簡易檢索 / 詳目顯示

回結果列表
研究生： 陳志嫻
Pattamon Rattanapan
論文名稱： 使用多時衛星圖像與機器學習方法來偵測房屋的興建以追蹤城市的成長
A Machine Learning Approach in Detecting Building Construction for Urban Growth Tracking Using Multi-Temporal Satellite Imagery
指導教授： 蘇豐文
Soo, Von-Wun
口試委員: 王佑中
Wang, Yu-Chung
郭柏志
Kuo, Po-Chih
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊系統與應用研究所
Institute of Information Systems and Applications
論文出版年： 2023
畢業學年度： 111
語文別： 英文
論文頁數： 53
中文關鍵詞： 城市追蹤 、建築物評估 、遠距感測 、衛星影像 、捲機類神經網路 、時序預測
外文關鍵詞： Urbanization Tracking, Building Assessment, Remote Sensing, Satellite Imagery, Convolutional Neural Networks, Time series prediction
相關次數： 點閱：1  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • N/A

    When the megacity is not only the problem for one city but many around the world with the dramatic increase in population. Megacity is a complicated problem and needs a practical solution to ease both the current situation and the problem that may occur in the future. Satellite imagery is a popularity resource for urban growth study because of its rich and up-to-date information at the affordable price. However, there are many challenges, including the quality of satellite imagery, the incomplete dataset as well as the inconsistency of color and shapes in the satellite imagery that change in response to the weather. We employ the effectiveness of Mask-RCNN with Restnet backbone to create the buildings mask. We calculate the building area and background area then make a prediction of the urban area in the next time step by utilizing the Long Short-Term Memory (LSTM) prediction model. Overall, our localization model provides the comparative performance in comparison with the baseline model with more sufficient time for training. We also discover that the model should include multiple image augmentation to the training since there is no universal pattern for urban growth. In extension of urban area prediction, the building mask prediction is also a possible study for future work.

    摘要..............................................................i Abstract.........................................................ii Acknowledgement.................................................iii List of Tables...................................................vi List of Figures.................................................vii 1 Introduction..............................................1 1.1 Motivation................................................1 1.2 Research Challenges.......................................5 1.3 Thesis Outline............................................6 1.4 Contributions.............................................6 2 Related Work..............................................8 2.1 Remote Sensing for Urbanization...........................8 2.2 Urbanization Study Using Computer Vision Techniques......10 2.3 Convolutional Neural Networks (CNN)......................11 2.4 Semantic Segmentation with Mask RCNN.....................13 2.5 Sequential Prediction....................................16 3 Methodology..............................................18 3.1 Dataset..................................................18 3.2 The Baseline Algorithm...................................22 3.3 System Overview..........................................23 3.4 Building Detection Localization Model....................25 3.5 Urbanization Prediction..................................26 3.5.1 Urban Area Prediction....................................26 3.6 Evaluation Metric........................................28 3.6.1 Evaluation Metric for Building Detection.................28 3.6.2 Evaluation Metric for Urbanization Prediction............30 4 Experimental Result and Discussion.......................32 4.1 Building Detection.......................................32 4.1.1 Data preprocessing.......................................32 4.1.2 Building detection accuracy..............................33 4.2 Urbanization Prediction..................................37 5 Conclusion and Future Work...............................41 5.1 Conclusion...............................................41 5.2 Future Work..............................................44 References.......................................................45

    1. Usama Al-Mulali, Hassan Gholipour Fereidouni, Janice YM Lee, and Che Normee Binti Che Sab. Exploring the relationship between urbanization, energy consumption, and co2 emission in mena countries. Renewable and Sustainable Energy Reviews, 23:107–112, 2013.
    2. Ram Avtar, Saurabh Tripathi, Ashwani Kumar Aggarwal, and Pankaj Kumar.Population–urbanization–energy nexus: a review. Resources, 8(3):136, 2019.
    3. Hasi Bagan and Yoshiki Yamagata. Analysis of urban growth and estimating popu- lation density using satellite images of nighttime lights and land-use and population data. GIScience & Remote Sensing, 52(6):765–780, 2015.
    4. Ellen M Brennan and Harry W Richardson. Asian megacity characteristics, problems, and policies. International Regional Science Review, 12(2):117–129, 1989.
    5. Ying-Chu Chen. Effects of urbanization on municipal solid waste composition. Waste management, 79:828–836, 2018.
    6. May Yen Chu, Teik Hua Law, Hussain Hamid, Siong Hook Law, and Jin Chai Lee.Examining the effects of urbanization and purchasing power on the relationship be- tween motorcycle ownership and economic development: A panel data. International Journal of Transportation Science and Technology, 2020.
    7. William C Clark, Lorrae Van Kerkhoff, Louis Lebel, and Gilberto C Gallopin. Craft- ing usable knowledge for sustainable development. Proceedings of the National Academy of Sciences, 113(17):4570–4578, 2016.
    8. Pablo Pozzobon De Bem, Osmar Ab´ılio de Carvalho Junior, Renato Fontes Guimara˜es, and Roberto Arnaldo Trancoso Gomes. Change detection of deforestation in the brazilian amazon using landsat data and convolutional neural networks. Remote Sensing, 12(6):901, 2020.
    9. Alex de Sherbinin, Deborah Balk, Karina Yager, Malanding Jaiteh, Francesca Pozzi, Chandra Giri, and Antroinette Wannebo. A ciesin thematic guide to social science applications of remote sensing. New York: Center for International Earth Science Information Network (CIESIN) of Columbia University, 2002.
    10. Chaweewan Denpaiboon and Hidehiko Kanegae. Compact city strategy of bangkok mega-city. Manusya: Journal of Humanities, 11(2):38–55, 2008.
    11. Faisal Faisal, Turgut Tursoy, Nil Gunsel Resatoglu, and Niyazi Berk. Electricity consumption, economic growth, urbanisation and trade nexus: empirical evidence from iceland. Economic research-Ekonomska istrazˇivanja, 31(1):664–680, 2018.
    12. Jing-Li Fan, Yue-Jun Zhang, and Bing Wang. The impact of urbanization on residen- tial energy consumption in china: An aggregated and disaggregated analysis. Renew- able and Sustainable Energy Reviews, 75:220–233, 2017.
    13. WY Fung, Ka Se Lam, WT Hung, SW Pang, and YL Lee. Impact of urban tempera- ture on energy consumption of hong kong. Energy, 31(14):2623–2637, 2006.
    14. Xavier Gastaldi. Shake-shake regularization. arXiv preprint arXiv:1705.07485, 2017.
    15. Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V Le. Dropblock: A regularization method for convolutional networks. arXiv preprint arXiv:1810.12890, 2018.
    16. Ross Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015.
    17. Philip Guest. The impact of population change on the growth of mega-cities. Asia- Pacific population journal, 9(1):37–56, 1994.
    18. Xuemei Han, Ci Hu, and Ling Lin. A study on the impact of china’s urbanization on the quantity of municipal solid waste produced. Waste Management & Research, 38(2):184–192, 2020.
    19. Kaiming He, Georgia Gkioxari, Piotr Dolla´r, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961– 2969, 2017.
    20. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
    21. Sepp Hochreiter and Ju¨rgen Schmidhuber. Long short-term memory. Neural compu- tation, 9(8):1735–1780, 1997.
    22. Anett Hofmann and Guanghua Wan. Determinants of urbanization. Technical report, ADB Economics Working Paper Series, 2013.
    23. Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pages 448–456. PMLR, 2015.
    24. Jayanth Koushik. Understanding convolutional neural networks. arXiv preprint arXiv:1605.09081, 2016.
    25. Yann LeCun, Le´on Bottou, Yoshua Bengio, and Patrick Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278– 2324, 1998.
    26. Ke Li and Boqiang Lin. Impacts of urbanization and industrialization on energy consumption/co2 emissions: does the level of development matter? Renewable and Sustainable Energy Reviews, 52:1107–1122, 2015.
    27. Tsung-Yi Lin, Piotr Dolla´r, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017.
    28. Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ra- manan, Piotr Dolla´r, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
    29. Yaobin Liu. Exploring the relationship between urbanization and energy consumption in china using ardl (autoregressive distributed lag) and fdm (factor decomposition model). Energy, 34(11):1846–1854, 2009.
    30. Abdel-Aziz Adam Mahamat, Adeeba Al-Hurban, and Nehaya Saied. Change de- tection of lake chad water surface area using remote sensing and satellite imagery. Journal of Geographic Information System, 13(5):561–577, 2021.
    31. Inmaculada Mart´ınez-Zarzoso and Antonello Maruotti. The impact of urbaniza- tion on co2 emissions: evidence from developing countries. Ecological Economics, 70(7):1344–1353, 2011.
    32. Don R McCreary. Cambridge academic content dictionary. Dictionaries: Journal of the Dictionary Society of North America, 30(1):151–155, 2009.
    33. Voula Mega. Bangkok–the mega-city of angels. Ekistics, 65(388-390):107, 1998.
    34. Geetilaxmi Mohapatra and AK Giri. Economic development and environmental qual- ity: an econometric study in india. Management of Environmental Quality: An Inter- national Journal, 2009.
    35. Keiron O’Shea and Ryan Nash. An introduction to convolutional neural networks.arXiv preprint arXiv:1511.08458, 2015.
    36. Jyoti Parikh and Vibhooti Shukla. Urbanization, energy use and greenhouse effects in economic development: Results from a cross-national study of developing countries. Global environmental change, 5(2):87–103, 1995.
    37. Jorge E Patino and Juan C Duque. A review of regional science applications of satel- lite remote sensing in urban settings. Computers, Environment and Urban Systems, 37:1–17, 2013.
    38. Phetkeo Poumanyvong and Shinji Kaneko. Does urbanization lead to less energy use and lower co2 emissions? a cross-country analysis. Ecological Economics, 70(2):434–444, 2010.
    39. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real- time object detection with region proposal networks. Advances in neural information processing systems, 28:91–99, 2015.
    40. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015.
    41. Mohammad Salahuddin, Md Idris Ali, Nick Vink, and Jeff Gow. The effects of ur- banization and globalization on co 2 emissions: evidence from the sub-saharan africa (ssa) countries. Environmental Science and Pollution Research, 26:2699–2709, 2019.
    42. Muhammad Shahbaz and Hooi Hooi Lean. Does financial development increase en- ergy consumption? the role of industrialization and urbanization in tunisia. Energy policy, 40:473–479, 2012.
    43. Ling Shan, Yuehua Jiang, Cuicui Liu, Yufei Wang, Guanghong Zhang, Xufeng Cui,
    and Fei Li. Exploring the multi-dimensional coordination relationship between population urbanization and land urbanization based on the mdce model: A case study of the yangtze river economic belt, china. Plos one, 16(6):e0253898, 2021.
    44. Juan Shang, Pengfei Li, Ling Li, and Yong Chen. The relationship between population growth and capital allocation in urbanization. Technological Forecasting and Social Change, 135:249–256, 2018.
    45. Pengfei Sheng, Yaping He, and Xiaohui Guo. The impact of urbanization on energy consumption and efficiency. Energy & Environment, 28(7):673–686, 2017.
    46. Karen Simonyan and Andrew Zisserman. Very deep convolutional networks for large- scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
    47. Ashbindu Singh. Review article digital change detection techniques using remotely- sensed data. International journal of remote sensing, 10(6):989–1003, 1989.
    48. Andre Sorensen and Junichiro Okata. Megacities: urban form, governance, and sus- tainability, volume 10. Springer Science & Business Media, 2010.
    49. Minghong Tan. Urban growth and rural transition in china based on dmsp/ols night- time light data. Sustainability, 7(7):8768–8781, 2015.
    50. Michael P Todaro. Urbanization, unemployment and migration in africa: Theory and policy. 1997.
    51. Adam Van Etten and Daniel Hogan. The spacenet multi-temporal urban development challenge. arXiv preprint arXiv:2102.11958, 2021.
    52. Adam Van Etten, Daniel Hogan, Jesus Martinez Manso, Jacob Shermeyer, Nicholas Weir, and Ryan Lewis. The multi-temporal urban development spacenet dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion, pages 6398–6407, 2021.
    53. Qiang Wang, Yue-e Zeng, Bo-wei Wu, et al. Exploring the relationship between urbanization, energy consumption, and co2 emissions in different provinces of china. Renewable and sustainable energy reviews, 54:1563–1579, 2016.
    54. Xin-Rui Wang, Eddie Chi-Man Hui, and Jiu-Xia Sun. Population migration, urban- ization and housing prices: Evidence from the cities in china. Habitat International, 66:49–56, 2017.
    55. Thilo Wellmann, Angela Lausch, Erik Andersson, Sonja Knapp, Chiara Cortinovis, Jessica Jache, Sebastian Scheuer, Peleg Kremer, Andre´ Mascarenhas, Roland Krae- mer, et al. Remote sensing in urban planning: Contributions towards ecologically sound policies? Landscape and Urban Planning, 204:103921, 2020.
    56. Qihao Weng. Techniques and methods in urban remote sensing. John Wiley & Sons, 2019.
    57. Yuxin Wu, Alexander Kirillov, Francisco Massa, Wan-Yen Lo, and Ross Girshick.Detectron2.https://github.com/facebookresearch/detectron2, 2019.
    58. Saining Xie, Ross Girshick, Piotr Dolla´r, Zhuowen Tu, and Kaiming He. Aggre- gated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1492–1500, 2017.
    59. Aston Zhang, Zachary C Lipton, Mu Li, and Alexander J Smola. Dive into deep learning. arXiv preprint arXiv:2106.11342, 2021.
    60. Hanqin Qiu Zhang, Jian Ming Luo, Qu Xiao, and Basak Denizci Guillet. The impact of urbanization on hotel development: Evidence from guangdong province in china. International Journal of Hospitality Management, 34:92–98, 2013.
    61. Min Zhao, Yuyu Zhou, Xuecao Li, Wenting Cao, Chunyang He, Bailang Yu, Xi Li, Christopher D Elvidge, Weiming Cheng, and Chenghu Zhou. Applications of satellite remote sensing of nighttime light observations: Advances, challenges, and perspec- tives. Remote Sensing, 11(17):1971, 2019.
    62. Naijun Zhou, Klaus Hubacek, and Mark Roberts. Analysis of spatial patterns of urban growth across south asia using dmsp-ols nighttime lights data. Applied Geography, 63:292–303, 2015.

    QR CODE