跳到主要內容

臺灣博碩士論文加值系統

(44.201.97.0) 您好!臺灣時間:2024/04/19 14:38
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:蔡靜偉
研究生(外文):Ching-Wei Tsai
論文名稱:監測蜂巢內蜜蜂運動行為之影像分析方法與系統
論文名稱(外文):Image Analysis Method and System for Honey Bee Movement Behavior Monitoring in Beehive
指導教授:林達德林達德引用關係
指導教授(外文):Ta-Te Lin
口試委員:江昭皚楊恩誠
口試委員(外文):Joe-Air JiangEn-Cheng Yang
口試日期:2016-07-14
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:生物產業機電工程學研究所
學門:工程學門
學類:機械工程學類
論文種類:學術論文
論文出版年:2016
畢業學年度:104
語文別:中文
論文頁數:123
中文關鍵詞:運動行為分析蜜蜂標記字元辨識機器學習影像處理
外文關鍵詞:Movement behavior analysisHoney bee labelingCharacter recognitionMachine LearningImage Processing
相關次數:
  • 被引用被引用:2
  • 點閱點閱:397
  • 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:0
蜜蜂為開花植物的重要授粉者,糧食與經濟作物的生產皆依賴蜜蜂授粉。在2006~2007年期間北美洲發生蜜蜂族群崩潰症候群,並導致嚴重的農業與經濟損失,因此該現象的原因亟需加以探討。基於此,本研究以前人的蜜蜂巢內行為影像系統為基礎,進行改良並重新開發系統,提高巢內影像系統性能以提供更大的觀察範圍與更加準確的蜜蜂巢內運動軌跡資訊,以提供一套科學工具探究蜜蜂族群崩潰症候群的原因。為偵測個別蜜蜂的軌跡,首先將欲觀察的蜜蜂貼上防水文字標籤,並使用霍爾圓轉換演算法 (Hough circle transform)偵測個別蜜蜂身上之標籤位置,然後將標籤影像進行方向梯度直方圖特徵提取演算法 (Histogram of oriented gradient, HOG)提取影像邊緣特徵,並使用主成分分析法降維與去除冗餘資訊,最後使用支持向量機演算法 (Support Vector Machine, SVM)作為字元辨識方法。獲得標籤位置與編號之後,使用軌跡追蹤演算法串接蜜蜂位置產生行為軌跡資訊。所擷取的個別蜜蜂軌跡進一步藉由切割片段軌跡並轉換成為個別步態、軌跡運動指標以及蜜蜂互動頻率,並搭配蜜蜂巢外覓食行為影像監測系統所記錄的蜜蜂進出巢資訊,分析蜜蜂在不同分工與日齡的行為差異。本研究設計三項實驗以驗證影像系統效能及蜜蜂行為分析方法,第一項實驗為蜜蜂使用不同標記方法後對於活動力的影響,由實驗得知負壓吸取法在標記後能夠維持較高的活動力。第二項實驗為箱內蜂與外勤蜂的運動行為比較,並由實驗結果得知外勤蜂於巢內的平均移動速度較快且具有週期性,不同分工的蜜蜂會因天氣狀況而動態調整於巢內的行為。第三項實驗則是不同日齡的蜜蜂行為模式比較,並由實驗得知隨日齡不同而導致軌跡步態比例與移動速度差異。所建立的蜂巢內影像監測系統與量化分析方法未來將可應用於各種蜜蜂行為之實驗與分析,為蜜蜂行為相關研究領域提供一個有用的研究工具。

Honey bees (Apis mellifera) are important pollinators in nature. In 2006~2007, North America occurred serious CCD (colony collapse disorder) problem. Abnormal and inadequate pollination cause enormous economic and agricultural loss, the reason of CCD problem is necessary to study. Base on the problem, we redevelop an image monitoring system in the beehive, it can provide larger FOV (field of view) and more accurate trajectory information in the beehive than former design. Provide a scientific tool to study the reason of CCD problem. In order to capture individual honey bee information in beehive, we label a water-proof text tag on each bee. After labeling, Hough circle transform technique is applied to detect tag position and to segment out the tag image. In order to extract the tag character feature, tag images are transformed into feature vectors by histogram of oriented gradient (HOG) algorithm. Extracting feature by HOG leads to feature dimension increase which slows down the computational speed. Hence, principle component of analysis (PCA) is applied to reduce the feature dimensionality first. Then, support vector machine (SVM) algorithm is applied to train and predict the tag text. After retrieving the position and text of tag, trajectory tracking algorithm is applied to generate trajectories. We establish a trajectory analysis method and activity indices are built up for evaluating honey bee’s activity in the beehive. Analyze the behavior differences of honey bee with different division of labor or different age.
We design 3 experiments to verify our image system and analysis method, first part of experiment is honey bee activity comparison experiment by different labeling method. According to the experiment result, it is clear that the labeling by vacuum fixation method can keep honey bee higher activity ability than freezing method. The second part of experiment is the foraging bee and in-hive bee behavior comparison experiment. We can compare that different task of honey bee have different moving speed and activity cycle from the experiment result. The last part of experiment is different age of honey bee behavior comparison experiment, we can find out the motion pattern ratio is different from the age of honey bee and the activity indices are also different with different age of honey bee.


誌謝 i
摘要 ii
Abstract iii
目錄 v
圖目錄 x
表目錄 xiv
1 第一章 緒論 1
1.1 前言 1
1.2 研究目的 3
2 第二章 文獻探討 5
2.1 蜜蜂行為監測 5
2.1.1 蜂巢進出監測 5
2.1.1.1 機械裝置輔助 5
2.1.1.2 電子裝置 6
2.1.1.3 影像裝置 7
2.1.2 蜂巢內部監測 8
2.1.2.1 蜜蜂無標記之影像監測系統 11
2.1.2.2 蜜蜂有標記之影像監測系統 11
2.2 廣角扭曲修正 14
2.3 影像接合 15
2.4 文字辨識 15
2.4.1 方向梯度直方圖 16
2.4.2 主成分分析 17
2.4.3 支持向量機 18
2.4.4 軌跡追蹤 18
2.5 蜜蜂行為軌跡分類與分析 19
2.6 蜜蜂年齡分工多樣性 20
2.7 人工蜜蜂孵化方法 21
3 第三章 研究設備與方法 23
3.1 蜜蜂標記方法 23
3.1.1 文字標籤設計 23
3.1.2 標記方法 24
3.2 蜂巢內影像監測系統硬體架構 26
3.2.1 改造小型蜂箱 27
3.2.2 補光燈板 29
3.2.3 高解析度數位攝影機 29
3.2.4 防水觀測箱 31
3.3 蜂巢內影像監測系統軟體架構 32
3.3.1 廣角扭曲修正方法 32
3.3.2 影像接合方法 33
3.3.3 標籤位置偵測 35
3.3.4 標籤影像前處理 38
3.3.5 標籤文字辨識 42
3.3.6 軌跡追蹤 44
3.4 人工蜜蜂孵化系統 46
3.4.1 硬體設計與架構 46
3.4.2 溫溼度控制 48
3.5 蜜蜂巢內外環境資訊感測系統 48
3.6 蜜蜂巢外覓食行為影像監測系統 49
3.7 蜜蜂行為軌跡分析 50
3.7.1 固定長度軌跡切割 50
3.7.2 固定長度副軌跡步態轉換 52
3.7.3 依據軌跡行為切割軌跡 54
3.7.4 個別蜜蜂行為模式比例與呈現方法 57
3.8 蜜蜂運動指標分析 57
3.9 蜜蜂互動頻率分析 58
3.10 驗證實驗規劃 59
3.10.1 不同標記方法影響蜜蜂活動力實驗 59
3.10.2 箱內蜂與外勤蜂行為比較實驗 60
3.10.3 不同日齡幼蜂行為比較 61
4 第四章 結果與討論 62
4.1 蜜蜂飼養狀況 62
4.2 蜂巢內影像監測系統性能分析 63
4.2.1 硬體架構成果與討論 63
4.2.2 軟體架構成果與討論 65
4.2.2.1 廣角扭曲修正與影像接合 67
4.2.2.2 標籤偵測與辨識 69
4.2.2.3 軌跡追蹤 71
4.2.3 軌跡分析方法討論 71
4.2.3.1 固定長度切割與步態轉換方法討論 72
4.2.3.2 依據行為切割軌跡與分析方法討論 73
4.2.4 系統性能分析 74
4.3 蜜蜂標記方法分析 75
4.4 人工孵化蜜蜂系統 76
4.4.1 環境控制 76
4.5 實驗結果分析 78
4.5.1 不同標記方法影響蜜蜂活動力實驗 78
4.5.2 箱內蜂與外勤蜂行為比較 81
4.5.2.1 實驗一 81
4.5.2.2 實驗二 88
4.5.3 不同日齡成蜂行為比較 94
5 第五章 結論與建議 104
5.1 結論 104
5.2 建議 105
參考文獻 107
附錄 113
附錄一、氣象資料 (2015/12/29~2016/01/05) 113
附錄二、2D PCA行為模式分布 (2015/12/29~2016/01/05) 114
附錄三、氣象資料 (2016/03/03~2016/03/08) 118
附錄四、2D PCA行為模式分布 (2015/12/29~2016/01/05) 119
附錄五、氣象資料 (2016/06/08~2016/06/29) 122


安 奎、 何 鎧光與陳 裕文。2004。養蜂學。第二版。台北:華香園。
周 美慧。2011。新劑型草酸防治蜂蟹蟎的效果與蜂產品殘留量檢測。碩士論文。宜蘭縣:國立宜蘭大學動物科技學系碩士班。
張 惠君。2010。益達胺的亞致死劑量對蜜蜂學習行為之影響。台北:國立臺灣大學昆蟲學研究所。
陳 大宇。2014。應用影像系統於蜂箱內蜜蜂運動行為之追蹤。碩士論文。國立臺灣大學生物產業機電工程學研究所,台北、台灣。
陳 易成。2012。新劑型百里酚防治蜂蟹蟎的效果。碩士論文。宜蘭縣:國立宜蘭大學動物科技學系碩士班。
陳 秋。2010。蜜蜂覓食行為監測與分析影像系統之研究。碩士論文。台北:國立臺灣大學生物產業機電工程學研究所。
陳 裕文、 陳 盈伃與陳 信鈞。2002。三種殺蟎劑對蜂蟹蟎的防治效果。宜蘭技術學報。9:53-60。
蔣 壽山。2008。應用頻譜影像分析蜜蜂色覺。碩士論文。台北市:國立臺灣大學生物產業機電工程學研究所。
Ashiralieva, A. and Genersch, E. 2006. Reclassification, genotypes and virulence of Paenibacillus larvae, the etiological agent of American foulbrood in honeybees-a review. Apidologie. 37:411-420
Bailey, L. 1983. Melissococcus pluton, the cause of European foulbrood of honey bees (Apis spp.). Journal of applied bacteriology. 55:65-69
Boser, B. E., Guyon, I. M. and Vapnik, V. N. 1992. A training algorithm for optimal margin classifiers. ACM. 144-152
Brown, M. and Lowe, D. G. 2007. Automatic panoramic image stitching using invariant features. International journal of computer vision. 74:59-73
Burges, C. C. 1998. A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery. 2:121-167
Campbell, J., Mummert, L. and Sukthankar, R. 2008. Video monitoring of honey bee colonies at the hive entrance. Visual observation & analysis of animal & insect behavior (ICPR).
Campbell, J. M., Dahn, D. C. and Ryan, D. A. 2005. Capacitance-based sensor for monitoring bees passing through a tunnel. Measurement Science and Technology. 16:2503
Canny, J. 1986. A Computational Approach to Edge Detection. Pattern Analysis and Machine Intelligence, IEEE Transactions on. PAMI-8:679-698
Chahl, J. S., Srinivasan, M. V. and Zhang, S.-W. 2004. Landing strategies in honeybees and applications to uninhabited airborne vehicles. The International Journal of Robotics Research. 23:101-110
Chang, H. C. 2010. Abnormality of honeybee learning behavior caused by sub-lethal dosage of imidacloprid. Master. Taipei, Taiwan: National Taiwan University, Department of Entomology.
Chiron, G., Gomez-Krämer, P. and Ménard, M. 2013. Detecting and tracking honeybees in 3D at the beehive entrance using stereo vision. EURASIP Journal on Image and Video Processing. 2013:59
Dalal, N. and Triggs, B. 2005. Histograms of oriented gradients for human detection. IEEE. 1:886-893
Decourtye, A., Devillers, J., Aupinel, P., Brun, F., Bagnis, C., Fourrier, J. and Gauthier, M. 2011. Honeybee tracking with microchips: a new methodology to measure the effects of pesticides. Ecotoxicology. 20:429-437
Deepu, V., Madhvanath, S. and Ramakrishnan, A. G. 2004. Principal component analysis for online handwritten character recognition. 2:327-330 Vol.2
Duda, R. O. and Hart, P. E. 1972. Use of the Hough transformation to detect lines and curves in pictures. Communications of the ACM. 15:11-15
Dunteman, G. H. 1989. Principal components analysis. Sage
Fabergé, A. 1943. Apparatus for recording the number of bees leaving and entering a hive. Journal of Scientific Instruments. 20:28
Feldman, A. and Balch, T. 2004. Representing honey bee behavior for recognition using human trainable models. Adaptive behavior. 12:241-250
Gary, N. E. 1967. A method for evaluating honey bee flight activity at the hive entrance. Journal of Economic Entomology. 60:102-105
Gary, N. E., Welch, N., Hart, W., Lear, B., Ulrich, A., Allen, W. W., Qualset, C., Prato, J., Rupert, J. and Vogt, H. 1971. A new tagging and recapture method for evaluating honeybee pollination activity. California Agriculture. 25:4-6
Gatien, P. and Currie, R. 2003. Timing of acaracide treatments for control of low-level populations of Varroa destructor (Acari: Varroidae) and implications for colony performance of honey bees. The Canadian Entomologist. 135:749-763
Gottumukkal, R. and Asari, V. K. 2004. An improved face recognition technique based on modular PCA approach. Pattern Recognition Letters. 25:429-436
Hendriks, C., Yu, Z., Lecocq, A., Bakker, T., Locke, B. and Terenius, O. 2012. Identifying all individuals in a honeybee hive-progress towards mapping all social interactions. Citeseer.
Henry, M., Beguin, M., Requier, F., Rollin, O., Odoux, J.-F., Aupinel, P., Aptel, J., Tchamitchian, S. and Decourtye, A. 2012. A common pesticide decreases foraging success and survival in honey bees. Science. 336:348-350
Jinfeng, B., Zhineng, C., Bailan, F. and Bo, X. 2014. Image character recognition using deep convolutional neural network learned from different languages. 2560-2564
Kastberger, G. and Stachl, R. 2003. Infrared imaging technology and biological applications. Behavior Research Methods, Instruments, & Computers. 35:429-439
Kato, N., Suzuki, M., Omachi, S., Aso, H. and Nemoto, Y. 1999. A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 21:258-262
Khan, Z., Balch, T. and Dellaert, F. 2004. A rao-blackwellized particle filter for eigentracking. IEEE. 2:II-980-II-986 Vol. 2
Kimura, T., Ohashi, M., Okada, R. and Ikeno, H. 2011. A new approach for the simultaneous tracking of multiple honeybees for analysis of hive behavior. Apidologie. 42:607-617
Knauer, U. and Meffert, B. 2009. Evaluation based combining of classifiers for monitoring honeybees. IEEE. 1-6
Landgraf, T. and Rojas, R. 2007. Tracking honey bee dances from sparse optical flow fields. Technical Report. 37:1-37
Landgraf, T., Rojas, R., Nguyen, H., Kriegel, F. and Stettin, K. 2011. Analysis of the waggle dance motion of honeybees for the design of a biomimetic honeybee robot. PloS one. 6:
Lee, J.-G., Han, J., Li, X. and Gonzalez, H. 2008. TraClass: trajectory classification using hierarchical region-based and trajectory-based clustering. Proceedings of the VLDB Endowment. 1:1081-1094
Lee, J.-G., Han, J. and Whang, K.-Y. 2007. Trajectory clustering: a partition-and-group framework. ACM. 593-604
Maitra, P., Schneider, S. and Shin, M. C. 2009. Robust bee tracking with adaptive appearance template and geometry-constrained resampling. IEEE. 1-6
Malone, L. A. and Pham-Delègue, M.-H. 2001. Effects of transgene products on honey bees (Apis mellifera) and bumblebees (Bombus sp.). Apidologie. 32:287-304
Newell, A. J. and Griffin, L. D. 2011. Multiscale histogram of oriented gradient descriptors for robust character recognition. IEEE. 1085-1089
Oldroyd, B. P. 2007. What’s killing American honey bees. PLoS Biol. 5:e168
Owens, J. and Hunter, A. 2000. Application of the self-organising map to trajectory classification. IEEE. 77-83
Pearson, K. 1901. LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science. 2:559-572
Rajavelu, A., Musavi, M. T. and Shirvaikar, M. V. 1989. A neural network approach to character recognition. Neural Networks. 2:387-393
Schneider, C. W., Tautz, J., Grünewald, B. and Fuchs, S. 2012. RFID tracking of sublethal effects of two neonicotinoid insecticides on the foraging behavior of Apis mellifera. PloS one. 7:e30023
Seeley, T. D. 1983. Division of labor between scouts and recruits in honeybee foraging. Behavioral Ecology and Sociobiology. 12:253-259
Seeley, T. D. 1992. The tremble dance of the honey bee: message and meanings. Behavioral Ecology and Sociobiology. 31:375-383
Seeley, T. D. 1982. Adaptive significance of the age polyethism schedule in honeybee colonies. Behavioral Ecology and Sociobiology. 11:287-293
Sharma, L. K., Vyas, O. P., Schieder, S. and Akasapu, A. K. 2010. Nearest neighbour classification for trajectory data. Springer. 180-185
Shaw, J. A., Nugent, P. W., Johnson, J., Bromenshenk, J. J., Henderson, C. B. and Debnam, S. 2011. Long-wave infrared imaging for non-invasive beehive population assessment. Optics express. 19:399-408
Streit, S., Bock, F., Pirk, C. W. and Tautz, J. 2003. Automatic life-long monitoring of individual insect behaviour now possible. Zoology. 106:169-171
Struye, M., Mortier, H., Arnold, G., Miniggio, C. and Borneck, R. 1994. Microprocessor-controlled monitoring of honeybee flight activity at the hive entrance*. Apidologie. 25:384-395
Sun, Z., Bebis, G. and Miller, R. 2002. On-road vehicle detection using Gabor filters and support vector machines. IEEE. 2:1019-1022
Suykens, J. A. and Vandewalle, J. 1999. Least squares support vector machine classifiers. Neural processing letters. 9:293-300
Theriault, D., Wu, Z., Hristov, N., Swartz, S., Breuer, K., Kunz, T. and Betke, M. 2010. Reconstruction and analysis of 3D trajectories of Brazilian free-tailed bats in flight. CS Department, Boston University, Tech. Rep.
Toews, M. and Arbel, T. 2009. Detection, localization, and sex classification of faces from arbitrary viewpoints and under occlusion. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 31:1567-1581
Trier, Ø. D., Jain, A. K. and Taxt, T. 1996. Feature extraction methods for character recognition-a survey. Pattern recognition. 29:641-662
Vanengelsdorp, D., Underwood, R., Caron, D. and Hayes Jr, J. 2007. estimate of managed colony losses in the winter of 2006-2007: A report commissioned by the Apiary Inspectors of America. American Bee Journal.
Veeraraghavan, A., Chellappa, R. and Srinivasan, M. 2008. Shape-and-behavior encoded tracking of bee dances. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 30:463-476
Wang, X. W., Ding, X. Q. and Liu, C. S. 2002. Gabor filters based feature extraction for robust Chinese character recognition. Acta Electronica Sinica. 30:1317-1322
Weng, J., Cohen, P. and Herniou, M. 1992. Camera calibration with distortion models and accuracy evaluation. IEEE Transactions on Pattern Analysis & Machine Intelligence. 965-980
Wu, C. Y. 2013. An Imaging System for Monitoring Honeybee In-and-out Activity Using Laser Labeling Method. Master. Taipei, Taiwan: National Taiwan University, Bio-industrial Mechatronic Engineering.
Yilmaz, A., Javed, O. and Shah, M. 2006. Object tracking: A survey. Acm computing surveys (CSUR). 38:13
Yu, S. J. 2012. A Study on Master-Slave Imaging System and Application for Ecological Monitoring. Master. Taipei, Taiwan: National Taiwan University, Bio-industrial Mechatronic Engineering.
Zhang, Z. 2000. A flexible new technique for camera calibration. Pattern Analysis and Machine Intelligence, IEEE Transactions on. 22:1330-1334

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊