en |
| dc.subject | Deep Learning | en |
| dc.title | 透過監視器影像之人體幾何資訊萃取與行動分析 | zh_TW |
| dc.title | Human body geometry extraction and motion analysis based on surveillance camera images | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 賴靜慧(Ching-Huei Lai),吳日騰(Rih-Teng Wu),林彥廷 | |
| dc.subject.keyword | 影像三維重建,深度學習,人體幾何資訊萃取,行人姿態分析,智慧化監視器, | zh_TW |
| dc.subject.keyword | 3D Reconstruct,Deep Learning,Human geometry information,Human pose analysis,Intellectual surveillance, | en |
| dc.relation.page | 53 | |
| dc.identifier.doi | 10.6342/NTU202200923 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-08-10 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| dc.date.embargo-lift | 2022-08-26 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1206202221063400.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 8.11 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。