研究生: |
連翊安 Yi-An Lian |
---|---|
論文名稱: |
基於深度學習與分散式框架之智慧監控系統 Intelligent Surveillance System Based on Deep Learning and Distributed Computing Framework |
指導教授: |
陳永耀
Yung-Yao Chen |
口試委員: |
阮聖彰
Shanq-Jang Ruan 呂政修 Jenq-Shiou Leu 林郁修 Yu-Hsiu Lin |
學位類別: |
碩士 Master |
系所名稱: |
電資學院 - 電子工程系 Department of Electronic and Computer Engineering |
論文出版年: | 2022 |
畢業學年度: | 110 |
語文別: | 中文 |
論文頁數: | 51 |
中文關鍵詞: | 雲運算 、邊緣運算 、邊緣雲協作 、物件偵測 、像監控 |
外文關鍵詞: | cloud computing, edge computing, edge-cloud collaboration, object detection, video surveillance |
相關次數: | 點閱:303 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
物聯網與人工智慧的結合引領新的風潮,將“智慧城市”的概念從理想變成現實。 其中影像監控在智慧城市中是十分重要的應用,通常是採用雲運算的方式實現,然而雲運算是基於集中式框架會將收集到的資料集中到雲端處理,優點在於雲端具有強大的運算資源,可以大量分析及處理資料,缺點在於無法即時分析與處理資料。因此,本文提出了基於深度學習與分散式框架之智慧監控系統,並進行了初步設置。本文中提出使用邊緣運算的技術來改善集中式框架的問題,因為邊緣運算可以在本地端執行人工智慧,此技術可以用來加速AIoT(AI 結合 IoT)的發展,並在智慧城市中應用於不同的領域,使人工智慧落地。 其中,本文們結合邊緣運算與雲端運算形成邊緣雲計算,通過在分散式邊緣節點上的人工智慧的將本地端的知識整合到雲端,並在雲端實現全球知識的人工智慧,並將全球知識分享給在分散式邊緣節點上的人工智慧進行即時影像監控。
The combination of IoT and artificial intelligence (AI) leads a new trend, turning the concept of "smart city" from an ideal into a reality. Among them, image monitoring is a very important application in smart cities. It is usually implemented by cloud computing. However, cloud computing is based on a centralized framework that will collect collected data in the cloud for processing. The advantage is that the cloud has powerful computing resources. It can analyze and process a large amount of data, but the disadvantage is that it cannot analyze and process data in real time. Therefore, this paper proposes an intelligent monitoring system based on deep learning and a decentralized framework, and conducts preliminary settings. This paper proposes the use of edge computing technology to improve the problem of centralized framework, because edge computing can perform AI on the local side, this technology can be used to accelerate the development of AIoT (AI combined with IoT) and applied in different smart cities the field of AI. Among them, this paper combines edge computing and cloud computing to form edge cloud computing, integrates local knowledge into the cloud through AI on distributed edge nodes, realizes AI of global knowledge in the cloud, and shares global knowledge with AI on distributed edge nodes for real-time video surveillance.
[1] H. Zhao, L.Yao, Z. Zeng, D. Li, J. Xie, W. Zhu, & J. Tang, "An edge streaming data processing framework for autonomous driving," in Connection Science, vol. 33, no. 2, pp. 173-200, 2021.
[2] Z. Xu, J. Li, & M. Zhang, "A surveillance video real-time analysis system based on edge-cloud and FL-YOLO cooperation in coal mine," in IEEE Access, no. 9, pp. 68482–6849, 2021.
[3] J. Ren, H. Guo, C. Xu, & Y. Zhang, " Serving at the edge: A scalable IoT architecture based on transparent computing," in IEEE Network., pp 96–105, 2017.
[4] W. Shi, & S. Dustdar, "The promise of edge computing, " in Computer, vol. 49, no. 5, pp. 78–81, 2016.
[5] Y. Y. Chen, & Y. H. Lin, "A smart autonomous time- and frequency-domain analysis current sensor-based power meter prototype developed over fog-cloud analytics for demand-side management," in Sensors, vol.19, no. 2, pp. 4443, 2019.
[6] S. S. Ahamad, & A.-S.K. Pathan, "A formally verified authentication protocol in secure framework for mobile healthcare during COVID-19-like pandemic, " in Connection Science, vol.33, no.3, pp. 532–554, 2020.
[7] R. Girshick,,J. Donahue, T. Darrell, and J. Malik, "Rich feature hierarchies for accurate object detection and semantic segmentation," Proceedings of IEEE conference on computer vision and pattern recognition, pp. 580-58, 2014.
[8] R. Girshick, "Fast r-cnn," Proceedings of conference on computer vision, pp. 1440-1448, 2015.
[9] S. Ren, K. He, R. Girshick and J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2017.
[10] J. Redmon, S. Divvala, R. Girshick and A. Farhadi, "You only look once: Unified, real-time object detection," Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 779-788, 2016.
[11] J. Redmon, and A. Farhadi. "Yolov3: An incremental improvement." arXiv preprint arXiv:1804.02767, 2018
[12] A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
[13] L. Min, C. Qiang, and Y. Shuicheng," Network in network," arXiv preprint arXiv:1312.4400, 2013.
[14] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, and A. Rabinovich, "Going deeper with convolutions, " Proceedings of IEEE conference on computer vision and pattern recognition, pp. 1-9, 2015
[15] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "Mobilenets: Efficient convolutional neural networks for mobile vision applications," arXiv preprint arXiv:1704.04861, 2017.
[16] S. Han, J. Pool, J. Tran, and W. Dally, "Learning both weights and connections for efficient neural network, " Proceedings of neural information processing systems, vol. 28, 2015.
[17] H. Li, A. Kadav, I. Durdanovic, H. Samet, and H. P. Graf, "Pruning filters for efficient convnets, " arXiv preprint arXiv:1608.08710, 2016.
[18] G. Hinton, O. Vinyals, and J. Dean, “Distilling the knowledge in a neural network,” arXiv preprint arXiv:1503.02531, 2015.
[19] G. Chen, W. Choi, X. Yu, T. Han, and M. Chandraker, “Learning efficient object detection models with knowledge distillation,” Proceedings of neural information processing systems, vol. 30, 2017.
[20] H. Chen, Y. Wang, C. Xu, B. Shi, C. Xu, Q. Tian, and C. Xu, “AdderNet: Do we really need multiplications in deep learning?,” Proceedings of IEEE conference on computer vision and pattern recognition, pp. 1468-1477, 2020.
[21] B. Wu, A. Wan, X. Yue, P. Jin, S. Zhao, N. Golmant, A. Gholaminejad, J. Gonzalez, and K. Keutzer, “Shift: A zero flop, zero parameter alternative to spatial convolutions,” Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 9127-9135, 2018.
[22] L. Duan, Y. Lou, S. Wang, W. Gao and Y. Rui, "AI-Oriented Large-Scale Video Management for Smart City: Technologies, Standards, and Beyond," in IEEE MultiMedia, vol. 26, no. 2, pp. 8-20, 2019.
[23] T. G. Rodrigues, K. Suto, H. Nishiyama and N. Kato, "Hybrid Method for Minimizing Service Delay in Edge Cloud Computing Through VM Migration and Transmission Power Control," in IEEE Transactions on Computers, vol. 66, no. 5, pp. 810-819, 2017.
[24] M. B. Dillencourt, H. Samet, & M. Tamminen, "A general approach to connected-component labeling for arbitrary image representations, " J. ACM, vol. 39, no. 2, pp. 253–280, 1992.
[25] E. B. Varghese, and S. M. Thampi, "Towards the cognitive and psychological perspectives of crowd behaviour: A vision-based analysis, " in Connection Science, vol. 33, no. 2, pp. 380–405, 2021.
[26] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, & S. Zagoruyko, "End-to-end object detection with transformers, " Proceedings of European conference on computer vision pp. 213-229, 2020.
[27] M. A. Ezzat, M. A. AbdElGhany, S. Almotairi, & M. A. -M. Salem, "Horizontal review on video surveillance for smart cities: Edge devices, applications, datasets, and future trends, " in Sensors, vol. 21, no. 9, pp. 3222, 2021.
[28] K. He, X. Zhang, S. Ren, & J. Sun, "Deep residual learning for image recognition, " Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778,2016.
[29] C. Y. Wang, H. Y. Mark Liao, Y. H. Wu, P. -Y. Chen, J. W. Hsieh and I. H. Yeh, "CSPNet: A New Backbone that can Enhance Learning Capability of CNN," Proceedings of the IEEE conference on Computer Vision and Pattern Recognition Workshops, pp. 1571-1580, 2020.
[30] H. Kaiming, Z. Xiangyu, R. Shaoqing, and S. Jian, "Spatial pyramid pooling in deep convolutional networks for visual recognition, " in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no.9, pp. 1904–1916, 2015.
[31] L. Shu, Q. Lu, Q. Haifang, S. Jianping, and J. Jiaya, "Path aggregation network for instance segmentation, " Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759–8768, 2018.
[32] D. Zhixing, R. Zhang, M. Chang, S. Liu, T. Chen & Y. Chen, "Distilling object detectors with feature richness," Proceedings of Neural Information Processing Systems, vol. 34, 2021.
[33] T. Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, & C. L. Zitnick, "Microsoft coco: Common objects in context, " Proceedings of European conference on computer vision, pp. 740-755, 2014.
[34] K. Simonyan, & A. Zisserman, "Very deep convolutional networks for large-scale image recognition, " arXiv preprint arXiv:1409.1556, 2014.
[35] A. Krizhevsky, & G. Hinton, "Learning multiple layers of features from tiny images, " 2009.
[36] J. Frankle, & M. Carbin, "The lottery ticket hypothesis: Finding sparse, trainable neural networks, " arXiv preprint arXiv:1803.03635, 2018.
[37] S. Girish, S. R. Maiya, K. Gupta, , H. Chen, L. S. Davis, , & A. Shrivastava, "The lottery ticket hypothesis for object recognition, " Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 762-771, 2021.
[38] R. Duncan, "A survey of parallel computer architectures, " in Computer, vol. 23, no. 2, pp. 5-16, 1990.
[39] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt and B. Scholkopf, "Support vector machines," in IEEE Intelligent Systems and their Applications, vol. 13, no. 4, pp. 18-28, 1998.