請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95971完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林國峰 | zh_TW |
| dc.contributor.advisor | Gwo-Fong Lin | en |
| dc.contributor.author | 曾元福 | zh_TW |
| dc.contributor.author | Yuan-Fu Zeng | en |
| dc.date.accessioned | 2024-09-25T16:24:18Z | - |
| dc.date.available | 2024-09-26 | - |
| dc.date.copyright | 2024-09-25 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2024-09-16 | - |
| dc.identifier.citation | Acosta-Coll, M., Ballester-Merelo, F., Martinez-Peiró, M., & De la Hoz-Franco, E. (2018). Real-time early warning system design for pluvial flash floods—A review. Sensors, 18(7), 2255.
Agency, W. R. (2023). Maintenance and Management of Water Image Monitoring Station and Cloud Platform Plan in 2022. M. Water Resources Agency. Baheti, B., Innani, S., Gajre, S., & Talbar, S. (2020). Semantic scene segmentation in unstructured environment with modified DeepLabV3+. Pattern Recognition Letters, 138, 223-229. https://doi.org/https://doi.org/10.1016/j.patrec.2020.07.029 Cao, X., Pan, J.S., Wang, Z., Sun, Z., ul Haq, A., Deng, W., & Yang, S. (2021). Application of generated mask method based on Mask R-CNN in classification and detection of melanoma. Computer Methods and Programs in Biomedicine, 207, 106174. https://doi.org/https://doi.org/10.1016/j.cmpb.2021.106174 Chan, H.Y., & Tsai, M.H. (2023). Alert notifications for governmental disaster response via instant messaging applications. International Journal of Disaster Risk Reduction, 96, 103984. https://doi.org/https://doi.org/10.1016/j.ijdrr.2023.103984 Chang, L.C., Liou, J.Y., & Chang, F.J. (2022). Spatial-temporal flood inundation nowcasts by fusing machine learning methods and principal component an-alysis. Journal of Hydrology, 612, 128086. https://doi.org/https://doi.org/10.1016/j.jhydrol.2022.128086 Chang, M.J., Chang, H.K., Chen, Y.C., Lin, G.F., Chen, P.-A., Lai, J.-S., & Tan, Y.-C. (2018). A Support Vector Machine Forecasting Model for Typhoon Flood Inundation Mapping and Early Flood Warning Systems. Water, 10(12), 1734. https://www.mdpi.com/2073-4441/10/12/1734 Chen, L.C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587. Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, At-rous Convolution, and Fully Connected CRFs. IEEE Transactions on Patt-ern Analysis and Machine Intelligence, 40(4), 834-848. https://doi.org/10.1109/TPAMI.2017.2699184 Cheng, J., Song, C., Liu, K., Fan, C., Ke, L., Chen, T., Zhan, P., & Yao, J. (2022). Satellite and UAV-based remote sensing for assessing the flooding ris-k from Tibetan lake expansion and optimizing the village relocation site. Science of The Total Environment, 802, 149928. https://doi.org/https://doi.org/10.1016/j.scitotenv.2021.149928 Conrady, C. R., Er, Ş., Attwood, C. G., Roberson, L. A., & de Vos, L. (2022). Automated detection and classification of southern African Roman seabream using mask R-CNN. Ecological Informatics, 69, 101593. https://doi.org/https://doi.org/10.1016/j.ecoinf.2022.101593 Disaster Prevention Research Center. (2024). Flood Sensor Information Integration. National Cheng Kung University. Retrieved April 05 from https://www.dprcflood.org.tw/SGDS/FDashboard.html Dubey, A. K., Kumar, P., Chembolu, V., Dutta, S., Singh, R. P., & Rajawat, A. S. (2021). Flood modeling of a large transboundary river using WRF-Hydro and microwave remote sensing. Journal of Hydrology, 598, 126391. https://doi.org/https://doi.org/10.1016/j.jhydrol.2021.126391 Fang, H., Hovad, E., Zhang, Y., & Juul Jensen, D. (2023). Application of Mask R-CNN for lab-based X-ray diffraction contrast tomography. Materials Characterization, 201, 112983. https://doi.org/https://doi.org/10.1016/j.matchar.2023.112983 Feng, Y., Brenner, C., & Sester, M. (2020). Flood severity mapping from Volunt-eered Geographic Information by interpreting water level from images containing people: A case study of Hurricane Harvey. ISPRS Journal of Photogrammetry and Remote Sensing, 169, 301-319. https://doi.org/https://doi.org/10.1016/j.isprsjprs.2020.09.011 Gu, Y.F., Hu, J., & Williams, G. A. (2023). A comparative study on CNN-based semantic segmentation of intertidal mussel beds. Ecological Informatics, 75, 102116. https://doi.org/https://doi.org/10.1016/j.ecoinf.2023.102116 Hastie, T., Tibshirani, R., Friedman, J. H., & Friedman, J. H. (2009). The elements of statistical learning: data mining, inference, and prediction (Vol. 2). Springer. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017, 22-29 Oct. 2017). Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), He, Y., Wang, J., Zhang, Y., & Liao, C. (2022). Enhancement of Urban Floodwater Mapping From Aerial Imagery With Dense Shadows via Semisupervised Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 9086-9101. https://doi.org/10.1109/JSTARS.2022.3215730 Huang, S.L., Lee, Y.C., & Chiang, L.Y. (2022). Assessing the synergies and trade-offs of development projects in response to climate change in an urban region. Journal of Environmental Management, 319, 115731. https://doi.org/https://doi.org/10.1016/j.jenvman.2022.115731 Hydraulic Engineering Office. (2023). Taipei City Flooding Statistics. Taipei City Government Retrieved March 03 from https://heovcenter.gov.taipei/TpeFloodRecord/Home.aspx#U Kaiser, P., Wegner, J. D., Lucchi, A., Jaggi, M., Hofmann, T., & Schindler, K. (2017). Learning Aerial Image Segmentation From Online Maps. IEEE Transactions on Geoscience and Remote Sensing, 55(11), 6054-6068. https://doi.org/10.1109/TGRS.2017.2719738 Karanjit, R., Pally, R., & Samadi, S. (2023). FloodIMG: flood image DataBase system. Data in brief, 48, 109164. Lai, C.H., Lin, I.S., & Huang, C.-S. (2020). Intelligent Flood Prevention System：Flood Sensing Equipment Deployment and Data Application. Public Governance Quarterly, 8(3), 82-93. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., & Wang, Z. (2017). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE conference on computer vision and pattern recognition, Lemley, J., Bazrafkan, S., & Corcoran, P. (2017). Smart Augmentation Learning an Optimal Data Augmentation Strategy. IEEE Access, 5, 5858-5869. https://doi.org/10.1109/ACCESS.2017.2696121 Lin, G.F., Huang, P.Y., & Chen, G.R. (2010). Using typhoon characteristics to improve the long lead-time flood forecasting of a small watershed. Journal of Hydrology, 380(3), 450-459. https://doi.org/https://doi.org/10.1016/j.jhydrol.2009.11.019 Ma, L., Dong, B., Yan, J., & Li, X. (2021, 5-9 July 2021). Matting Enhanced Mask R-CNN. 2021 IEEE International Conference on Multimedia and Expo (ICME), Mai, T., Mushtaq, S., Reardon-Smith, K., Webb, P., Stone, R., Kath, J., & An-Vo, D.-A. (2020). Defining flood risk management strategies: A systems approach. International Journal of Disaster Risk Reduction, 47, 101550. https://doi.org/https://doi.org/10.1016/j.ijdrr.2020.101550 Moy de Vitry, M., Kramer, S., Wegner, J. D., & Leitão, J. P. (2019). Scalable flood level trend monitoring with surveillance cameras using a deep convolutional neural network. Hydrol. Earth Syst. Sci., 23(11), 4621-4634. https://doi.org/10.5194/hess-23-4621-2019 Munawar, H. S., Hammad, A. W. A., & Waller, S. T. (2021). A review on flood management technologies related to image processing and machine learning. Automation in Construction, 132, 103916. https://doi.org/https://doi.org/10.1016/j.autcon.2021.103916 Pally, R. J., & Samadi, S. (2022). Application of image processing and convolutional neural networks for flood image classification and semantic segmentation. Environmental Modelling & Software, 148, 105285. https://doi.org/https://doi.org/10.1016/j.envsoft.2021.105285 Park, S., Baek, F., Sohn, J., & Kim, H. (2021). Computer Vision–Based Estimation of Flood Depth in Flooded-Vehicle Images. Journal of Computing in Civil Engineering, 35(2), 04020072. https://doi.org/doi:10.1061/(ASCE)CP.1943-5487.0000956 Ronneberger, O., Fischer, P., & Brox, T. (2015, 2015//). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Cham. Rosebrock, A. (2017). Deep learning for computer vision with python: Starter bundle. PyImageSearch. Rosser, J. F., Leibovici, D. G., & Jackson, M. J. (2017). Rapid flood inundation mapping using social media, remote sensing and topographic data. Natural Hazards, 87(1), 103-120. https://doi.org/10.1007/s11069-017-2755-0 Russell, B. C., Torralba, A., Murphy, K. P., & Freeman, W. T. (2008). LabelMe: A Database and Web-Based Tool for Image Annotation. International Journal of Computer Vision, 77(1), 157-173. https://doi.org/10.1007/s11263-007-0090-8 Sadiq, R., Akhtar, Z., Imran, M., & Ofli, F. (2022). Integrating remote sensing and social sensing for flood mapping. Remote Sensing Applications: Society and Environment, 25, 100697. https://doi.org/https://doi.org/10.1016/j.rsase.2022.100697 Shahinfar, S., Meek, P., & Falzon, G. (2020). “How many images do I need?” Understanding how sample size per class affects deep learning model performance metrics for balanced designs in autonomous wildlife monitoring. Ecological Informatics, 57, 101085. https://doi.org/https://doi.org/10.1016/j.ecoinf.2020.101085 Shih, S.S., Kuo, P.H., & Lai, J.S. (2019). A nonstructural flood prevention measure for mitigating urban inundation impacts along with river flooding effects. Journal of Environmental Management, 251, 109553. https://doi.org/https://doi.org/10.1016/j.jenvman.2019.109553 Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0 Torres, D. L., Feitosa, R. Q., Rosa, L. E. C. L., Happ, P. N., Marcato, J., Gonçalves, W. N., Martins, J., & Liesenberg, V. (2020, 22-26 March 2020). Semantic Segmentation Of Endangered Tree Species In Brazilian Savanna Using Deeplabv3+ Variants. 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS), Wang, C.H. (2020). Real-time flood inundation simulation and flood forecast for extreme rainfall with multiple hydrometeorological data based on cellular automata flood inundation model (Project No. MOST109-2625-M002-022). NSTC. https://www.grb.gov.tw/search/planDetail?id=13530672 Wang, J.H., Lin, G.F., Huang, Y.R., Huang, I. H., & Chen, C.-L. (2023). Application of hybrid machine learning model for flood hazard zoning assessments. Stochastic Environmental Research and Risk Assessment, 37(1), 395-412. https://doi.org/10.1007/s00477-022-02301-3 Wang, Y., Shen, Y., Salahshour, B., Cetin, M., Iftekharuddin, K., Tahvildari, N., Huang, G., Harris, D. K., Ampofo, K., & Goodall, J. L. (2024). Urban flood extent segmentation and evaluation from real-world surveillance camera images using deep convolutional neural network. Environmental Modelling & Software, 173, 105939. https://doi.org/https://doi.org/10.1016/j.envsoft.2023.105939 Wieland, M., Martinis, S., Kiefl, R., & Gstaiger, V. (2023). Semantic segmentation of water bodies in very high-resolution satellite and aerial images. Remote Sensing of Environment, 287, 113452. https://doi.org/https://doi.org/10.1016/j.rse.2023.113452 Wu, M.C., & Lin, G.F. (2015). An Hourly Streamflow Forecasting Model Coupled with an Enforced Learning Strategy. Water, 7(11), 5876-5895. https://www.mdpi.com/2073-4441/7/11/5876 Wu, X., Zhang, Z., Xiong, S., Zhang, W., Tang, J., Li, Z., An, B., & Li, R. (2023). A Near-Real-Time Flood Detection Method Based on Deep Learning and SAR Images. Remote Sensing, 15(8). You, J., & Korhonen, J. (2022). Attention integrated hierarchical networks for no-reference image quality assessment. Journal of Visual Communication and Image Representation, 82, 103399. https://doi.org/https://doi.org/10.1016/j.jvcir.2021.103399 Yousefi, S., Pourghasemi, H. R., Rahmati, O., Keesstra, S., Emami, S. N., & Hooke, J. (2021). Geomorphological change detection of an urban meander loop caused by an extreme flood using remote sensing and bathymetry measurements (a case study of Karoon River, Iran). Journal of Hydrology, 597, 125712. https://doi.org/https://doi.org/10.1016/j.jhydrol.2020.125712 Zeng, Z., Gan, Y., Kettner, A. J., Yang, Q., Zeng, C., Brakenridge, G. R., & Hong, Y. (2020). Towards high resolution flood monitoring: An integrated methodology using passive microwave brightness temperatures and Sentinel synthetic aperture radar imagery. Journal of Hydrology, 582, 124377. https://doi.org/https://doi.org/10.1016/j.jhydrol.2019.124377 川の防災情報ホームページ. (2024). 水害リスクライン. 国土交通省. Retrieved March 05 from https://frl.river.go.jp/TopViewMain?header=1&areacd=88 水利署水利防災組. (2024, April 18). 烏來吊橋、烏來老街與覽勝橋，新北市烏來區 [Video]. YouTube. https://www.youtube.com/watch?v=tx07sS9lCvY | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/95971 | - |
| dc.description.abstract | 受全球氣候變遷加劇影響，短延時強降雨之發生頻率及強度日漸嚴重，連帶增加淹水災害發生之可能性，對於城市和地下水道之基礎設施構成了嚴峻挑戰，而淹水發生區域及範圍定位資訊對於即時搶救災至關重要。傳統上，淹水事件多仰賴人力進行通報或於淹水熱區建置路淹感測器，然而這些作法缺乏時效性且需考量裝設成本及維護管理，亦僅能提供區域性之監測數據。因此，如何有效且具即時性之淹水檢測方法乃為刻不容緩之議題。
本研究基於深度學習模型開發即時淹水影像辨識模式，並透過路口監視器影像作為資料輸入，盼以既有廣泛佈設之CCTV (closed-circuit television)取代路淹感測器未能觸及之區域及人力監測通報，以達全面性並適用於城市應用。本研究所建立之模式包含兩個模組:圖像增強及影像辨識模組。首先，為改善監視器資料畫質普遍不佳及鏡頭固定使畫面呈單一性之缺點，本研究以Super Resolution General Adversarial Network (SRGAN)作為新穎影像增強作法來提升影像品質。接著，影像辨識模式模組使用Mask R-CNN及DeepLabv3+為基礎分別建構。最後，研究以實際淹水事件作為模式應用，以評估所開發之模式性能，結果證明是以DeepLabv3+模式結合影像增強作法表現為最佳，可以有效識別淹水發生及其範圍，並保有高效檢測效率可有效應用。在測試場次中，針對淹水辨識精確率為92%、召回率為94%，而用於評鑑辨識及實際重疊度的交併比(IoU)指標為87%；與水利署模式相比，本模式對於淹水範圍之判斷更為準確；針對模式適用性而言，於國、內外之影像畫面也能有效識別水體及應用。 此外，本研究亦證明預訓練權重及訓練數據對於模式有顯著影響，其中又以預訓練權重影響甚大，本研究所提出之影像增強作法，可有效提升模式整體性能，且模式辨識類別之範圍及準確度皆有所提升。總而言之，為彰顯淹水災害時快速且有效應變之重要性，本研究所提出之模式為提升城市的防災應變能力提供有效且準確之資訊，大幅降低淹水所造成生命財產損失之風險，且有助於提升城市的防災應變能力，以應對氣候變遷所帶來的威脅。 | zh_TW |
| dc.description.abstract | The frequency and intensity of short-duration heavy rainfall have escalated due to global climate change, increasing the probability of recurrent flooding and presenting a significant challenge to urban and underground water infrastructure. Information on the location of flooding zones and boundaries is crucial for disaster prevention and management decisions. Traditionally, flooding events are manually reported or are determined by flood sensors installed in critical areas of roads; however, these methods lack timeliness, incur installation and maintenance costs, and provide only regional monitoring data. Therefore, an effective and timely flood detection method is necessary.
This study develops a deep learning model based on real-time flooding image recognition to replace flooding sensors and human monitoring using the existing widely distributed closed-circuit television (CCTV), ensuring comprehensiveness and the applicability of this method in urban applications. Images from intersection monitors are employed as data input. The model comprises two modules: image enhancement and image recognition. First, the super-resolution general adversarial network (SRGAN) is used as a image enhancement method to improve image quality by improving the pixel quality of the CCTV data and the uniqueness of the lens fixation. Next, the image recognition module is constructed using the mask region-based convolutional neural network (Mask R-CNN) and DeepLabv3+. This study addresses whether to employ pre-trained weights in modeling and the effect of training data on the model to analyze and determine the optimal model. Finally, this study utilizes an actual flooding event to evaluate the performance of the developed model. The results indicate that the model, particularly when using the DeepLabv3+ model combined with image enhancement techniques, achieves optimal performance. It effectively identifies the occurrence and extent of flooding while maintaining high detection efficiency. During the testing set, the model achieved a precision rate of 92% and a recall rate of 94% for flood identification, with an Intersection over Union (IoU) score of 87%, reflecting the overlap between predicted and actual flood extents. Compared to models used by the Water Resources Agency (WRA), this model demonstrates superior accuracy in determining flood boundaries. Furthermore, the model has been shown to be applicable in identifying water bodies and flood extents in both domestic and international image datasets. In conclusion, the proposed model offers significant potential for enhancing disaster prevention and management capabilities in urban areas, enabling more effective responses to flooding events driven by climate change. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-09-25T16:24:18Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2024-09-25T16:24:18Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書 i
誌謝 ii 中文摘要 iii Abstract v Contents vii List of figures ix List of tables xi Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Objectives 5 1.3 Organization 5 Chapter 2 Methodology 6 2.1 Super-resolution generative adversarial network 6 2.2 DeepLabv3+ 8 2.2.1 Codec–Decoder Architecture and Backbone Networks 9 2.2.2 Atrous Spatial Pyramid Pooling 10 2.3 Mask region-based convolutional neural network 12 2.3.1 Backbone Feature Extraction Network 12 2.3.2 Regional Proposal Network 15 2.3.3 Network Heads 17 Chapter 3 Real-Time Flood Recognition Model Development 20 3.1 CCTV Flooding Database Establishment Step 21 3.1.1 Study Area 21 3.1.2 Flooding Image Dataset Establishment 22 3.2 Image Enhancement Modeling Step 28 3.3 Recognition Modeling Step 31 3.3.1 DeepLabv3+ 33 3.3.2 Mask R-CNN 34 3.4 Performance Measures 38 Chapter 4 Results and Discussion 41 4.1 Performance Comparison of the Flooding Recognition Model 41 4.1.1 Pre-trained Weight Results 41 4.1.2 Training Data Results 46 4.1.3 Image Enhancement Results 51 4.2 Performance of the Proposed Model for Test Events 58 4.3 Comparison of Existing Models and Model Applicability 66 Chapter 5 Conclusions 70 References 72 Publications 78 | - |
| dc.language.iso | en | - |
| dc.title | 人工智慧技術於即時淹水影像辨識之研究 | zh_TW |
| dc.title | Real-time flooding image recognition model using artificial intelligence techniques | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.oralexamcommittee | 林文欽;李方中;陳清田;范致豪 | zh_TW |
| dc.contributor.oralexamcommittee | Wen-Chin Lin;Fang-Chung Lee;Ching-Tien Chen;Chih-hao Fan | en |
| dc.subject.keyword | 影像辨識,淹水檢測,影像增強,深度學習,防災應變, | zh_TW |
| dc.subject.keyword | Image recognition,flood detection,image enhancement,deep learning,disaster response, | en |
| dc.relation.page | 79 | - |
| dc.identifier.doi | 10.6342/NTU202404377 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2024-09-16 | - |
| dc.contributor.author-college | 工學院 | - |
| dc.contributor.author-dept | 土木工程學系 | - |
| dc.date.embargo-lift | 2029-09-13 | - |
| 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-113-1.pdf 目前未授權公開取用 | 52.84 MB | Adobe PDF | 檢視/開啟 |
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。