應用全卷積網路於遙測影像偵測都市地區之建築物與道路

Apply Fully Convolutional Network to Detect Buildings and Roads in Urban Areas from Remote Sensing Images

10.6161/jgs.202304_(104).0003

范慶龍(Ching-Lung Fan)

深度學習 ； UAV影像 ； 衛星影像 ； 建築物 ； 道路 ； deep learning ； UAV image ； satellite image ； buildings ； roads

地理學報

104期（2023 / 04 / 01）

35 - 51

繁體中文;英文

都市地區的土地利用圖是提供整體都市規劃與管理的重要空間資訊。儘管已經開發許多從遙測影像中來萃取都市土地利用的分類方法，但是這些傳統方法受限於不同影像的解析度，以及分類的準確性與效率，不足以滿足現實世界中的應用需求。近年來，深度學習的分類方法興起，已經在影像辨識中達到相當高的性能水準。因此，本研究使用基於深度學習之全卷積網路（Fully Convolutional Network, FCN），從無人飛行載具（Unmanned Aerial Vehicles, UAV）和衛星所取得不同解析度之RGB影像中，萃取都市地區（高雄市鳳山區）之建築物及道路。基於FCN的架構重新設計網路層數與結構，並進行各種超參數的調整與測試，將其學習到的特徵轉換至分割任務。本研究所建構FCN模型之學習誤差小於0.073，且無產生過擬合現象。實驗結果顯示，該模型對於UAV影像或衛星影像之整體準確度（overall accuracy, OA）均高於97%以上，可以有效提供都市地區地圖更新之參考。

The Land-use maps of urban areas present important spatial information that informs urban planning and management. Although many classification methods for remote sensing images have been developed to derive land-use information in urban areas, traditional methods are limited by image resolution, and in many cases, the accuracy and efficiency of legacy classification processes are not sufficient for real-world requirements. Recently, deep learning classification methods have emerged and improved, attaining a high level of performance in image recognition. This study employs those advances, adopting a fully convolutional network (FCN) based on deep learning to extract buildings and roads in the selected area (Fengshan District, Kaohsiung). This application uses RGB images of different resolutions obtained from Unmanned Aerial Vehicles (UAVs) and satellites. The FCN-based architecture revises the number and structure of network layers and performs various hyperparameter tuning and testing to translate learned features into segmentation tasks. The learning error of the FCN model constructed in this study is less than 0.073, and there is no overfitting phenomenon. The experimental results show that the overall accuracy (OA) of the model for UAV images and satellite images is higher than 97%, which can effectively provide a reference for updating maps in urban areas.

1. 張家豪,朱子豪,劉英毓(2005)。應用高解像力遙測影像於台北市建物屋頂加蓋物之監測。臺灣地理資訊學刊，3，15-26。
   連結：
2. 陳偉文,卓柏漢,林莉珊(2020)。火龍果與荔枝航照影像判釋－運用卷積神經網路影像辨識技術與作物特徵萃取分類演算法。航測及遙測學刊，25(1)，25-38。
   連結：
3. 羅正方,劉正倫,李良輝,陳信安,張庭榮,林昌鑑,施錦揮(2018)。無人機傾斜攝影於三維都市模型重建之應用。航測及遙測學刊，23(2)，127-140。
   連結：
4. Chen, J.,Zhou, Y.,Zipf, A.,Fan, H.(2019).Deep learning from multiple crowds: A case study of humanitarian mapping.IEEE Transactions on Geoscience and Remote Sensing,57(3),1713-1722.
5. Deshpande, A. 2016. About A Beginner's Guide to Understanding Convolutional Neural Networks. https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks (last accessed 30 September 2022).
6. Feng, Q.,Liu, J.,Gong, J.(2015).UAV remote sensing for urban vegetation mapping using random forest and texture analysis.Remote Sensing,7(1),1074-1094.
7. Gibril, M. B. A.,Shafri, H. Z. M.,Hamedianfar, A.(2017).New semi-automated mapping of asbestos cement roofs using rule-based object-based image analysis and Taguchi optimization technique from WorldView-2 images.International Journal of Remote Sensing,38(2),467-491.
8. Gómez-Chova, L.,Tuia, D.,Moser, G.,Camps-Valls, G.(2015).Multimodal classification of remote sensing images: A review and future directions.Proceedings of the IEEE,103(9),1560-1584.
9. Gonzalez, R. C.,Woods, R. E.(2008).Digital image processing.New Jersey:Prentice Hall.
10. Guo, L.,Chehata, N.,Mallet, C.,Boukir, S.(2011).Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests.ISPRS Journal of Photogrammetry and Remote Sensing,66(1),56-66.
11. Huang, B.,Zhao, B.,Song, Y.(2018).Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery.Remote Sensing of Environment,214,73-86.
12. La, H. P.,Eo, Y. D.,Chang, A.,Kim, C.(2015).Extraction of individual tree crown using hyperspectral image and LiDAR data.KSCE Journal of Civil Engineering,19(4),1078-1087.
13. Leichtle, T.,Geiß, C.,Wurm, M.,Lakes, T.,Taubenböck, H.(2017).Unsupervised change detection in VHR remote sensing imagery - an object-based clustering approach in a dynamic urban environment.International Journal of Applied Earth Observation and Geoinformation,54,15-27.
14. Lillesand, T. M.,Kiefer, R. W.(2000).Remote sensing and image interpretation.New York:John Wiley & Sons.
15. Liu, W.,Yang, M. Y.,Xie, M.,Guo, Z.,Li, E.,Zhang, L.,Pei, T.,Wang, D.(2019).Accurate building extraction from fused DSM and UAV images using a chain fully convolutional neural network.Remote Sensing,11(24),2912.
16. Long, J.,Shelhamer, E.,Darrell, T.(2015).Fully Convolutional Networks for Semantic Segmentation.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Boston, Massachusetts, USA.:
17. Maboudi, M.,Amini, J.,Hahn, M.,Saati, M.(2017).Object-based road extraction from satellite images using ant colony optimization.International Journal of Remote Sensing,38(1),179-198.
18. Majd, R. D.,Momeni, M.,Moallem, P.(2019).Transferable object-based framework based on deep Convolutional Neural Networks for building extraction.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,12(8),2627-2635.
19. Sharma, A.,Liu, X.,Yang, X.,Shi, D.(2017).A patch-based convolutional neural network for remote sensing image classification.Neural Networks,95,19-28.
20. Westoby, M. J.,Brasington, J.,Glasser, N. F.,Hambrey, M. J.,Reynolds, J. M.(2012).Structure-from-Motion photogrammetry: A low-cost, effective tool for geoscience applications.Geomorphology,179,300-314.
21. Younis, M. C.,Keedwell, E.(2019).Semantic segmentation on small datasets of satellite images using convolutional neural networks.Journal of Applied Remote Sensing,13(4),046510.
22. Zhang, C.,Sargent, I.,Pan, X.,Li, H.,Gardiner, A.,Hare, J.,Atkinson, P. M.(2019).Joint Deep Learning for land cover and land use classification.Remote Sensing of Environment,221,173-187.
23. Zhang, L.,Huang, X.,Huang, B.,Li, P.(2006).A pixel shape index coupled with spectral information for classification of high spatial resolution remotely sensed imagery.IEEE Transactions on Geoscience and Remote Sensing,44(10),2950-2961.
24. 陳韻安,饒見有(2017)。應用空載傾斜攝影密匹配點雲於建物變遷分析。航測及遙測學刊，23(3)，205-26。