臺灣博碩士論文加值系統

蛋的相關分析在養雞場有非常多的研究，例如計算蛋的尺寸、分析雞蛋是否受精，但卻極少在養鵝場中實驗。鵝的下蛋量可以代表鵝的健康狀態，也可以用來選擇適合養殖的鵝隻。若下蛋量異常，須特別觀察，以確認是否感染病毒。因此，本論文開發養鵝場的蛋產量分析系統。在這個系統中，每隻鵝都會佩戴一個專屬的RFID腳環，當它進入鵝籠時，會讀取RFID數據並記錄下這隻鵝停留在鵝籠的時間。在此系統中，使用攝影機監控滾動中的鵝蛋，結合運動方向與CNN(YOLOv3)的辨識方法，在充滿各式雜訊(例如: 鵝毛、蜘蛛網、老鼠…)的養鵝場環境中分析鵝的蛋產量，經實驗顯示本系統的準確率達96%。

There are a lot of related analysis in the chicken farm. For example, calculate egg size and determine fertilized egg, but rarely experimenting in goose farms. The amount of eggs laid by a goose can represent the health status of the goose. It can also be used to select goose suitable for breeding. If the number of eggs is abnormal, special observation is required to confirm whether the virus is infected. This paper develops an egg production analysis system for goose farms. In this system, each goose worn a unique RFID foot ring, when it enter goose cage, record RFID information and record the time of this goose stay in. Use a camera to monitor the eggs in the scroll. We combined movement direction and CNN(YOLOv3). Analysis of goose egg production in a goose farm environment filled with various noises (e.g. spider webs, goose feathers, mice...). The experiment shows that the accuracy of the system reaches 96%.

摘要 i
Abstract ii
誌謝 iii
目 錄 iv
圖 目 錄 vi
表 目 錄 viii
符號說明 ix
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 論文架構 4
第二章 相關文獻探討 5
2.1 雞蛋的尺寸分析 5
2.2 利用孵蛋的過程分析雞蛋的狀態 6
2.3 基於RFID技術分析蛋產量 7
第三章 鵝的下蛋量分析系統 10
3.1 養鵝場的模擬環境介紹 10
3.2 鵝蛋追蹤與分析 11
3.3 待克服問題 14
3.4 系統方塊圖 18
3.5 鵝蛋辨識流程 18
3.6 FCM分群法 21
3.7 連通標記法 26
3.8 應用菱形框描述鵝蛋形狀 28
3.9 應用菱形框的實驗結果 32
3.10 蜘蛛網問題 34
3.11 應用類神經網路辨識鵝蛋及其實驗結果 35
3.11.1 倒傳遞類神經網路 36
3.11.2 卷積神經網路(Convolutional Neural Network, CNN) 39
3.11.3 YOLOv3 概述 44
3.11.3.1 YOLOv3 COCO訓練集 44
第四章 應用卷積神經網路與運動方向分析鵝產蛋量 46
4.1 養鵝場實況概述 46
4.2 YOLOv3 實驗結果 48
4.3 運動方向是鵝蛋與常見雜訊的最大差異 50
4.4 運動方向 51
4.5 植基於運動方向的實驗結果 54
第五章 結論與未來展望 58
參考文獻 60
附錄 63

[1] Fernando Alfredo Auat Cheein and Ricardo Carelli, "Agricultural Robotics: Unmanned Robotic Service Units in Agricultural Tasks," IEEE Industrial Electronics Magazine, pp. 48-58, Sep 2013.
[2] I.S. Akila , A. Sivakumar and S. Swaminathan, "Automation in plant growth monitoring using high-precision image classification and virtual height measurement techniques," 2017 International Conference on Innovations in Information, Embedded and Communication Systems, 17-18 March 2017.
[3] R. Waranusast, P. Intayod and D. Makhod, “Egg size classification on Android mobile devices using image processing and machine learning,” Fifth ICT International Student Project Conference (ICT-ISPC), Thailand, 2016.
[4] L. K. S. Tolentino, E. J. G. Enrico, R. L. M. Listanco, M. A. M. Ramirez, T. L. U. Renon and M. R. B. Samson, “Development of Fertile Egg Detection and Incubation System Using Image Processing and Automatic Candling,” TENCON 2018 - 2018 IEEE Region 10 Conference, Korea, 2018.
[5] 張伸彰, 林旻蓉 與 賈玉祥, “養鵝工廠化之精準管理,” 2011. [線上]. Available: https://coa.imita.org/ws.php?id=23884.
[6] 中華民國養鵝協會, “產業介紹,” [線上]. Available: http://www.goosetw.com/IndustryIntro.aspx.
[7] 姚中慧, “禽流感防疫措施簡介,” 12 2005. [線上]. Available: https://www.coa.gov.tw/ws.php?id=10422&print=Y.
[8] 柯皓翔 與 周崇熙, “【農百科】禽疫當前，何種飼養較抗病？先搞懂這些再說！,” 7 3 2017. [線上]. Available: https://www.agriharvest.tw/theme_data.php?theme=article&sub_theme=article&id=325&fb_comment_id=1596989803674930_1597099740330603.
[9] P. Suresh, K. Shoba and J. J. Rajeswar, “Incidence of Egg Drop Syndrome –1976 in Namakkal district, Tamil Nadu,” Vet World, Vol.6, 6, pp. 350-353, 2013.
[10] 林德田 與 許天來, “產蛋下降症之簡介與其防治,” 中國畜牧雜誌, 第 30冊, 編號 11.
[11] 行政院農業委員會, “國際禽流感疫情現況,” [線上]. Available: https://www.coa.gov.tw/files/news/7197/A01_1.pdf.
[12] 張伸彰, 林旻蓉, 賈玉祥 與 范揚廣, “智慧型水禽產蛋辨識監控系統”. 台灣 專利: I482590, 1 5 2015.
[13] W. Jiang, H. Xuelong and S. Quan, “Research on Yangzhou Goose breeding system based on RFID,” IEEE International Conference on Electronic Measurement & Instruments (ICEMI), Qingdao, China, 2015.
[14] R. O. Duda and P. E. Hart, “Use of the Hough transformation to detect lines and curves in pictures,” Communications of the ACM, Vol.15, 1, pp. 11-15 , 1972 .
[15] Teh-ChuanChen and Kuo-LiangChung, "An Efficient Randomized Algorithm for Detecting Circles," Computer Vision and Image Understanding, pp. 172-191, August 2001.
[16] J. Bezdec, Pattern Recognition with Fuzzy Objective Function Algorithms, New York: Plenum Press, 1981.
[17] A. Jain and R. C. Dubes, Algorithms for Clustering Data, New Jersey: Prentice hall, 1988.
[18] L.A.Zadeh, “Fuzzy sets,” Information and Control,Vol.8,3, pp. 338-353, 1965.
[19] A. AbuBaker, R. Qahwaji, S. Ipson and M. Saleh, “One Scan Connected Component Labeling Technique, IEEE International Conference on Signal Processing and Communications, Dubai, United Arab Emirates, 2007.
[20] 維基百科, “神經元,” [線上]. Available: https://zh.wikipedia.org/wiki/%E7%A5%9E%E7%B6%93%E5%85%83.
[21] D. E. Rumelhart, G. E. Hinton and R. J. Williams, “Learning representations by back-propagating errors,” Nature, Vol.323, pp. 533-536, 1986.
[22] G. Medina, “drawing back propagation neural network,” 25 2 2014. [線上]. Available: https://tex.stackexchange.com/questions/162326/drawing-back-propagation-neural-network?answertab=active#tab-top.
[23] A. Krizhevsky, I. Sutskever and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” International Conference on Neural Information Processing Systems, 2012.
[24] MathWorks, “Learn About Convolutional Neural Networks,” [線上]. Available: https://www.mathworks.com/help/deeplearning/ug/introduction-to-convolutional-neural-networks.html.
[25] Joseph Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 於 omputer Vision and Pattern Recognition , 2018.
[26] J. Redmon, “Darknet: Open Source Neural Networks in C,” http://pjreddie.com/darknet/, 2013-2016.
[27] G. A. Y. Kencana, I. N. Suartha, A. Nurhandayani and Syamsidar, “The Characteristic of Egg Drop Syndrome,” Journal of Veterinary Medicine and Animal Science,Vol.1, 1, pp. 15-19, 2 2017.