請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18988
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳世芳(Shih-Fang Chen) | |
dc.contributor.author | Yi-Zhen Lin | en |
dc.contributor.author | 林宜蓁 | zh_TW |
dc.date.accessioned | 2021-06-08T01:41:38Z | - |
dc.date.copyright | 2020-09-25 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-18 | |
dc.identifier.citation | 王安石、蔡志勇、沈雅鈞。2019。北部地區柑橘產業發展與輔導。北部地區柑橘栽培管理技術暨產業輔導研討會。1-10。 江淑雯、盧柏松。2011。臍橙精準套袋技術簡介。農政與農情 234:90~92。 行政院農業委員會。2012。蔬果品質分級標準暨包裝規格手冊-水果篇。網址:https://www.afa.gov.tw/ebook/afa/ebook13_1。上網日期:2020-4-13。 台北農產運銷股份有限公司。2016。蔬果分級標準及包裝規格手冊。網址:http://www.tapmc.com.taipei/Pages/Market/Packing。上網日期:2020-7-10。 陳祈男、黃維廷、蔡佳欣、蔡志濃、湯楊欽憲、石憲宗。2015。柑橘健康管理生產體系之研究。農試所特刊之188號。103年度重點作物健康管理生產體系及關鍵技術之研發成果研討會論文集。 陳右人、邱祝櫻、阮素芬、李文豪。2017。柑橘類的產期調節。果樹產期調節研究發展與產業調適研討會論文輯 134:59-90。吳庭嘉、葉文彬、陳盟松、徐錦木主編。臺中:行政院農業委員會臺中區農業改良場。 黃美華。2005。臺灣柑橘產業回顧與展望。台灣柑橘產業發展研討會專刊,中國園藝學會出版。嘉義,台灣。25-39。 馮永富。2020。北部地區桶柑採收後處理及儲藏技術。北部地區柑桔栽培管理技術暨產業輔導研討會。65-71。 鄒芳諭。2010。以非量測性相機進行近景攝影測量探討。碩士論文。新竹:國立交通大學土木工程學系。 劉曰聖。2018。基於遮蔽感知深度量測之光場相機深度擷取系統。碩士論文。新竹:國立交通大學光電工程學系。 劉元昌、張志展、李宗樺。2019。北部地區柑橘產銷研究-以青果 合作社新竹分社為例。北部地區柑橘栽培管理技術暨產業輔導研討會。73-85。 Chang, C. C., Lin, C. J. (2011). LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2(3), 27. https://doi.org/10.1145/1961189.1961199 Cheng, H., Damerow, L., Sun, Y., Blanke, M. (2017). Early yield prediction using image analysis of apple fruit and tree canopy features with neural networks. J. Imaging, 3(1), 6. https://doi.org/10.3390/jimaging3010006 Dalal, N., Triggs, B. (2005, June). Histograms of oriented gradients for human detection. Proc. 2005 IEEE Int. Conf. Computer Vision Pattern Recognition (CVPR), 1, pp. 886- 893. Everingham, M., Van Gool, L., Williams, C. K., Winn, J., Zisserman, A. (2010). The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis., 88(2), 303-338. https://doi.org/10.1007/s11263-009-0275-4 He, Z. L., Xiong, J.-T., Lin, R., Zou, X., Tang, L.Y., Yang, Z. G., Liu, Z., Song, G. (2017). A method of green litchi recognition in natural environment based on improved LDA classifier. Comput. Electron. Agric., 140, 159-167. Hung, C., Underwood, J., Nieto, J., Sukkarieh, S. (2015). A feature learning based approach for automated fruit yield estimation. In Field and service robotics. (pp. 485-498). Cham: Springer. Klose, R., Penlington, J., Ruckelshausen, A. (2009). Usability study of 3D time-of-flight cameras for automatic plant phenotyping. In 1st Int. Workshop on Computer Image Analysis in Agriculture, pp. 93-105. Lehnert, C., Sa, I., McCool, C., Upcroft, B., Perez, T. (2016). Sweet pepper pose detection and grasping for automated crop harvesting. Proc. 2016 IEEE Int. Conf. Robotics and Automation (ICRA), pp. 2428–2434. Liu, F., Shen, C., Lin, G., Reid, I. D. (2016). Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields. IEEE Trans. Pattern Anal. Mach. Intell., 38(10), 2024-2039. López-Rubio, E., Thurnhofer-Hemsi, K., de Cózar-Macías, Ó. D., Blázquez-Parra, E. B., Muñoz-Pérez, J., de Guevara-López, I. L. (2017). Robust fitting of ellipsoids by separating interior and exterior points during optimization. J. Math. Imaging Vis., 58(2), 189-210. Müller-Linow, M., Pinto-Espinosa, F., Scharr, H., Rascher, U. (2015). The leaf angle distribution of natural plant populations: assessing the canopy with a novel software tool. Plant methods, 11(1), 11. https://doi.org/10.1186/s13007-015-0052-z. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., ... Desmaison, A. (2019). Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems (NIPS), pp. 8026-8037. Regunathan, M. W. S. Lee. 2005. Citrus Fruit Identification and Size Determination Using Machine Vision and Ultrasonic Sensors. ASABE Paper No. 053017. St. Joseph, Mich.: ASABE. Ren, S., He, K., Girshick, R., Sun, J. (2015). Faster R-CNN: Towards real-time object detection with region proposal networks. Proc. 28th Int. Conf. Neural Information Processing Systems 28 (NIPS). NY: Curran Associates. Sa, I., Lehnert, C., English, A., McCool, C., Dayoub, F., Upcroft, B., Perez, T. (2017). Peduncle detection of sweet pepper for autonomous crop harvesting—Combined Color and 3-D Information. In IEEE Robotics and Automation Letters, 2(2), pp. 765-772. Saxena, A., Chung, S. H., Ng, A. Y. (2005). Learning Depth from Single Monocular Images. In Advances in Neural Information Processing Systems Conference (NIPS), pp. 1161-1168. Sengupta, S., Lee, W. S. (2014). Identification and determination of the number of immature green citrus fruit in a canopy under different ambient light conditions. Biosyst. Eng., 117, 51-61. Simonyan, K., Zisserman , A. (2015). Very deep convolutional networks for large-scale image recognition. Proc. Int. Conf. Learning Representations (ICLR). NY: Ithaca. Tzutalin (2015). LabelImg. Git code:https://github.com/tzutalin/labelImg。上網日期:2020-6-10。 Wang, Z., Walsh, K. B., Verma, B. (2017). On-tree mango fruit size estimation using RGB-D images. Sensors, 17(12), 2738. https://doi.org/10.3390/s17122738 Yamamoto, K., Guo, W., Yoshioka, Y., Ninomiya, S. (2014). On plant detection of intact tomato fruits using image analysis and machine learning methods. Sensors, 14(7), 12191-12206. https://doi:10.3390/s140712191 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18988 | - |
dc.description.abstract | 應用機器視覺協助田間作物偵測,將有助於減緩農業勞動力短缺的困境,並可透過提供即時的生長狀況以利農民制定生產策略。然由於田間狀況多變,如:光線變化、作物與背景間顏色相近、遮蔽等,皆造成傳統影像處理方法之辨識難點。近年來卷積神經網路興起,其具適應性強之優勢,故本研究將應用卷積神經網路進行柑橘作物之辨識及定位,並結合深度攝影機,建立可提供柑橘成熟度、果實數量及尺寸之預測模型。首先採用更快速區域卷積神經網路(faster region convolutional neural network, Faster-RCNN)模型於彩色影像中判讀果實所在位置及其成熟度。成熟度共分為轉色期及成熟期兩類,在設定工作範圍20至200公分內,可得目標物召回率及精確度分別為89%及73%。接續使用支持向量機(support vector machine, SVM)區分出辨識結果中未遮蔽的樣本以進行尺寸評估,將彩色影像辨識出之果實所在區域分別對應至深度圖(depth map)及點雲(point cloud)資訊。取深度圖之平均深度為物距,利用薄透鏡公式(thin lens equation)估計直徑;點雲資訊則進行橢球面擬合,以求得之軸長估計直徑。兩模型之平均絕對百分比誤差(mean absolute percentage error, MAPE)分別為6%及22%。結合以上述流程所開發之柑橘採收狀態評估模型,並配合現有之產銷分級標準,可將影像中之目標物進行初步分級統計。透過所開發之預測模型所提供之果實計數、成熟度及分級分佈之評估等即時資訊,期可協助農民快速掌握作物生長狀態、便利作業安排,及提升田間管理之效率。 | zh_TW |
dc.description.abstract | Applying machine vision on crops monitoring alleviates the labor shortage issue, and it helps framers to formulate production strategies by providing real-time growing status. However, various field conditions pose a higher challenge in traditional image processing, such as illumination changes, color similarity, and occlusion, etc. In recent years, convolutional neural networks have gradually risen, and it has the advantage of strong adaptability. Therefore, this study applied the convolutional neural network to identify and locate citrus fruits, and it combined a depth camera to establish a predictive model. It could provide the information of ripeness, and estimate the fruit counts and associated sizes. First, faster region convolutional neural network (Faster RCNN) was applied to the color images to localize the fruit position and identify two ripeness, including ripening and ripened. The recall and precision of all fruits were 89% and 73% in the measuring range from 20 to 200 cm. Then the support vector machine (SVM) were applied to distinguish the non-occluded samples in the identification results for size estimation. The identified regions in the color image were mapped to the depth map and point cloud, respectively. The object distances were the average of depth maps, and the thin lens equation was applied to obtain the estimated diameters. The point clouds were conducted with ellipsoid fitting method to obtain the estimated diameters according to the resulted major axis length. The mean absolute percentage error (MAPE) of these two models were 6% and 22%, respectively. The proposed algorithm, evaluating the harvesting status for citrus fruit, was obtained by combining the above-mentioned processes. Cooperating with the existing grading standards, the objects in the images can be classified and counted. Through the developed model, real-time information including the fruit counts, stages of ripeness, and distribution of the potential grading could be provided. It helps farmers to monitor the growth condition in time, facilitates operation arrangement, and improve the efficiency of field management. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T01:41:38Z (GMT). No. of bitstreams: 1 U0001-1708202023214000.pdf: 4369192 bytes, checksum: aa9652a5502362545312010c120e9461 (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | 致謝 i 摘要 ii Abstract iii 目錄 v 圖目錄 vii 表目錄 ix 中英文名詞暨縮寫對照 x 第一章 緒論 1 1.1 前言 1 1.2 研究目的 2 第二章 文獻回顧 3 2.1 台灣之柑桔產業概況 3 2.2 田間果實定位及辨識 4 2.3 深度資訊應用於農業領域 5 2.3.1 深度量測技術 5 2.3.2 深度資訊應用於作物尺寸評估 6 第三章 材料與方法 7 3.1 資料擷取及蒐集 8 3.1.1 影像蒐集步驟及取像設備 8 3.2 柑橘二維定位及辨識 12 3.2.1 影像樣本 12 3.2.2 柑橘辨識模型之訓練 14 3.2.3 評估方式 16 3.2.4 遮蔽狀況分辨模型 17 3.3 柑橘尺寸評估 21 3.3.1 薄透鏡原理 21 3.3.2 點雲橢球擬合 22 3.4 系統開發環境 26 第四章 結果與討論 27 4.1 柑橘影像定位及辨識 27 4.1.1 目標物距離估計 27 4.1.2 Faster-RCNN模型結果 28 4.2 遮蔽狀況判別及影響 32 4.3 柑橘尺寸及分級預測 33 4.3.1 利用深度圖估計柑橘直徑 33 4.3.2 利用點雲估計柑橘直徑 35 第五章 結論與建議 39 5.1 結論 39 5.2 建議 40 參考文獻 41 | |
dc.language.iso | zh-TW | |
dc.title | 卷積神經網路及深度資訊於柑橘採收狀態評估之應用 | zh_TW |
dc.title | Evaluation of Harvesting Status for Citrus Fruit Using Convolutional Neural Networks and Depth Information | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 謝廣文(Kuang-Wen Hsieh),郭彥甫(Yan-Fu Kuo) | |
dc.subject.keyword | 卷積神經網路,深度圖,點雲,水果採收,成熟度, | zh_TW |
dc.subject.keyword | Convolutional neural network,Depth map,Point cloud,Fruit harvesting,Ripeness, | en |
dc.relation.page | 43 | |
dc.identifier.doi | 10.6342/NTU202003888 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2020-08-19 | |
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 |
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 | |
---|---|---|---|
U0001-1708202023214000.pdf 目前未授權公開取用 | 4.27 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。