基於邊緣運算和YOLO的智慧長照人臉辨識系統

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：46

、訪客IP：3.145.202.60

姓名

周子翔(Tzu-Hsiang Chou) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

基於邊緣運算和YOLO的智慧長照人臉辨識系統
(Smart Long-Term Care Facial Recognition System based on Edge Computing and YOLO)

相關論文

★ UHF頻段RFID彈藥管理系統之設計、實作與評估	★ 移動物偵測與追蹤之IP Camera系統
★ SDN自適應性自動化網路安全之研究	★ Wi-Fi Direct Service 應用於IoT
★ 射頻前端電路應用於載波聚合長期演進技術	★ 3C無線充電裝置運用在車載系統所產生之EMI輻射
★ 基於LoRa技術的物聯網前端防盜警示感測裝置實作與評估	★ DOCSIS 3.1 效能研究與下行通道干擾阻隔之設計
★ 藍芽無線光學投影翻譯筆	★ 手持裝置應用於MIMO ( 8x8 ) Wi-Fi系統之設計
★ 基於無伺服器運算之智慧農業雲端系統設計與研究	★ 嵌入式系統實現電梯物聯網
★ 在802.11 Ad-Hoc網路中基於速率考量之路由協定設計	★ 合作博弈與灰色模糊方法改善無線網路之性能
★ 採用拍賣策略之動態分散式方法於減少叢集小型基地台間干擾之研究	★ 在LTE-A下聚合未授權頻譜及動態分配資源以優化系統效能

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

至系統瀏覽論文 (2025-7-20以後開放)

摘要(中)

隨著人口老齡化的加劇，智慧長照的需求也日益增長。在智慧長照場景下，如何快速、準確地識別長者身份成為了一個亟待解決的問題。人臉辨識技術因其非接觸式、高效率的優點而受到廣泛關注，也成為智慧長照場景下人員識別的重要手段之一。
本論文採用樹莓派作為邊緣裝置，透過YOLO和三元組網路來實現人臉辨識，並利用邊緣運算的概念，樹莓派可以在本地端完成人臉辨識任務，不必將數據傳輸到伺服器或雲端進行集中式處理，同時也能保障用戶的隱私和資料安全。最後，本研究將辨識結果儲存於AWS雲端服務中，如果有狀況發生，可透過Line Bot通知相關人員進行處理。這種基於邊緣運算的人臉辨識系統可以大大減少數據傳輸和處理時間，提高了系統的即時性和效率。

摘要(英)

With the intensification of population aging, the demand for smart elderly care is increasing. In the context of smart elderly care, how to quickly and accurately identify the identity of the elderly has become an urgent problem. Face recognition technology has received wide attention in the field of smart elderly care due to its non-contact and efficient advantages, and it has become an important means of personnel identification.
This thesis uses Raspberry Pi as an edge device to implement face recognition through YOLO and triplet networks. By utilizing the concept of edge computing, Raspberry Pi can complete the face recognition task locally without transmitting data to a server or cloud for centralized processing, thus ensuring user privacy and data security. Finally, this study stores the recognition results in AWS cloud services. If any issues occur, relevant personnel can be notified through a Line Bot for further handling. This edge computing-based face recognition system significantly reduces data transmission and processing time, thereby improving the system′s real-time performance and efficiency.

關鍵字(中)

★ YOLO
★ 人臉辨識
★ 邊緣計算
★ 智慧長照

關鍵字(英)

★ YOLO
★ Face Recognition
★ Edge Computing
★ Smart Long-term Care

論文目次

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
圖目錄 vii
表目錄 ix
第一章序論 1
1-1 前言 1
1-2 研究動機 2
1-3 論文架構 4
第二章相關研究背景 5
2-1 邊緣運算 5
2-1-1 嵌入式裝置—樹莓派 7
2-1-2 Pi Camera 9
2-2 人臉辨識 10
2-2-1 主要步驟 10
2-2-2 人臉辨識的實現方法 12
2-3 物件偵測 14
2-3-1 YOLO 15
2-4 機器學習 17
2-4-1 卷積神經網路 CNN 18
2-4-2 資料強化 19
2-4-3 Triplet Loss 20
2-5 AWS雲端服務 22
2-5-1 IAM 23
2-5-2 Amazon S3 23
2-5-3 Amazon DynamoDB 24
2-6 Line 25
2-6-1 Line Bot 25
第三章系統架構與流程 27
3-1 場景比較與系統架構 27
3-1-1 場景比較 27
3-1-2 系統架構 29
3-2 伺服器端 30
3-2-1 收集人臉樣本 31
3-2-2 資料強化 32
3-2-3 訓練機器學習模型 34
3-2-4 更新人臉資料庫及部署模型 36
3-2-5 混淆矩陣及閾值選擇 38
3-3 邊緣端 41
3-3-1 預測辨識 43
3-3-2 預測前處理 44
3-3-3 連線雲端資料庫及發送Line Bot通知 46
第四章模擬與分析 48
4-1 模擬設定 48
4-1-1 機器學習模型設定 48
4-1-2 測試資料集 50
4-2 模擬結果 51
4-2-1 模型訓練結果 52
4-2-2 模型效能評估 55
4-2-3 系統運行效能 59
第五章結論與未來研究方向 60
參考文獻 62

參考文獻

[1] F. Cirillo, D. Gómez, L. Diez, I. E. Maestro, T. B. J. Gilbert and R. Akhavan, “Smart City IoT Services Creation Through Large-Scale Collaboration”, IEEE Internet of Things Journal, Vol.7, pp.5267-5275, 2020.
[2] B. L. Risteska Stojkoska and K. V. Trivodaliev, “A review of Internet of Things for smart home: Challenges and solutions”, Journal of Cleaner Production, Vol.140, pp.1454-1464, 2017.
[3] S. Qazi, B. A. Khawaja and Q. U. Farooq, “IoT-Equipped and AI-Enabled Next Generation Smart Agriculture: A Critical Review, Current Challenges and Future Trends”, IEEE Access, Vol.10, pp.21219-21235, 2022.
[4] M. Nasr, Md. M. Islam, S. Shehata, F. Karray and Y. Quintana, “Smart Healthcare in the Age of AI: Recent Advances, Challenges, and Future Prospects”, IEEE Access, Vol.9, pp.145248-145270, 2021.
[5] 網路資料on line resources︰Number of wide-area and short-range IoT devices worldwide from 2014 to 2027。取自https://www.statista.com/statistics/1016276/wide-area-and-short-range-iot-device-installed-base-worldwide/
[6] N. Abbas, Y. Zhang, A. Taherkordi and T. Skeie, “Mobile Edge Computing: A Survey”, IEEE Internet of Things Journal, Vol.5, pp.450-465, 2017.
[7] W. Shi, J. Cao, Q. Zhang, Y. Li and L. Xu, “Edge Computing: Vision and Challenges”, IEEE Internet of Things Journal, Vol.3, pp.637-646, 2016.
[8] M. Babar, M. S. Khan, F. Ali, M. Imran and M. Shoaib, “Cloudlet Computing: Recent Advances, Taxonomy, and Challenges”, IEEE Access, Vol.9, pp.29609-29622, 2021.
[9] A. K. Kyaw, H. P. Truong and J. Joseph, “Low-Cost Computing Using Raspberry Pi 2 Model B”, Journal of Computers, Vol.13, pp. 287-299, 2018.
[10] 網路資料on line resources︰Raspberry Pi Documentation。取自https://www.raspberrypi.com/documentation/computers/os.html
[11] 網路資料on line resources︰Raspberry Pi Camera Module 2。取自https://www.raspberrypi.com/products/camera-module-v2/
[12] R. Febbo, B. Flood, J. Halloy, P. Lau, K. Wong and A. Ayala, “Autonomous Vehicle Control Using a Deep Neural Network and Jetson Nano”, PEARC ′20: Practice and Experience in Advanced Research Computing, pp.333-338, 2020.
[13] I. Adjabi, A. Ouahabi, A. Benzaoui and A. Taleb-Ahmed, “Past, Present, and Future of Face Recognition: A Review”, Electronics, Vol.9, 2020.
[14] Y. Kortli, M. Jridi, A. Al Falou and M. Atri, “Face Recognition Systems: A Survey”, Sensors, Vol.20, 2020.
[15] T. Napoléon and A. Alfalou, “Pose invariant face recognition: 3D model from single photo”, Optics and Lasers in Engineering, Vol.89, pp.150-161, 2017.
[16] L. Lenc and P. Král, “Automatic face recognition system based on the SIFT features”, Computers & Electrical Engineering, Vol.46, pp.256-272, 2015.
[17] M. Turk and A. Pentland, “Eigenfaces for Recognition”, Journal of Cognitive Neuroscience, Vol.3, pp.71-86, 1991.
[18] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. E. Reed, C. Y. Fu and A. C. Berg, “SSD: Single Shot MultiBox Detector”, European Conference on Computer Vision (ECCV), pp.21-37, 2016.
[19] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[20] S. Ren, K. He, R. Girshick and J. Sun, “Faster R-CNN: towards real-time object detection with region proposal networks”, NIPS′15: Proceedings of the 28th International Conference on Neural Information Processing Systems, Vol.1, pp.91-99, 2015.
[21] O. Corcoll, “Semantic Image Cropping”, ArXiv, 2021
[22] A. Bochkovskiy, C. Y. Wang and H. Y. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection”, ArXiv, 2020, https://doi.org/10.48550/arXiv.2004.10934
[23] 網路資料on line resources︰YOLOv5。取自https://github.com/ultralytics/yolov5
[24] 網路資料on line resources︰Object Detection: 初探YOLOV5爭議以及與YOLOV4之比較。取自https://pedin024.medium.com/%E5%88%9D%E6%8E%A2yolov5-71f13b4ba78d
[25] 網路資料on line resources︰Yolo-FastestV2。取自https://github.com/dog-qiuqiu/Yolo-FastestV2
[26] J. Alzubi1, A. Nayyar and A. Kumar, “Machine Learning from Theory to Algorithms: An Overview”, Journal of Physics: Conference Series, Vol.1142, 2018.
[27] 網路資料on line resources︰卷積神經網路的運作原理。取自https://brohrer.mcknote.com/zh-Hant/how_machine_learning_works/how_convolutional_neural_networks_work.html
[28] L. Perez and J. Wang, “The Effectiveness of Data Augmentation in Image Classification using Deep Learning”, ArXiv, 2017.
[29] E. Hoffer and N. Ailon, “Deep Metric Learning Using Triplet Network”, Similarity-Based Pattern Recognition, Vol.9370, pp.84-92, 2015.
[30] D. Chicco, “Siamese Neural Networks: An Overview”, Methods in molecular biology, Vol.2190, pp.73-94, 2021.
[31] F. Schroff, D. Kalenichenko and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[32] S. Bankar, “Cloud Computing Using Amazon Web Services (AWS)”, International Journal of Trend in Scientific Research and Development (ijtsrd), Vol.2, pp.2156-2157, 2018.
[33] 網路資料on line resources︰Amazon Macie。取自https://aws.amazon.com/tw/macie/features/
[34] 網路資料on line resources︰Amazon GuardDuty。取自https://aws.amazon.com/tw/guardduty/features/
[35] 網路資料on line resources︰IAM。取自https://docs.aws.amazon.com/zh_tw/IAM/latest/UserGuide/introduction.html
[36] 網路資料on line resources︰Amazon S3。取自https://docs.aws.amazon.com/zh_tw/AmazonS3/latest/userguide/Welcome.html
[37] 網路資料on line resources︰Amazon DynamoDB。取自https://docs.aws.amazon.com/amazondynamodb/latest/developerguide/Introduction.html
[38] 網路資料on line resources︰LINE。取自https://zh.wikipedia.org/zh-tw/LINE
[39] S. Lee, J. Lee, W. Lee, S. Lee, S. Kim and E. T. Kim, “Design of Integrated Messenger Anti-virus System using Chatbot Service”, 2020 International Conference on Information and Communication Technology Convergence (ICTC), 2020.
[40] S. Yang, P. Luo, C. C. Loy and X. Tang, “WIDER FACE: A Face Detection Benchmark”, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
[41] G. B. Huang, M. Mattar, T. L. Berg and E. Learned-Miller, “Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments”, University of Massachusetts: Amherst, Technical Report 07-49, 2007.
[42] 網路資料on line resources︰Cascade Classifier。取自https://docs.opencv.org/3.4/db/d28/tutorial_cascade_classifier.html
[43] M. Sandler, A. G. Howard, M. Zhu, A. Zhmoginov and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks”, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[44] 網路資料on line resources︰Gaussian filter。取自https://en.wikipedia.org/wiki/Gaussian_filter
[45] 網路資料on line resources︰Cross entropy。取自https://en.wikipedia.org/wiki/Cross_entropy
[46] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization”, International Conference on Learning Representations (ICLR), 2015.

指導教授

吳中實(Jung-Shyr Wu)

審核日期

2023-7-20

推文