(3.236.175.108) 您好!臺灣時間:2021/02/27 05:44
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:::

我願授權國圖
: 
twitterline
研究生:邱俊銘
研究生(外文):Chun-Ming Chiu
論文名稱:以最佳化技術為基礎之感測網路視頻監控之卸載與路由策略
論文名稱(外文):Optimization Based Offloading and Routing Strategies for Video Surveillance in Sensor Networks
指導教授:林永松林永松引用關係
指導教授(外文):Yeong-Sung Lin
口試委員:溫演福呂俊賢鍾順平林宜隆
口試日期:2019-07-26
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊管理學研究所
學門:電算機學門
學類:電算機一般學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:46
中文關鍵詞:物聯網邊際運算視訊監控卸載路由
DOI:10.6342/NTU201902289
相關次數:
  • 被引用被引用:0
  • 點閱點閱:56
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
近來物聯網(IoT)感應器被賦予的功能與運算需求越發複雜,隨著邊際運算技術的成熟提升與人工智慧(AI)晶片的誕生,使得這些高運算功能得以被實現。邊際運算的理論和架構也在近年趨近於成熟引入了邊際雲的概念,對於感應器耗時過久的計算,能夠卸載給靠近物聯網端的邊際雲協助運算,而非如傳統須將運算傳送給中心雲運算後才能將結果傳送給使用者,大大降低了服務的延遲時間物聯網也引入邊際運算的概念,使得低延遲服務運算能夠被妥善完成。然而由於以下IoT應用框架下的特點,系統的服務效能往往不能達到使用者可接受的程度:第一、感應器與邊際雲溝通時可用的通訊頻寬有限;第二、感應器硬體本身之運算資源有限;第三、低延遲服務之有效時間限制。再者,由於硬體特性緣故,各個感應器的處理效能與可偵測事件往往不盡相同,因此當發生感應器自身所無法之事件發生時,感應器須將此事件發生時之視訊傳送給可處理這類事件偵測之感應器,或是傳回給邊際雲,又或是中心雲做處理,這大大提申了服務卸載的困難度某些類型服務須經過多階段的運算處理,且需要特定硬體規格的主機才能夠滿足該階段功能之運算需求。感應器本身無法獨自完成運算,因此需要將該服務卸載給邊際雲完成後續運算,也增加了服務卸載的困難度。故本文的研究主要內容為在智慧城市之應用情景下如何將產生視訊串流之感應器,如:網路監控攝影機,在事件發生時將其安排給可處理的合適對象結合路由規劃對其所負責偵測事件所需的各個運算功能進行有效的運算排程規劃,並考慮上述之限制,目標是將整個物聯網系統單個事件偵測之服務運算時間和該事件所被賦予可接受運算時間之差距最大化,使得系統整體的服務使用品質能夠讓使用者所接受。
Nowadays, Internet-of-Things (IoT) sensors required more complicated computation power to serve video surveillance functions. With the advancement of edge computing technology and the birth of Artificial Intelligence chips make it possible for high computing capacity required services to be served.
Edge computing, also known as cloudlet, adopts the concept of edge cloud. When the service that requires high computing cost for IoT sensors to compute, the computation task will send to cloudlet to perform the task. Unlike traditional cloud computing, the sensors don''t have to send the raw data that route through multiple hops to the cloud for doing computation. In edge computing scenario, the sensors only need to submit the raw data to the edge cloud, which is the closest cloud to the IoT network, which significantly reduces the latency of the service. 
However, due to the properties of IoT applications, the system tends to be inefficient and is not acceptable by the users as the following reasons. Such as insufficient computation power of sensor''s hardware, insufficient bandwidth between the sensors and the cloudlet and tolerable delay of real-time service. 
Moreover, the computing capacity and detecting functions of sensors varied among sensor hardware. For example, when an event is detected, the coordinate sensor happens to unable to handle the event. This sensor needs to send the video to a sensor, cloudlet, or core cloud where it can handle the event. Moreover, our approach would use the constraint to make the offloading decision. 
In our work, we focus on Smart City scenario. Our method not only can decide the offloading and routing strategy for each video gathering capability nodes but also considering the overall system constraints to maximize the minimum delay gap between the tolerable delay and the system service time. With this, the quality-of-experience (QoE) of the IoT system can be fulfilled.
中文摘要 I
Abstract II
Table of Contents IV
List of Figures VII
List of Tables VIII
Chapter 1. Introduction 1
1.1. Background 1
1.2. Motivation 3
1.3. Objective 4
1.4. Research Scope 5
Chapter 2. Literature Survey 6
2.1. Events Detection 6
2.2. Edge Computing 7
2.3. Video Surveillance 7
Chapter 3. Model & Problem Description 9
3.1. Model 9
3.2. Problem Description 10
3.3. Problem Notations 11
3.4. Problem Formulation 13
Chapter 4. Solution Approach 17
4.1. Lagrangian Relaxation Method 17
4.2. Lagrangian Relaxation Objective Function and Constraints 17
4.2.1 Subproblem 1 20
4.2.2 Subproblem 2 21
4.2.3 Subproblem 3 22
4.2.4 Subproblem 4 23
4.2.5 Subproblem 5 24
4.2.6 Subproblem 6 25
4.2.7 Subproblem 7 26
4.2.8 Subproblem 8 27
4.2.9 Subproblem 9 27
4.2.10 Subproblem 10 28
4.2.11 Subproblem 11 29
4.2.12 Subproblem 12 30
4.2.13 Subproblem 13 30
4.2.14 Subproblem 14 31
4.3. Getting Primal Feasible Solution 32
Chapter 5. Computational Experiments 33
5.1. Experiment Environment 33
5.2. Algorithms for Comparison 34
5.2.1. First Fit 34
5.2.2. All Core 34
5.3. Experiment Result 34
5.3.1 Experiment of Number of Source Nodes 35
5.3.2 Experiment of Number of Total Nodes 36
5.3.3 Experiment on Data Size 38
5.3.4 Experiment of Number of Events 39
Chapter 6. Conclusions and Future Work 42
6.1. Conclusions 42
6.2. Discussion 43
6.3. Future Work 43
References 45
[1]C. Long, Y. Cao, T. Jiang, and Q. Zhang, “Edge Computing Framework for Cooperative Video Processing in Multimedia IoT Systems,” in IEEE Transactions on Multimedia, vol. 20, no. 5, pp. 1126-1139, May 2018.
[2]F. Ahmad, A. Najam, and Z. Ahmed, “Image-based Face Detection and Recognition: State of the Art,” in IJCSI International Journal of Computer Science Issues, vol. 9, no. 6, pp. 169-172, Nov. 2012.
[3]E. Bermejo, O. Deniz, G. Bueno, and R. Sukthankar, “Violence Detection in Video Using Computer Vision Techniques,” Proc. 14th Int. Congress on Computer Analysis of Images and Patterns, pp. 332-339, Aug. 2011.
[4]N. True, “Computer Vision Based Fire Detection”. [Online]. Available: https://pdfs.semanticscholar.org/46f6/63bd1d32cdbec9b7ba206d471f94b9bbc03f.pdf
[5]F. Samie, V. Tsoutsouras, L. Bauer, S. Xydis, D. Soudris, and J. Henkel, “Computation Offloading and Resource Allocation for Low-Power IoT Edge Devices,” Proc. IEEE 3rd World Forum Internet Things (WF-IoT), pp. 7-12, Dec. 2016.
[6] N. Chen, Y. Chen, Y. You, H. Ling, and R. Zimmermann, “Dynamic Urban Surveillance Video Stream Processing Using Fog Computing,” Proc. the 2nd IEEE International Conference on Multimedia Big Data (BigMM 2016), pp. 105-112, 2016.
[7]N. Chen, Y. Chen, E. Blasch, H. Ling, Y. You, and X. Ye, “Enabling Smart Urban Surveillance at The Edge,” Proc. 2017 IEEE International Conference on Smart Cloud (SmartCloud), pp. 109-119, 2017.
[8]G. L. Foresti, “Object Recognition and Tracking for Remote Video Surveillance,” in IEEE Transactions on Circuits and Systems for Video Technology, vol. 9, no. 7, pp. 1045-1062, Oct. 1999.
[9]H. Guo, J. Liu, and H. Qin, “Collaborative Mobile Edge Computation Offloading for IoT over Fiber-Wireless Networks,” in IEEE Network, vol. 32, no. 1, pp. 66-71, Jan.-Feb. 2018.
[10]L. Hu and Q. Ni, “IoT-Driven Automated Object Detection Algorithm for Urban Surveillance Systems in Smart Cities,” in IEEE Internet of Things Journal, vol. 5, no. 2, pp. 747-754, Apr. 2018.
[11]P. Gorur and B. Amrutur, “Skip Decision and Reference Frame Selection for Low-Complexity H.264/AVC Surveillance Video Coding,” in IEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 7, pp. 1156-1169, Apr. 2014.
[12]G. Gualdi, A. Prati, and R. Cucchiara, “Video Streaming for Mobile Video Surveillance,” in IEEE Transactions on Multimedia, vol. 10, no. 6, pp. 1142-1154, Oct. 2008.
[13]Y. Ye, S. Ci, A. K. Katsaggelos, Y. Liu, and Y. Qian, “Wireless Video Surveillance: A Survey,” in IEEE Access, vol. 1, pp. 646-660, Sep. 2013.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔