請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93169完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 覺文郁 | zh_TW |
| dc.contributor.advisor | WEN-YUH JYWE | en |
| dc.contributor.author | 賴柏綸 | zh_TW |
| dc.contributor.author | PO-LUN LAI | en |
| dc.date.accessioned | 2024-07-22T16:11:16Z | - |
| dc.date.available | 2024-07-23 | - |
| dc.date.copyright | 2024-07-22 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-07-15 | - |
| dc.identifier.citation | [1] M. Jovanovic and M. Campbell, "Generative artificial intelligence: Trends and prospects," Computer, vol. 55, no. 10, pp. 107-112, 2022.
[2] F. Manuri and A. Sanna, "A survey on applications of augmented reality," ACSIJ Advances in Computer Science: an International Journal, vol. 5, no. 1, pp. 18-27, 2016. [3] K. A. Kobbacy, D. P. Murthy, L. Pintelon, and A. Parodi-Herz, "Maintenance: an evolutionary perspective," Complex system maintenance handbook, pp. 21-48, 2008. [4] X. Mehmeti, B. Mehmeti, and R. Sejdiu, "The equipment maintenance management in manufacturing enterprises," IFAC-PapersOnLine, vol. 51, no. 30, pp. 800-802, 2018. [5] R. Ravnå and P. Schjølberg, "Industry 4.0 and Maintenance," Norsk Forening for Vedlikehold (NFV), 2016. [6] 王若珩, "建立MR智慧巡檢系統應用於HoloLens及穿戴裝置," Master, 國立臺灣大學, 2023. [7] 資誠（PwC Taiwan）, 財團法人資訊工業策進會, and 中華民國軟體資訊協會, "臺灣中小企業數位轉型現況調查," 2021. [Online]. Available: https://digital-trans-survey.com/download_file/2021%E8%87%BA%E7%81%A3%E4%B8%AD%E5%B0%8F%E4%BC%81%E6%A5%AD%E8%BD%89%E5%9E%8B%E7%8F%BE%E6%B3%81%E5%8F%8A%E9%9C%80%E6%B1%82%E8%AA%BF%E6%9F%A5.pdf [8] I. E. Sutherland, "A head-mounted three dimensional display," in Proceedings of the December 9-11, 1968, fall joint computer conference, part I, 1968, pp. 757-764. [9] P. C. Thomas and W. David, "Augmented reality: An application of heads-up display technology to manual manufacturing processes," in Hawaii international conference on system sciences, 1992, vol. 2: ACM SIGCHI Bulletin, pp. 659-669. [10] L. B. Rosenberg, "The use of virtual fixtures to enhance operator performance in time delayed teleoperation," Journal of Dynamic Systems Control, vol. 49, no. 1, pp. 29-36, 1993. [11] W. Piekarski and B. Thomas, "ARQuake: the outdoor augmented reality gaming system," Communications of the ACM, vol. 45, no. 1, pp. 36-38, 2002. [12] L. Madden, Professional augmented reality browsers for smartphones: programming for junaio, layar and wikitude. John Wiley & Sons, 2011. [13] 愛范兒 ifanr. "Google Glass發布10年了！吵著要取代手機的AR眼鏡，為什麼總是紅不起來？." 數位時代bnext. https://www.bnext.com.tw/article/73091/ar-glasses-product? (accessed 2024-06-04. [14] A. Haddick. "Pokémon is no longer just a game — it’s a lifestyle." The Verge,. https://www.theverge.com/23970890/pokemon-poketsume-transformation-games-brand (accessed 2024-06-04. [15] G. Evans, J. Miller, M. I. Pena, A. MacAllister, and E. Winer, "Evaluating the Microsoft HoloLens through an augmented reality assembly application," in Degraded environments: sensing, processing, and display 2017, 2017, vol. 10197: SPIE, pp. 282-297. [16] Microsoft. "HoloLens 2–概觀、功能和規格." Microsoft. https://www.microsoft.com/zh-tw/hololens/hardware#%E8%A8%98%E9%8C%84%E9%AB%94%E9%A9%97 (accessed 2024-06-04. [17] ARLOOPA Inc. Augmented and Virtual Reality Apps. "ARLOOPA是一款AR體驗APP." Google Play Store. https://play.google.com/store/apps/details?id=com.arloopa.arloopa&hl=zh-TW&pli=1 (accessed 2022-07-19. [18] SevenD GmbH. "AR Viewer (Augmented Reality)." Google Play Store. https://play.google.com/store/apps/details?id=com.ipol.arviewer.app (accessed 2024-06-04). [19] Fectar BV. "Fectar | Meet in AR Metaverse." Google Play Store. https://play.google.com/store/apps/details?id=io.spoton.viewer (accessed 2024-06-04. [20] Grymala apps. "AR Ruler: 測量尺,尺子量度,直尺量度,ar量度器." Google Play Store. https://play.google.com/store/apps/details?id=com.grymala.aruler (accessed 2024-06-04. [21] Grymala apps. "ARPlan 3D 捲尺，尺子量度，平面圖測繪，AR 測距儀." Google Play Store. https://play.google.com/store/apps/details?id=com.grymala.arplan (accessed 2024-06-04. [22] micware. "PinnAR AR擴增實境行人導航." Google Play Store. https://play.google.com/store/apps/details?id=jp.co.telecomsquare.app.pinnar (accessed 2024-06-04. [23] Routes Software SRL. "PeakVisor - 3D地圖、山峰識别." Google Play Store. https://play.google.com/store/apps/details?id=tips.routes.peakvisor (accessed 2024-06-04. [24] Jet Propulsion Laboratory. "Spacecraft AR." Google Play Store. https://play.google.com/store/apps/details?id=gov.nasa.jpl.spacecraftAR (accessed 2024-06-04. [25] Arthur Arzumanyan. "AR Solar System." Google Play Store. https://play.google.com/store/apps/details?id=com.ar.solar (accessed 2024-06-04. [26] Augmented/Virtual Reality Lens & Creator (LightUp). "Animal Safari AR." Google Play Store. https://play.google.com/store/apps/details?id=io.lightup.safari (accessed 2024-06-04. [27] DIGI SPACE. "AR PLAZA." Google Play Store. https://play.google.com/store/apps/details?id=tw.com.arplaza (accessed 2024-06-04. [28] LiveABC. "Outstanding AR." Google Play Store. https://play.google.com/store/apps/details?id=com.liveabc.outstandingar (accessed 2024-06-04. [29] Dell Inc. "Dell AR Assistant." Google Play Store. https://play.google.com/store/apps/details?id=com.dell.arassist (accessed 2024-06-04. [30] D. V. E. LLC. "AR Art Projector: Da Vinci Eye." Google Play Store. https://play.google.com/store/apps/details?id=com.cubemg.davincieye (accessed 2024-06-04. [31] TeamViewer. "TeamViewer Assist AR (Pilot)." Google Play Store. https://play.google.com/store/apps/details?id=com.teamviewer.pilot (accessed 2024-06-04. [32] C. Jin and D. Tong, "Wearable Device-Based Intelligent Patrol Inspection System Design and Implementation," International Journal of Distributed Systems and Technologies (IJDST), vol. 14, no. 2, pp. 1-10, 2023. [33] H. Yu, S. Yan, W. Ma, Y. Sun, and J. Li, "Design and Implementation of MR Patrol Inspection System Based on Digital Twins," in 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2022, vol. 10: IEEE, pp. 2560-2564. [34] J. Wang and Y. Qi, "A multi-user collaborative AR system for industrial applications," Sensors, vol. 22, no. 4, p. 1319, 2022. [35] K. Osaki et al., "Development of a Patrol System Using Augmented Reality and 360-Degree Camera," in Advances in Condition Monitoring and Structural Health Monitoring: WCCM 2019: Springer, 2021, pp. 365-373. [36] B. Jansen, T. Goodwin, V. Gupta, F. Kuipers, and G. Zussman, "Performance evaluation of WebRTC-based video conferencing," ACM SIGMETRICS performance evaluation review, vol. 45, no. 3, pp. 56-68, 2018. [37] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788. [38] J. Terven and D. Cordova-Esparza, "A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond," arXiv preprint arXiv:2304.00501, 2023. [39] C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, "YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information," arXiv preprint arXiv:2402.13616, 2024. [40] CH.Tseng. "YOLOV9論文導讀及使用." chtseng.wordpress.com. https://chtseng.wordpress.com/2024/03/01/yolov9%E8%AB%96%E6%96%87%E5%B0%8E%E8%AE%80%E5%8F%8A%E4%BD%BF%E7%94%A8/ (accessed 2024-06-06. [41] R. Zellers, A. Holtzman, Y. Bisk, A. Farhadi, and Y. Choi, "Hellaswag: Can a machine really finish your sentence?," arXiv preprint arXiv:1905.07830, 2019. [42] K. Guu, K. Lee, Z. Tung, P. Pasupat, and M. Chang, "Retrieval augmented language model pre-training," in International conference on machine learning, 2020: PMLR, pp. 3929-3938. [43] P. Lewis et al., "Retrieval-augmented generation for knowledge-intensive nlp tasks," Advances in Neural Information Processing Systems, vol. 33, pp. 9459-9474, 2020. [44] D. Merkel, "Docker: lightweight linux containers for consistent development and deployment," Linux j, vol. 239, no. 2, p. 2, 2014. [45] M. H. Ibrahim, M. Sayagh, and A. E. Hassan, "A study of how Docker Compose is used to compose multi-component systems," Empirical Software Engineering, vol. 26, pp. 1-27, 2021. [46] R. Johns. "PyTorch vs TensorFlow for Your Python Deep Learning Project." https://realpython.com/pytorch-vs-tensorflow/ (accessed 2024-06-10. [47] Samsung Mobile Press. "Galaxy Note9." Samsung Mobile Press,. https://www.samsungmobilepress.com/media-assets/galaxy_note9/?tab=specs (accessed 2024-06-25. [48] Samsung 台灣. "規格| Samsung Galaxy S23 Ultra | Samsung 台灣." Samsung. https://www.samsung.com/tw/smartphones/galaxy-s23-ultra/specs/ (accessed 2024-06-25. [49] M. I. Maulana. "waste object Dataset." Roboflow. https://universe.roboflow.com/muhammad-iqbal-maulana-c9irx/waste-object (accessed 2024-06-10. [50] A. Wannakrairot. "Gauge detection Dataset." Roboflow. https://universe.roboflow.com/anupong-wannakrairot-ud9ty/gauge-detection-cohbz (accessed 2024-06-10. [51] O. Detection. "Gauge_Detection Dataset." Roboflow. https://universe.roboflow.com/object-detection-3horq/gauge_detection-xmljs (accessed 2024-06-10. [52] T.-Y. Lin et al., "Microsoft coco: Common objects in context," in Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, 2014: Springer, pp. 740-755. [53] S. J. Pan and Q. Yang, "A survey on transfer learning," IEEE Transactions on knowledge and data engineering, vol. 22, no. 10, pp. 1345-1359, 2009. [54] A. Kane. "pgvector: Open-source vector similarity search for Postgres." github. https://github.com/pgvector/pgvector (accessed 2024-06-12. [55] Unity. "About Unity Render Streaming." Unity. https://docs.unity3d.com/Packages/com.unity.renderstreaming@3.1/manual/index.html (accessed 2024-06-12. [56] Unity. "About Signaling Type." Unity. https://docs.unity3d.com/Packages/com.unity.renderstreaming@3.1/manual/signaling-type.html (accessed 2024-06-13. [57] SOLOMON Technology Corporation. "SOLOMON META-aivi 全球首創穿戴式AI+AR眼鏡." SOLOMON. https://www.solomon-3d.com/tw/solomon-meta-aivi/ (accessed 2024-06-20. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/93169 | - |
| dc.description.abstract | 隨著工業4.0的發展和智慧製造的演進，工業設備的巡檢需求日益增加。傳統巡檢方式往往依賴人工操作，效率低且容易受到主觀因素影響，導致結果不穩定。為了提升巡檢效率和準確性，本研究開發了一套基於生成式人工智慧（Generative AI）和擴增實境（Augmented Reality, AR）的智慧巡檢系統，應用於Android平台的可攜式裝置。
本系統集成了生成式人工智慧技術、影像辨識技術與AR技術，設計並實現了庫存盤點、指針式錶頭數值判讀、機台型號辨識和遠端專家協作影像串流等功能。系統透過YOLOv9模型進行影像辨識，能夠自動檢測庫存數量、判讀錶頭數值，並結合生成式人工智慧知識系統自動分析和提供問題解決方案。系統同時也具備影像串流功能，能夠實現巡檢人員與遠端專家的即時通訊。 在伺服器的設計中，使用Docker技術進行容器化，實現了高效的部署和維護。本研究透過多階段的技術整合，有效提升了工業巡檢的自動化程度，降低了人力成本，並提高了巡檢結果的精確性和一致性。 系統測試結果顯示，基於YOLOv9模型的影像辨識技術具備高準確度，並且系統在影像串流方面的延遲亦有進行比較，能夠滿足即時巡檢需求。未來，將繼續優化生成式人工智慧模型，並探索其在巡檢應用中的潛力。 | zh_TW |
| dc.description.abstract | With the advancement of Industry 4.0 and the evolution of smart manufacturing, the demand for industrial equipment inspections is increasing. Traditional inspection methods often rely on manual operations, which are inefficient and susceptible to subjective influences, leading to inconsistent results. To enhance inspection efficiency and accuracy, this study develops an intelligent inspection system based on Generative Artificial Intelligence (Generative AI) and Augmented Reality (AR), applied to portable devices on the Android platform.
The system integrates Generative AI technology, image recognition technology, and AR technology, and it is designed to perform inventory counting, analog gauge value reading, machine model recognition, and remote expert collaboration via video streaming. The system utilizes the YOLOv9 model for image recognition, allowing automatic detection of inventory quantities, gauge value interpretation, and combining Generative AI knowledge systems to automatically analyze and provide problem-solving solutions. The system features video streaming capabilities, enabling real-time communication between inspection personnel and remote experts. In the server design, Docker technology is used for containerization, achieving efficient deployment and maintenance. This research effectively enhances the automation of industrial inspections through multi-stage technical integration, reducing labor costs and improving the accuracy and consistency of inspection results. System testing results show that the image recognition technology based on the YOLOv9 model exhibits high accuracy, and the system’s latency in video streaming has been compared, meeting real-time inspection needs. Future work will continue to optimize the Generative AI model and explore its potential in inspection applications. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-07-22T16:11:16Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-07-22T16:11:16Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 I
誌謝 II 摘要 III ABSTRACT IV 目次 V 圖次 VIII 表次 X 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機 2 1.3 研究目的 3 第二章 文獻探討 4 2.1 傳統巡檢方法 4 2.2 AR技術發展歷程 5 2.3 現有AR應用程式 5 2.4 AR相關技術應用於巡檢[6] 8 2.5 影像串流技術 9 2.6 YOLO影像辨識模型發展 10 2.7 YOLOV9影像辨識模型 11 2.8 檢索增強生成（RAG） 16 2.9 DOCKER容器化 17 第三章 系統架構 19 3.1 系統建立流程 19 3.2 庫存盤點影像辨識技術 21 3.3 指針式錶頭數值判讀之影像辨識技術 22 3.4 生成式人工智慧知識系統整合技術 23 3.5 遠端專家協作影像串流技術 24 3.6 系統應用情境與架構 25 第四章 研究方法 27 4.1 研究使用設備 27 4.2 影像辨識訓練資料集 31 4.3 影像辨識模型訓練 37 4.4 指針式錶頭數值判讀演算法 41 4.5 影像辨識伺服器建立 44 4.6 以DOCKER容器部署影像辨識伺服器 46 4.7 生成式人工智慧知識系統建立 47 4.8 WEBRTC影像串流方法 48 4.9 終端使用者應用程式 49 第五章 研究結果與討論 50 5.1 YOLO影像辨識模型訓練結果 50 5.2 UNITY RENDER STREAMING影像串流延遲測試結果 60 5.3 應用程式使用情境 62 5.4 伺服器容器化與DOCKER-COMPOSE部署 66 5.5 討論 67 5.6 SOLOMON META-AIVI與本研究系統比較 68 第六章 結論與未來展望 70 6.1 結論 70 6.2 未來展望 70 參考文獻 74 | - |
| dc.language.iso | zh_TW | - |
| dc.title | 建立一智慧巡檢系統基於生成式人工智慧與AR技術 | zh_TW |
| dc.title | Establishing a Smart Inspection System Based on Generative AI and Augmented Reality | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 112-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 謝東賢;熊仕傑;潘明憲 | zh_TW |
| dc.contributor.oralexamcommittee | TUNG-HSIEN HSIEH;SHIH-CHIEH HSIUNG;MING-HSIEN PAN | en |
| dc.subject.keyword | 生成式人工智慧,擴增實境,影像辨識,YOLOv9,工業巡檢, | zh_TW |
| dc.subject.keyword | Generative Artificial Intelligence,Augmented Reality,Image Recognition,YOLOv9,Industrial Inspection, | en |
| dc.relation.page | 78 | - |
| dc.identifier.doi | 10.6342/NTU202401777 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2024-07-16 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 機械工程學系 | - |
| 顯示於系所單位： | 機械工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-112-2.pdf 目前未授權公開取用 | 6.44 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。