(3.230.143.40) 您好!臺灣時間:2021/04/21 08:03
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:陳伯群
研究生(外文):CHEN, BO-CYUN
論文名稱:運用深度學習及電腦視覺技術於菜蟲動態分析研究
論文名稱(外文):The Dynamic Analysis of a Cabbage Caterpillar with Deep Learning and Computer Vision Technology
指導教授:林宸生林宸生引用關係
指導教授(外文):LIN,CHERN-SHENG
口試委員:賴雲龍鄭經華
口試委員(外文):LAY,YUN-LONGCHENG,CHING-HWA
口試日期:2018-06-05
學位類別:碩士
校院名稱:逢甲大學
系所名稱:生醫資訊暨生醫工程碩士學位學程
學門:工程學門
學類:生醫工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:中文
論文頁數:52
中文關鍵詞:菜蟲影像處理深度學習動態追蹤
外文關鍵詞:Cabbage caterpillarImage preprocessingDeep learningDynamic tracking
相關次數:
  • 被引用被引用:0
  • 點閱點閱:157
  • 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
本研究利用X-Y Table雙軸精密移動平台結合攝影機進行菜蟲之動態分析,透過影像預處理、影像分割、型態影像處理,搭配程式中深度學習目標特徵演算法(HOG、LBP、HAAR),判斷目標物是否為菜蟲,經由影像的重心提取進行動態追蹤的相關作業,計算菜蟲食用面積及移動軌跡,在系統 24小時的不間斷攝影,可依其移動之位置進行自動追蹤,進而統計其各項數據,例如移動距離、食用面積、體積變化、微量農藥殘留之影響等,以利於之後研究觀察之數據比較,可提供更深入的探討,例如菜蟲生長週期紀錄、行為能力路徑分析等,進而增加菜蟲動態分析的準確度。
In this study, the dynamic analysis of cabbage caterpillar was performed using a XY Table dual-axis precision mobile platform combined with a camera. Through image preprocessing, image segmentation, and morphological image processing, the deep learning target feature algorithm (HOG, LBP, and HAAR) was used in the program. The system can judge if the target object is a vegetable caterpillar, then extract the relevant operations for dynamic tracking through the center of gravity of the image. It can also calculate the edible area and movement trajectory of the vegetable caterpillar. In the system the follow-up operation for 24 hours, according to the location of the movement, can be performed automatically. The data, such as movement distance, edible area, change in caterpillar volume, impact of trace amounts of pesticide residues, etc. can provide more in-depth discussion on the comparison of data for subsequent studies and observations. This study can also provide further analysis to enhance the dynamic analysis accuracy of the cabbage caterpillar.
致謝 i
中文摘要 ii
Abstract iii
目錄 ⅳ
圖目錄 vi
表目錄 viii
第一章、 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.2.1 CCD鏡頭取像 2
1.2.2 圖像特徵定位分析 2
1.2.3 動態追蹤目標物分析 2
1.3文獻回顧 3
1.3.1農藥暴露和殘留的健康效應 3
1.3.2機器視覺特徵檢測應用於農業 5
1.3.3智能視頻監控目標追蹤 7
第二章、 研究理論與方法 9
2.1自動化農業 9
2.1.1影像感測器(CCD與CMOS) 9
2.1.2機器視覺取像裝置 10
2.2深度學習相關訓練 11
2.2.1利用AdaBoost算法進行特徵選擇 11
2.2.2利用Matlab Cascade對象檢測器 13
2.3目標檢測影像特徵 14
2.3.1 HOG特徵 15
2.3.2 LBP特徵 16
2.3.3 Haar-like特徵 17
2.4 影像辨識相關處理 18
2.4.1影像預處理 18
2.4.2影像分割處理 19
2.4.3外形影像處理 20
2.4.4影像重心提取 21
2.5圖像差分法用於目標動態跟蹤 21
2.5.1幀間差分法 22
2.5.2背景差分法 22
2.6有機農藥-蘇力菌的應用 23
第三章、系統架構與流程 24
3.1菜蟲動態分析之自動光學檢測系統 24
3.1.1軟硬體系統設備 24
3.1.2硬體設備 26
3.2系統架構圖 28
3.3系統流程圖 29
第四章、 實驗數據與研究成果 31
4.1深度學習辨識 31
4.2程式介面建立與操作 33
4.3菜蟲食用菜葉畫面與分析 33
4.3實驗結果 37
第五章、 結論與未來展望 39
5.1結論 39
5.2未來展望 39
參考文獻 40

參考文獻
[1]Michael C.R. Alavanja, JaneA.Hoppin, Freya Kamel , "Health Effects of Chronic Pesticide Exposure: Cancer and Neurotoxicity", Annual Review of Public Health, 25, 2004,155-197.
[2]G. V. Ranga Rao, B. Ratna Kumari, K. L. Sahrawat, S. P. Wani, "Awareness on Pesticide Residues in Food Crops: A Challenge", Economic and Ecological Significance of Arthropods in Diversified Ecosystems, 2016, 411-422.
[3]衛生福利部食品藥物管理署(2017)。”市售不合格農產品之檢出情形及抽樣地點”2016年,取自https://www.fda.gov.tw/TC/index.aspx。
[4]Al-Hiary H, S. Bani-Ahmad, M. Reyalat, M. Braik and Z. Al Rahamneh, "Fast and accurate detection and classification of plant disease", International Journal of computer Application, ISSN 0975- 8887, 17, 2011,No1, 31-38.
[5]AakankshaRastogi, Ritika Arora, Shanu Sharma,"Leaf Disease Detection and Grading using Computer Vision Technology &Fuzzy Logic", 2015 2nd International Conference on Signal Processing and Integrated Networks (SPIN), 500-505.
[6]Faithpraise Fina1, Philip Birch, Rupert Young, J. Obu, Bassey Faithpraise, Chris Chatwin, "Automatic plant pest detection and recognition using k-means clustering algorithm and correspondence filters" International Journal of Advanced Biotechnology and Research, ISSN 0976-2612, 4, 2013, 189-199.
[7]張承偉,郝緒彤,郭一蓉,”基於幀間差分法的幀間差分法的動體特徵速度聚類分析” ,計算機應用研究,第33卷,2016年,3151-3155。
[8]文韜,洪添勝,李震,羅文輝,”基於機器視覺的橘小實蠅運動軌跡跟踪與數量檢測”,農業工程學報,第27卷,2011年,137-141。
[9]胡錦標,林宸生,謝宏榮等,”精密光電技術”,高立書局,1990年。
[10]洪昌佑, ”矽穿孔晶片黏晶機之高精度光學校準補償控制”,逢甲大學資訊電機工程學系碩士論文,2009。
[11]Yoav Freund, Robert Schapire, "A desicion-theoretic 60 generalization of on-line learning and an application to boosting " Lecture Notes in Computer Science, 904, 1995, 23-37.
[12]詹勳安,”以修正Adaboosting演算法的人臉偵測及醫學影像分類” ,義守大學資訊工程學系碩士論文,2014。
[13]Elena Alionte, Corneliu Lazar, "A Practical Implementation of Face Detection by Using Matlab Cascade Object Detector", 2015 19th International Conference on System Theory, Control and Computing (ICSTCC),785-790.
[14]E. H. W. Meijering, K. J. Zuiderveld, M. A. Viergever, "Image reconstruction by convolution with symmetrical piecewise nth-order polynomial kernels", IEEE Transactions on Image Processing , 8 , 1999, 192-201.
[15]Guolong Gan, Jian Cheng, "Pedestrian Detection Based on HOG-LBP Feature ", 2011 Seventh International Conference on Computational Intelligence and Security, 1184-1187.
[16]Xiaoyu Wang, Tony X. Han, Shuicheng Yan, "An HOG-LBP human detector with partial occlusion handling", 2009 IEEE 12th International Conference on Computer Vision, 32-39.
[17]T.Mita, T.Kaneko, O.Hori, "Joint Haar-like features for face detection", Tenth IEEE International Conference on Computer Vision (ICCV) ,1, 01-08.
[18]N.Dalal, B.Triggs, "Histograms of Oriented Gradients for Human Detection", IEEE Computer Society Conference on Computer Vision and Pattern Recognition ,1, 2005, 886-893.
[19] Carl Vondrick, Aditya Khosla, Tomasz Malisiewicz, Antonio Torralba, "HOGgles: Visualizing Object Detection Features", 2013 IEEE International Conference on Computer Vision (ICCV) ,2013, 01-08.
[20]T. Ojala, M .Pietikäinen, T .Mäenpää,"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns",IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 2002, 971 - 987.
[21]Kah-Kay Sung, Tomaso Poggio,"Example-Based Learning for View-Based Human Face Detection",IEEE Transactions on Pattern Analysis and Machine Intelligence ,20, 1998, 39-51.
[22]Paul Viola , Michael Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features" Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 512-518.
[23]N. Otsu, "A Threshold Selection Method from Gray-Level Histograms", Image Analysis and Processing,9 , 62-66.
[24]連國珍,”數位影像處理”,儒林圖書公司,1992 年 9月。
[25]陳彥良,”即時立體視覺物體追蹤系統”,中原大學機械工程學系碩士論文,2003。
[26]劉衍琦,詹福宇,蔣獻文,周華英”MATLAB計算機視覺與深度學習實戰”,電子工業出版社,2017年06月。
[27]曾經洲,”本土蘇力菌研發及應用”行政院農業委員會農業藥物毒物試驗所,2009年01月。

電子全文 電子全文(網際網路公開日期:20230626)
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