請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84569完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 郭彥甫(Yan-Fu Kuo) | |
| dc.contributor.author | Yu-Jung Tsai | en |
| dc.contributor.author | 蔡侑容 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:15:59Z | - |
| dc.date.copyright | 2022-09-26 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-09-20 | |
| dc.identifier.citation | Alameer, A., Kyriazakis, I., & Bacardit, J. (2020). Automated recognition of postures and drinking behaviour for the detection of compromised health in pigs. Scientific reports, 10(1), 1-15. Balasaravanan, T., Chezhian, P., Kamalakannan, R., Yasodha, R., Varghese, M., Gurumurthi, K., & Ghosh, M. (2006). Identification of species-diagnostic ISSR markers for six Eucalyptus species. Silvae Genetica, 55(3), 119-122. Council of Agriculture, E. Y., Taiwan. (2020). BASIC AG. STATISTICS 2020 Council of Agriculture, Executive Yuan, Taiwan Fukushima, K. (1980). Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biological Cybernetics, 36(4), 193-202. https://doi.org/10.1007/bf00344251 Gaab, T., Nogay, E., & Pierdon, M. (2022). Development and Progression of Shoulder Lesions and Their Influence on Sow Behavior. Animals, 12(3), 224. https://doi.org/10.3390/ani12030224 Gill, J., & Thomson, W. (1956). Observations on the behaviour of suckling pigs. Brit. J. Animal Behaviour, 4, 46-51. Ho, K. Y., Tsai, Y. J., & Kuo, Y. F. (2021). Automatic monitoring of lactation frequency of sows and movement quantification of newborn piglets in farrowing houses using convolutional neural networks. Computers and Electronics in Agriculture, 189. Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://dx.doi.org/10.1162/neco.1997.9.8.1735 Ison, S. H., Jarvis, S., Ashworth, C. J., & Rutherford, K. M. (2017). The effect of post-farrowing ketoprofen on sow feed intake, nursing behaviour and piglet performance. Livestock science, 202, 115-123. Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Kingma, D. P., Ba, J.,. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. https://dx.doi.org/10.48550/arxiv.1412.6980 Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval research logistics quarterly, 2(1‐2), 83-97. Lao, F., Brown-Brandl, T., Stinn, J. P., Liu, K., Teng, G., & Xin, H. (2016). Automatic recognition of lactating sow behaviors through depth image processing. Computers and Electronics in Agriculture, 125, 56-62. Maselyne, J., Adriaens, I., Huybrechts, T., De Ketelaere, B., Millet, S., Vangeyte, J., Van Nuffel, A., & Saeys, W. (2016). Measuring the drinking behaviour of individual pigs housed in group using radio frequency identification (RFID). Animal, 10(9), 1557-1566. Milan, A., Leal-Taixé, L., Reid, I., Roth, S., & Schindler, K. (2016). MOT16: A benchmark for multi-object tracking. arXiv preprint arXiv:1603.00831. Mingxing Tan, Q. V. L. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. International Conference on Machine Learning. https://doi.org/10.48550/arxiv.1905.11946 Muns, R., Manzanilla, E. G., Sol, C., Manteca, X., & Gasa, J. (2013). Piglet behavior as a measure of vitality and its influence on piglet survival and growth during lactation. Journal of animal science, 91(4), 1838-1843. Nasirahmadi, A., Sturm, B., Olsson, A.-C., Jeppsson, K.-H., Müller, S., Edwards, S., & Hensel, O. (2019). Automatic scoring of lateral and sternal lying posture in grouped pigs using image processing and Support Vector Machine. Computers and Electronics in Agriculture, 156, 475-481. Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., Lin, Z., Desmaison, A., Antiga, L., & Lerer, A. (2017). Automatic differentiation in pytorch. Pedersen, M., Moustsen, V., Nielsen, M., & Kristensen, A. (2011). Improved udder access prolongs duration of milk letdown and increases piglet weight gain. Livestock science, 140(1-3), 253-261. Redmon, J., & Farhadi, A. (2016). YOLO9000: Better, faster, stronger. arXiv. arXiv preprint arXiv:1612.08242. Sun, L., Zou, Y., Li, Y., Cai, Z., Li, Y., Luo, B., Liu, Y., & Li, Y. (2018). Multi target pigs tracking loss correction algorithm based on Faster R-CNN. International Journal of Agricultural and Biological Engineering, 11(5), 192-197. Timsina, M. P., & Thiengtham, J. (2007). Effect of L-carnitine Supplementation in Gestating and Lactating Diets on Sow Performances. Agriculture and Natural Resources, 41(3), 467-477. Tzutalin. (2015). LabelImg. https://github.com/tzutalin/labelImg Van Beirendonck, S., Van Thielen, J., Verbeke, G., & Driessen, B. (2014). The association between sow and piglet behavior. Journal of Veterinary Behavior, 9(3), 107-113. Wojke, N., Bewley, A., & Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. Yang, A., Huang, H., Yang, X., Li, S., Chen, C., Gan, H., & Xue, Y. (2019). Automated video analysis of sow nursing behavior based on fully convolutional network and oriented optical flow. Computers and Electronics in Agriculture, 167, 105048. Yang, A., Huang, H., Zheng, B., Li, S., Gan, H., Chen, C., Yang, X., & Xue, Y. (2020). An automatic recognition framework for sow daily behaviours based on motion and image analyses. Biosystems Engineering, 192, 56-71. Yang, X., Liu, Q., Yan, J., Li, A., Zhang, Z., & Yu, G. (2019). R3det: Refined single-stage detector with feature refinement for rotating object. arXiv 2019. arXiv preprint arXiv:1908.05612. Zhang, Y., Cai, J., Xiao, D., Li, Z., & Xiong, B. (2019). Real-time sow behavior detection based on deep learning. Computers and Electronics in Agriculture, 163, 104884. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84569 | - |
| dc.description.abstract | 台灣養豬產業產值為全台畜牧業之冠，根據2020年行政院農業委員會的統計，養豬產業產值佔畜牧業總產值的42.4%。在台灣的養豬產業中，有14%的仔豬會在斷奶前死亡，而如何降低仔豬的死亡率一直是被受關注的議題。傳統上，分娩欄位內母豬與仔豬的健康狀態通常採人工監測，而此方法較主觀且耗時。因此，本研究旨在建立一個可以監測分娩欄位內母豬和仔豬行為的系統。本研究使用嵌入式系統搭配廣角攝影機來收集分娩欄位的影片。目前收集到的影片數量已超過5000小時。在母豬方面，本研究提出了一個結合EfficientNet與長短期記憶（LSTM）的模型來辨識母豬的7種姿態。而仔豬方面則是利用旋轉目標檢測器R3Det來進行仔豬定位，並透過簡單在線實時追蹤(SORT)演算法追蹤連續影像中的仔豬。本研究在母豬姿態辨識上的F1-score達到0.92，仔豬定位的F1-score達到0.92，而仔豬追蹤的MOTA達94.6%。根據母豬姿態模型辨識的結果，可計算母豬的哺乳時長、哺乳頻率、吃料時長、吃料頻率、趴臥時長及姿勢變化頻率6個指標；根據仔豬偵測與追蹤模型的結果，可計算仔豬的活動量及吃奶、活動、休息的比例；而結合以上兩個模型的辨識結果，則可偵測於母豬哺乳時未吃奶的仔豬。此外，本研究將兩模型應用在十個分娩欄位中，對母豬分娩後第1至15天進行了長期分析。本研究提出的方法可以監測分娩欄內哺乳母豬及其仔豬的相關行為，有望為養豬行業勞動力短缺問題提供有效幫助。 | zh_TW |
| dc.description.abstract | Pork accounts for a major proportion of meat consumption in Taiwan. In 2020, the output value of pig production reached 42.4% of the total output value of animal production. However, in Taiwan’s pig farming, the preweaning mortality rate is about 14%, which severely impacts the output value. Traditionally, manual monitoring and diagnosis of the health condition of piglets and sows in farrowing crates has been discontinuous, subjective, and time-consuming. Therefore, this study aims to establish a system that can monitor the behavior of sows and piglets in farrowing houses. In this study, embedded systems equipped with webcams to collect the videos were installed in farrowing crates. More than 5,000 hours of videos have been collected. On the aspect of the sow, a model combining EfficientNet and long short-term memory (LSTM) was proposed to identify the posture of the sow. On the aspect of piglets, the Refined Rotation RetinaNet (R3Det) was used to locate the piglets in each frame of the video, and the SORT algorithm was introduced to track the piglets. The F1-score of sow posture recognition reached 0.92. The F1-score of piglet localization reached 0.92, and the MOTA of piglet tracking was 94.6%. Using the results of the sow posture recognition model, six metrics of the sow were calculated, namely sow lactating time, sow lactating frequency, sow feeding time, sow feeding frequency, sow recumbency time, and sow posture change frequency. Through the results of the piglet localization model and piglet tracking, two metrics of piglets were calculated, which were piglet movement and the daily activity ratio of piglet (feeding, active, and rest). By combining the results of the two models, unfed piglet events could be found. Furthermore, the two models were successfully applied in ten sets of farrowing crates across a 15-day period in this study. Long-term analysis of each crate was performed, and anomalous crates were successfully identified. By monitoring the behavior of lactating sow and her piglets in the farrowing crate using the method proposed in this study, the labor shortage problem in the pig industry can be ameliorated. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:15:59Z (GMT). No. of bitstreams: 1 U0001-2009202216114400.pdf: 2871058 bytes, checksum: d1bc2c5242e68849d85694bb884628cf (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | TABLE OF CONTENTS ACKNOWLEDGEMENTS I 摘要 II ABSTRACT III TABLE OF CONTENTS V LIST OF FIGURES VII LIST OF TABLES X CHAPTER 1 INTRODUCTION 1 1.1 Background 1 1.2 Objectives 1 1.3 Organization 2 CHAPTER 2 LITERATURE REVIEW 3 2.1 Correlation between the behavior of sow and the growth of her piglets 3 2.2 Image processing-based and deep learning-based approaches for pig posture recognition 4 2.3 Deep learning-based approaches for pig localization and tracking 5 CHAPTER 3 MATERIALS AND METHODS 6 3.1 Overview of the system 6 3.2 Experimental sites 7 3.3 Video acquisition 7 3.4 Video conversion 8 3.5 Clip and image annotation 9 3.6 Sow posture recognition and daily metrics 11 3.7 Piglet localization and movement quantification 11 3.8 Unfed piglet detection 13 3.9 Video collection for long-term analysis 14 CHAPTER 4 RESULTS AND DISCUSSION 15 4.1 Performance of sow posture recognition model 15 4.2 Long-term sow posture analysis 19 4.3 Performance of piglet localization 24 4.4 Performance of piglet tracking 25 4.5 Long-term piglet movement analysis 25 4.6 Piglet activity quantification using SPRM and PLM 27 4.7 Unfed piglet detection 28 CHAPTER 5 CONCLUSION 30 REFERENCE 32 | |
| dc.language.iso | en | |
| dc.subject | 仔豬偵測 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 母豬姿態 | zh_TW |
| dc.subject | Piglet detection | en |
| dc.subject | Deep learning | en |
| dc.subject | Sow posture | en |
| dc.title | 利用卷積神經網路監測分娩欄位內母豬及仔豬泌乳相關行為 | zh_TW |
| dc.title | Monitoring the behaviors related to lactating of sow and her piglets in farrowing crates using CNNs | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳永耀(Yung-Yao Chen),王佩華(Pei-Hwa Wang),林恩仲(En-Chung Lin) | |
| dc.subject.keyword | 深度學習,母豬姿態,仔豬偵測, | zh_TW |
| dc.subject.keyword | Deep learning,Sow posture,Piglet detection, | en |
| dc.relation.page | 35 | |
| dc.identifier.doi | 10.6342/NTU202203657 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-09-22 | |
| dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
| dc.contributor.author-dept | 生物機電工程學系 | zh_TW |
| dc.date.embargo-lift | 2022-09-26 | - |
| 顯示於系所單位： | 生物機電工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2009202216114400.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 2.8 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。