請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97799完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 韓仁毓 | zh_TW |
| dc.contributor.advisor | Jen-Yu Han | en |
| dc.contributor.author | 江冠均 | zh_TW |
| dc.contributor.author | Guan-Jyun Jiang | en |
| dc.date.accessioned | 2025-07-16T16:18:07Z | - |
| dc.date.available | 2025-07-17 | - |
| dc.date.copyright | 2025-07-16 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-07-05 | - |
| dc.identifier.citation | Bernhard Bauer-Marschallinger, Senmao Cao, Mark Edwin Tupas, Florian Roth, Claudio Navacchi, Thomas Melzer, Vahid Freeman, and Wolfgang Wagner. Satellite-based flood mapping through Bayesian inference from a Sentinel-1 SAR datacube. Remote Sensing, 2022.
Abhishek Chaurasia and Eugenio Culurciello. Linknet: Exploiting encoder representations for efficient semantic segmentation. In Proceedings of the IEEE Visual Communications and Image Processing (VCIP), 2017. Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, and Hartwig Adam. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European Conference on Computer Vision (ECCV), 2018. Wei-Wei Chen, Hsien-Kuo Chang, and Chin-Cheng Liu. Analysis of spatiotemporal characteristics of cloud cover over coastal areas in Taiwan using MTSAT satellite imagery [in Chinese]. Journal of Photogrammetry and Remote Sensing, 2014. Xiaolong Dai and Siamak Khorram. The effects of image misregistration on the accuracy of remotely sensed change detection. IEEE Transactions on Geoscience and Remote Sensing, 1998. Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, and Jakob Uszkoreit. An image is worth 16×16 words: Transformers for image recognition at scale. arXiv preprint, 2020. Omar Elharrouss, Noor Almaadeed, Somaya Al-Maadeed, and Younes Akbari. Image inpainting: A review. Neural Processing Letters, 2020. Joseph J. Erinjery, Mewa Singh, and Rafi Kent. Mapping and assessment of vegetation types in the tropical rainforests of the Western Ghats using multispectral Sentinel-2 and SAR Sentinel-1 satellite imagery. Remote Sensing of Environment, 2018. Steve Foga, Pat Scaramuzza, Sen Guo, Zhe Zhu, Robert D. Dilley, and Tom Beckmann. Cloud detection algorithm comparison and validation for operational Landsat data products. Remote Sensing of Environment, 2017. Nafiseh Ghasemian and Mehdi Akhoondzadeh. Introducing two random forest based methods for cloud detection in remote sensing images. Advances in Space Research, 2018. Christine Guillemot and Olivier Le Meur. Image inpainting: Overview and recent advances. IEEE Signal Processing Magazine, 2014. Nguyen Thanh Hoan and Ryutaro Tateishi. Cloud removal of optical image using SAR data for ALOS applications. Journal of the Remote Sensing Society of Japan, 2023. André Hollstein, Karl Segl, Luis Guanter, Maximilian Brell, and Michael Enesco. Comparison of machine learning approaches for the retrieval of biophysical and biochemical variables from Sentinel-2A data. Remote Sensing, 2016. Kai Hu, Dongsheng Zhang, and Min Xia. CDUNet: Cloud detection UNet for remote sensing imagery. Remote Sensing, 2021. Ioannis Kavouras, Ioannis Rallis, Nikolaos Doulamis, and Anastasios Doulamis. Oceandc: An analysis-ready data cube framework for environmental and climate change monitoring over the port areas. In Proceedings of the International Conference on PErvasive Technologies Related to Assistive Environments (PETRA), 2024. A. Lewis, S. Oliver, L. Lymburner, B. Evans, L. Wyborn, N. Mueller, G. Raevski, J. Hooke, D. Irving, A. Ang, and B. Killough. Operational continental-scale land cover mapping of Australia using the Open Data Cube. Remote Sensing of Environment, 2017. Jiayi Li and Qunming Wang. CSDFormer: A cloud and shadow detection method for Landsat images based on transformer. International Journal of Applied Earth Observation and Geoinformation, 2024. Liyuan Li, Xiaoyan Li, Xin Liu, Wenwen Huang, Zhuoyue Hu, and Fansheng Chen. Attention mechanism cloud detection with modified FCN for infrared remote sensing images. IEEE Access, 2021. M. Li, S. C. Liew, and L. K. Kwoh. Producing cloud free and cloud-shadow free mosaic from cloudy IKONOS images. In IGARSS IEEE International Geoscience and Remote Sensing Symposium, 2003. Pengfei Li, Limin Dong, Huachao Xiao, and Mingliang Xu. A cloud image detection method based on SVM vector machine. Neurocomputing, 2015. Chao-Hung Lin, Po-Hung Tsai, Kang-Hua Lai, and Jyun-Yuan Chen. Cloud removal from multitemporal satellite images using information cloning. IEEE Transactions on Geoscience and Remote Sensing, 2012. Shuxian Liu, Yan Yin, Zhigang Chu, and Shuai An. CDL: A cloud detection algorithm over land for MWHS-2 based on the gradient boosting decision tree. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020. Yuhui Liu, Yu Zhou, and Xiaoqiang Yang. Bathymetry derivation and slope-assisted benthic mapping using optical satellite imagery in combination with ICESat-2. International Journal of Applied Earth Observation and Geoinformation, 2024. Luca Lorenzi, Farid Melgani, and Grégoire Mercier. Inpainting strategies for reconstruction of missing data in VHR images. IEEE Geoscience and Remote Sensing Letters, 2011. Aldo Maalouf, Philippe Carré, Bertrand Augereau, and Christine Fernandez-Maloigne. A bandelet-based inpainting technique for clouds removal from remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing, 2009. F. Melgani and A. Benabdelkader. Contextual reconstruction of cloud-contaminated multitemporal multispectral images. IEEE Transactions on Geoscience and Remote Sensing, 2006. Fausto Milletari, Nassir Navab, and Seyed-Ahmad Ahmadi. V-Net: Fully convolutional neural networks for volumetric medical image segmentation. arXiv preprint, 2016. Nathalie Pettorelli, William F. Laurance, Timothy G. O’Brien, Martin Wegmann, Harini Nagendra, and Will Turner. Satellite remote sensing for applied ecologists: Opportunities and challenges. Journal of Applied Ecology, 2014. Pattana Rakwatin, Wasuntorn Naenna, and Yossapong Laoonual. Restoration of Aqua MODIS band 6 using histogram matching and local least squares fitting. IEEE Transactions on Geoscience and Remote Sensing, 2009. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI, 2015. William B. Rossow and Robert A. Schiffer. ISCCP cloud data products. Bulletin of the American Meteorological Society, 1991. Arun Sen and Atish P. Sinha. Toward developing data warehousing process standards: An ontology-based review of existing methodologies. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 2007. Connor Shorten and Taghi M. Khoshgoftaar. A survey on image data augmentation for deep learning. Journal of Big Data, 2019. Peter Strobl, Peter Baumann, Adam Lewis, Zoltan Szantoi, Brian Killough, Matthew Purss, Max Craglia, Stefano Nativi, Alex Held, Trevor Dhu, et al. The six faces of the data cube. In Proceedings of the Conference on Big Data from Space, 2017. Carole H. Sudre, Wenqi Li, Tom Vercauteren, Sebastien Ourselin, and M. Jorge Cardoso. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In Lecture Notes in Computer Science, 2017. SR Surya and Philomina Simon. Automatic cloud removal from multitemporal satellite images. Journal of the Indian Society of Remote Sensing, 2015. Sory I. Toure, Douglas A. Stow, Hsiao-chien Shih, John Weeks, and David Lopez-Carr. Land cover and land use change analysis using multi-spatial resolution data and object-based image analysis. Remote Sensing of Environment, 2018. Wolfgang Wagner, Bernhard Bauer-Marschallinger, Claudio Navacchi, Felix Reuß, Senmao Cao, Christoph Reimer, Matthias Schramm, and Christian Briese. A Sentinel-1 backscatter datacube for global land monitoring applications. Remote Sensing, 2021. Qunming Wang, Yijie Tang, Yong Ge, Huan Xie, Xiaohua Tong, and Peter M. Atkinson. A comprehensive review of spatial-temporal-spectral information reconstruction techniques. Science of Remote Sensing, 2023. Q. Weng. Generating annual temperature maps from MODIS data through spatiotemporal analyses. Remote Sensing of Environment, 2014. Qihao Weng, Peng Fu, and Feng Gao. Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data. Remote Sensing of Environment, 2014. L. Zhang, P. Li, X. Sun, and L. Wang. Restoration of clouded pixels in multispectral remotely sensed imagery with cokriging. Remote Sensing of Environment, 2009. Xiao Zhang, Liangyun Liu, Xidong Chen, Shuai Xie, and Yuan Gao. Fine land-cover mapping in China using Landsat datacube and an operational Speclib-based approach. Remote Sensing, 2019. Zongwei Zhou, Md Mahfuzur Rahman Siddiquee, Nima Tajbakhsh, and Jianming Liang. UNet++: A nested U-Net architecture for medical image segmentation. arXiv preprint, 2018. Zhe Zhu, Shaohua Wang, and Curtis E. Woodcock. Object-based cloud and cloud shadow detection in Landsat imagery. Remote Sensing of Environment, 2015. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97799 | - |
| dc.description.abstract | 本研究針對光學衛星影像中雲層遮蔽問題，建構一套結合深度學習、資料立方與自動化影像融合之雲層偵測與除雲系統。首先，於雲層偵測階段，採用五種語義分割模型進行性能比較，結果顯示基於 Transformer 架構的 CSDFormer 於雲區識別表現最為優異，達成 91.08% 的雲區準確率（PA）、93.78% 的使用者準確率（UA）與 97.25% 的整體準確率（OA），並具備最快的推論速度與最低計算複雜度。其次，於除雲流程中，本研究以 SSIM（結構相似性指標）為排序依據，結合泊松融合進行雲區補全，於高達 80% 雲覆蓋情境下仍能維持 0.7105 的 SSIM，顯示良好的視覺品質與輻射一致性。最後，透過自行開發之資料立方系統整合影像屬性、空間範圍與坐標資訊，實作多條件篩選、影像排序與動態除雲操作，前端介面以 Flask 架構實現互動式展示，強化系統應用實用性。整體成果顯示，本研究提出之架構於多時序光學影像管理與除雲應用中具備高準確性、擴充性與操作效率，未來可作為光學遙測資料品質提升與資料治理整合之基礎平台。 | zh_TW |
| dc.description.abstract | This study proposes an integrated system for cloud detection and removal in optical satellite imagery, combining deep learning, a Datacube framework, and automated image fusion. Among five evaluated segmentation models, the Transformer-based CSDFormer achieved the best performance (PA: 91.08%, UA: 93.78%, OA: 97.25%) with the fastest inference speed and lowest complexity. For cloud removal, SSIM-based image ranking and Poisson blending were employed, maintaining an SSIM of 0.7105 even under 80% cloud cover. A custom Datacube was developed to manage metadata and spatial queries, supporting dynamic filtering and processing. The system, implemented with a Flask-based interface, shows strong accuracy, efficiency, and scalability for enhancing multi-temporal optical imagery. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-16T16:18:07Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-16T16:18:07Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 ii
摘要 iii Abstract iv 目次 v 圖次 ix 表次 xi 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 2 1.3 論文架構 5 第二章 文獻回顧 6 2.1 雲層對光學衛星影像品質與可用性之限制 6 2.2 光學衛星影像之雲層偵測技術演進 7 2.2.1 基於閾值的雲偵測方法 8 2.2.2 基於機器學習的雲偵測方法 9 2.2.3 基於深度學習的雲偵測方法 10 2.3 因應雲覆挑戰之光學影像除雲技術回顧 13 2.3.1 基於影像修復的除雲方法 15 2.3.2 基於多光譜影像的除雲方法 16 2.3.3 基於多時序影像之除雲方法 18 2.4 結合資料立方之多時序遙測影像管理與分析技術 20 2.4.1 資料倉儲與資料立方之關係 20 2.4.2 ROLAP 架構與空間查詢設計 21 2.4.3 資料立方在遙測影像應用 22 2.4.4 資料服務與模組化架構 23 2.4.5 資料立方之完整架構設計 24 2.5 小結 26 第三章 研究方法 28 3.1 光學衛星影像之資料前處理 29 3.1.1 光學衛星影像研究區域 29 3.1.2 影像裁切與格式轉換 30 3.1.3 訓練與測試資料劃分 32 3.2 雲層偵測模型訓練 32 3.2.1 訓練影像預處理與影像標註 33 3.2.2 雲層標註流程 34 3.2.3 模型選擇與訓練流程 36 3.2.4 評估指標與最佳模型選取 38 3.3 基於資料立方之自動除雲整合架構 40 3.3.1 雲層遮罩整合與影像中繼資料擷取 41 3.3.2 關聯式資料庫設計與建置 42 3.3.3 資料立方建構與功能整合 44 3.3.4 本研究資料庫設計特色總結 45 3.4 基於泊松方程之除雲方法 46 3.4.1 雲層替換區域選擇 46 3.4.2 泊松方程重建 47 3.4.3 全域優化處理 48 3.4.4 相似性評估指標 49 3.4.5 除雲成果評估 50 3.5 小結 51 第四章 實驗與結果分析 52 4.1 雲層偵測模型效能評估 52 4.1.1 光學衛星影像來源 53 4.1.2 資料前處理 55 4.1.3 模型參數設定 57 4.1.4 訓練硬體配置與模型實作細節 59 4.1.5 模型訓練成果 59 4.1.6 模型預測成果 60 4.1.7 模型在異源與異質區表現 62 4.2 除雲成果展示與評估 63 4.2.1 除雲流程設計 63 4.2.2 除雲成果分析 64 4.3 資料立方系統呈現 71 4.3.1 實體關聯圖設計 72 4.3.2 資料庫建構與實作 73 4.3.3 資料立方系統功能展示與測試設計 74 4.4 小結 77 第五章 結論與未來展望 79 5.1 結論 79 5.2 未來工作建議 80 參考文獻 82 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 泊松融合 | zh_TW |
| dc.subject | 資料立方 | zh_TW |
| dc.subject | 雲層去除 | zh_TW |
| dc.subject | 雲層偵測 | zh_TW |
| dc.subject | Datacube | en |
| dc.subject | Cloud Detection | en |
| dc.subject | Cloud Removal | en |
| dc.subject | Deep Learning | en |
| dc.subject | Poisson Blending | en |
| dc.title | 基於資料立方架構之光學衛星影像雲偵測與除雲技術 | zh_TW |
| dc.title | Cloud Detection and Removal Techniques for Optical Satellite Imagery Based on a Datacube Framework | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 張立雨;曾國欣;張智安 | zh_TW |
| dc.contributor.oralexamcommittee | Li-Yu Chang;Kuo-Hsin Tseng;Tee-Ann Teo | en |
| dc.subject.keyword | 雲層偵測,雲層去除,深度學習,泊松融合,資料立方, | zh_TW |
| dc.subject.keyword | Cloud Detection,Cloud Removal,Deep Learning,Poisson Blending,Datacube, | en |
| dc.relation.page | 88 | - |
| dc.identifier.doi | 10.6342/NTU202500924 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2025-07-08 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| dc.date.embargo-lift | 2025-07-17 | - |
| 顯示於系所單位： | 土木工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 17.64 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。