( 您好!臺灣時間:2023/09/24 09:42
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::


論文名稱(外文):Intelligent IoT System in Conjunction with Edge Computing and Image Recognition to the Case of Wildfire Monitoring
外文關鍵詞:Forest firesWildfireCarbon sinkInternet of ThingsEdge ComputingImage RecognitionArtificial Intelligence
  • 被引用被引用:1
  • 點閱點閱:32
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1

In recent years, due to the continuous development of human economic activities, climate change has become increasingly serious, resulting in continuous disasters all over the world, among which forest fires are particularly important. Climate extremes brought by global warming lead to increase in forest fires. Therefore, a large amount of carbon dioxide is produced. At the same time, the carbon sink that the forest can absorb is lost, which undoubtedly aggravates global warming and falls into a vicious circle. This thesis takes forest fire monitoring as the research topic, and builds edge computing device for the forest fire monitoring system. Early warning of forest fires and early warning of fires and inform the relevant people to take actions as soon as possible to reduce the losses caused by forest fires. This thesis propose the following three-tier architecture of the Internet of Things. The perception layer uses one-dimensional time-series data (temperature, humidity) and two-dimensional time-series data (images, thermal imaging) as the basis for judging the occurrence of fire. Use image recognition to detect flames or smoke as early as possible, and measure temperature and humidity to judge whether the weather is prone to fire and push an alarm. The network layer uses 4G network to transmit images and data which provides wide bandwidth and relatively real-time network transmission. The application layer provides a visual monitoring interface that allow users to browse images and data of monitored areas on the web. This can let the user understand the current situation of the forest and take corresponding actions. It can be seen from the system test results that the mAP of the object detection results in this thesis can reach 92.6%. In the actual test results, it was detected by the system 1.01 seconds after the flame was generated. Received alert after 3.19 seconds. Finally, after 7.15 seconds, the streaming video processed by the system can be seen.
摘要 i
誌謝 iv
目錄 v
表目錄 viii
圖目錄 x
中英字詞對照表 xiii
1 第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究範圍與方法 2
1.3 論文架構與內容 4
2 第二章 文獻回顧 5
2.1 氣候變遷與永續發展 5
2.1.1 全球暖化與極端氣候 5
2.1.2 聯合國永續發展目標 6
2.1.3 臺灣永續發展方向 7
2.2 火災 9
2.2.1 火災原理及分類 9
2.2.2 森林火災 11
2.3 森林重要性 13
2.3.1 森林的定義 13
2.3.2 森林的價值 13
2.3.3 碳匯與常態化差異植生指標 14
2.4 物聯網系統 16
2.4.1 物聯網系統簡介 16
2.4.2 物聯網應用案例 18
2.5 邊緣運算 20
2.5.1 邊緣運算簡介 20
2.5.2 邊緣運算優勢 21
2.5.3 邊緣運算應用案例 21
2.6 人工智慧 23
2.6.1 機器學習 24
2.6.2 物件偵測 25
3 第三章 研究方法 27
3.1 物聯網系統介紹 27
3.1.1 感知層 27
3.1.2 網路層 32
3.1.3 應用層 33
3.1.4 供電層 35
3.1.5 森林火災監測系統 39
3.2 一維時序資料量測方法 41
3.2.1 儀器設備 41
3.2.2 溫度 43
3.2.3 相對濕度 43
3.3 二維時序資料量測方法 44
3.3.1 光學影像 44
3.3.2 紅外線熱成像 49
3.4 森林火災監測之方法 54
3.4.1 模擬情境概述 54
3.4.2 森林火災監測實踐 57
4 第四章 研究結果與討論 60
4.1 一維時序資料分析 60
4.1.1 溫度量測之分析 60
4.1.2 相對濕度量測之分析 61
4.2 二維時序資料分析 62
4.2.1 物件偵測結果 62
4.2.2 紅外線測溫結果 63
4.3 森林火災監測成效 65
4.3.1 監測頁面顯示 65
4.3.2 推播告警 67
4.3.3 火災啟動事件時序分析 68
4.4 森林火災監測結果與討論 70
5 第五章 結論與未來研究方向 72
5.1 結論 72
5.2 未來研究方向 73
參考文獻 75

[1]J. Wen, X.-X. Zhao, Q. Fu, and C.-P. Chang, "The impact of extreme weather events on green innovation: Which ones bring to the most harm?," Technological Forecasting and Social Change, vol. 188, p. 122-322, 2023.
[2]綠色和平,"什麼是氣候變遷?全球暖化的原因?有哪些影響?懶人包一次告訴你",取自:https://www.greenpeace.org/taiwan/update/22703/什麼是氣候變遷?全球暖化的原因?有哪些影響?/ (accessed 3/26, 2023)。
[4]國家災害防救科技中心,IPCC氣候變遷第六次評估報告之科學重點摘錄與臺灣氣候變遷評析更新報告,取自:https://tccip.ncdr.nat.gov.tw/km_abstract_one.aspx?kid=20210810134743 (accessed 03/26, 2023)。
[5]D. Herring, R. Lindsey, "What evidence exists that Earth is warming and that humans are the main cause?"取自:https://www.climate.gov/news-features/climate-qa/what-evidence-exists-earth-warming-and-humans-are-main-cause (accessed 03/26, 2023)。
[6]U. Nations, "Transforming our World: The 2030 Agenda for Sustainable Development." 取自:https://sdgs.un.org/2030agenda (accessed 03/26, 2023)。
[7]"Do you know all 17 SDGs?",取自:https://sdgs.un.org/goals#icons (accessed 02/05, 2023)。
[8]行政院國家永續發展委員會,"臺灣永續發展目標",取自:https://ncsd.ndc.gov.tw/Fore/AboutSDG (accessed 03/26, 2023)。
[9]張緒華,"拚淨零轉型 12項關鍵戰略年底提具體方案",取自:https://www.rti.org.tw/news/view/id/2147366 (accessed 03/26, 2023)。
[10]中華民國國家發展委員會,"臺灣2050淨零排放路徑及策略總說明",取自:https://www.ndc.gov.tw/Content_List.aspx?n=DEE68AAD8B38BD76 (accessed 04/09, 2023)。
[11]內政部消防署,"防火管理人講習訓練教材初訓-消防常識與火災預防",取自:https://www.nfa.gov.tw/pro/index.php?code=list&ids=750 (accessed 04/09, 2023)。
[14]"Global Forest Resources Assessment 2000.",取自:https://www.fao.org/3/Y1997E/Y1997E00.htm (accessed 03/26, 2023).
[15]吳俊賢,"森林的真正價值知多少",取自:https://www.forest.gov.tw/MagazineFile.aspx?fno=5250 (accessed 03/26, 2023)。
[16]Food and Agriculture Organization, "THE STATE OF THE WORLD’S FORESTS 2022." https://www.fao.org/3/cb9360en/online/cb9360en.html (accessed 03/26, 2023).
[17]T. Keenan and C. Williams, "The terrestrial carbon sink," Annual Review of Environment and Resources, vol. 43, pp. 219-243, 2018.
[18]C. C. Li et al., "Using NDVI percentiles to monitor real-time crop growth,", Comput. Electron. Agric., Article vol. 162, pp. 357-363, Jul 2019.
[19]白佩鑫,"輕鬆掌握GEE,立即成為遙測高手-多時序NDVI分析初體驗",取自:https://tech.swcb.gov.tw/EPaper/Home/EPaper?PaperID=9ba18a16-9961-462f-8f6e-e5ed46700173 (accessed 03/26, 2023)。
[20]NASA. "Normalized Difference Vegetation Index (NDVI)."取自:https://earthobservatory.nasa.gov/features/MeasuringVegetation/measuring_vegetation_2.php (accessed03/26, 2023).
[21]胡蝶, et al. "在林业碳汇量估算中遥感方法的应用分析." World Journal of Forestry 11 (2022).
[22]J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, "Internet of Things (IoT): A vision, architectural elements, and future directions," Future Generation Computer Systems, vol. 29, no. 7, pp. 1645-1660, 2013.
[23]CH.Tseng.,"關於物聯網的標準.",取自:https://chtseng.wordpress.com/2014/10/23/%E9%97%9C%E6%96%BC%E7%89%A9%E8%81%AF%E7%B6%B2%E7%9A%84%E6%A8%99%E6%BA%96/ (accessed 03/26, 2023)。
[24]B. B. Gupta and M. Quamara, "An overview of Internet of Things (IoT): Architectural aspects, challenges, and protocols," Concurrency and Computation: Practice and Experience, vol. 32, no. 21, p. e4946, 2020.
[25]M. Wu, T.-J. Lu, F.-Y. Ling, J. Sun, and H.-Y. Du, "Research on the architecture of Internet of Things," in 2010 3rd international conference on advanced computer theory and engineering (ICACTE), 2010, vol. 5: IEEE, pp. V5-484-V5-487.
[26]P. P. Ray, "A survey on Internet of Things architectures," Journal of King Saud University-Computer and Information Sciences, vol. 30, no. 3, pp. 291-319, 2018.
[27]Y. Jadeja and K. Modi, "Cloud computing - concepts, architecture and challenges," in 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET), 21-22 March 2012, pp. 877-880.
[29]N. Chowdhury, D. R. Mushfiq, and A. E. Chowdhury, "Computer Vision and Smoke Sensor Based Fire Detection System," in 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), 3-5 May 2019, pp. 1-5.
[30]K. Jayaram, K. Janani, R. Jeyaguru, R. Kumaresh, and N. Muralidharan, "Forest Fire Alerting System With GPS Co-ordinates Using IoT," in 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), 15-16 March 2019, pp. 488-491.
[31]S. Ishitha, S. Nagaraju, H. A. Mohan, M. Harshitha, G. R. Gowda, and N. J, "IoT based Anti-poaching and Fire Alarm System for Forest," in 2021 IEEE Mysore Sub Section International Conference (MysuruCon), 24-25 Oct. 2021, pp. 711-715.
[32]Y. Song, S. S. Yau, R. Yu, X. Zhang, and G. Xue, "An Approach to QoS-based Task Distribution in Edge Computing Networks for IoT Applications," in 2017 IEEE International Conference on Edge Computing (EDGE), 25-30 June 2017, pp. 32-39.
[33]M. Caprolu, R. D. Pietro, F. Lombardi, and S. Raponi, "Edge Computing Perspectives: Architectures, Technologies, and Open Security Issues," in 2019 IEEE International Conference on Edge Computing (EDGE), 8-13 July 2019, pp. 116-123,.
[34]W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE internet of things journal, vol. 3, no. 5, pp. 637-646, 2016.
[35]Mitra, S. Biswas, T. Adhikari, A. Ghosh, S. De, and R. Karmakar, "Emergence of Edge Computing: An Advancement over Cloud and Fog," in 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 1-3 July 2020, pp. 1-7.
[36]Chen, J. Jiang, Y. Zhou, N. Lv, X. Liang, and S. Wan, "An edge intelligence empowered flooding process prediction using Internet of things in smart city," Journal of Parallel and Distributed Computing, vol. 165, pp. 66-78, 2022.
[37]F. Righetti, C. Vallati, A. K. Tubak, N. Roy, B. Basnyat, and G. Anastasi, "Assessing the Feasibility of Exploiting Edge Computing for Real-Time Monitoring of Flash Floods," in 2022 IEEE International Conference on Smart Computing (SMARTCOMP), 2022: IEEE, pp. 281-286.
[38]F. J. Pierce and P. Nowak, "Aspects of precision agriculture," Advances in agronomy, vol. 67, pp. 1-85, 1999.
[39]M. N. Akhtar, A. J. Shaikh, A. Khan, H. Awais, E. A. Bakar, and A. R. Othman, "Smart sensing with edge computing in precision agriculture for soil assessment and heavy metal monitoring: A review," Agriculture, vol. 11, no. 6, p. 475, 2021.
[40]V. Joshi and A. V. Joshi, "Introduction to AI and ML," Machine learning and artificial intelligence, pp. 3-7, 2020.
[41]V. Gupta, V. K. Mishra, P. Singhal, and A. Kumar, "An Overview of Supervised Machine Learning Algorithm," in 2022 11th International Conference on System Modeling & Advancement in Research Trends (SMART), 16-17 Dec. 2022, pp. 87-92.
[42]H. U. Dike, Y. Zhou, K. K. Deveerasetty, and Q. Wu, "Unsupervised Learning Based On Artificial Neural Network: A Review," in 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), 25-27 Oct. 2018, pp. 322-327.
[43]X. Lu, Q. Li, B. Li, and J. Yan, "MimicDet: bridging the gap between one-stage and two-stage object detection," in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16, 2020: Springer, pp. 541-557.
[44]B. Liu, W. Zhao, and Q. Sun, "Study of object detection based on Faster R-CNN," in 2017 Chinese Automation Congress (CAC), 20-22 Oct. 2017, pp. 6233-6236.
[45]W. Liu et al., "Ssd: Single shot multibox detector," in Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14, 2016: Springer, pp. 21-37.
[46]李謦伊,"YOLOv4 訓練教學",取自:https://medium.com/ching-i/yolo-c49f70241aa7 (accessed 5/13, 2023)。
[47]周韋宏,"紅外線結合物件偵測應用於非接觸寵物 體溫量測之研究",碩士論文,國立臺北科技大學,2022。

電子全文 電子全文(網際網路公開日期:20280726)
第一頁 上一頁 下一頁 最後一頁 top