應用深度學習方法進行UAV影像植被區分類之研究

THE STUDY OF APPLYING DEEP LEARNING TO VEGETATION CLASSIFICATION USING UAV IMAGES

10.6652/JoCICHE.201910_31(6).0006

林迪詒(Di-Yi Lin)；謝嘉聲(Chia-Sheng Hsieh)；翁綺君(Chi-Chun Weng)

深度學習 ； UAV影像 ； 植被區 ； deep learning ； UAV images ； vegetation area

中國土木水利工程學刊

31卷6期（2019 / 10 / 01）

579 - 588

繁體中文

UAV影像具有高機動性、高解析度之優點，被廣泛應用到許多領域，但拍攝的過程易受到環境影響，因此在進行影像處理時需考量UAV影像圖幅小、影像數量多、傾斜之特點，且UAV影像中常會拍攝到大量的植被，因植被分佈不均和易受時空環境影響具高度變動性，易造成影像匹配錯誤、遮蔽地物等問題，導致植被區產生較大的誤差，因此利用分類方法將植被區框選剔除，可獲得高精度之數值地表模型進行應用。由於近年來熱門發展的深度學習技術具有優越的分類效果，因此本研究嘗試以深度學習方法中Mask-RCNN演算法進行影像分類之探討，但該演算法對於影像邊界處容易因資訊不完整而分類錯誤，因此本研究提出重疊切割正射影像方法，避免影像邊界分類錯誤之問題，另因研究區植被種類與網路常用之公開樣本訓練集有所不同，在此利用遷移學習方法解決研究區少量樣本集的問題。利用本研究所提出的研究流程，經實驗成果顯示整體分類精度提高至96%，能有效框選出植被區。

The advantages of capturing images by UAV are high maneuverability and high resolution. Therefore, this technique is widely used in many fields. However, the process of taking pictures is susceptible to environmental influences, so that it is necessary to consider the characteristics of small view frames, large number of images, and oblique shooting when performing image processing. In addition, UAV imagery often captures a lot of vegetation. However, vegetation has non-uniform distribution and high variability that is susceptible to space-time environment, which may cause problems such as image matching errors and shielding of ground objects. It causes a large error in the vegetation area. Therefore, using the classification method to remove the vegetation area, it can obtain the high-precision numerical surface model to do more application. In recent years, the deep learning technology have the superior classification effect, this study attempts to explore the image classification by the Mask-RCNN algorithm in the deep learning method. However, this algorithm is easy to classify wrongly near image border due to incomplete information. Therefore, this study proposes an overlapped orthophotos method to avoid the problem. And, the vegetation types in the study area are different from the public sample training sets in the network. Here the transfer learning method is used to solve the problem of a small sample set in this study area. Using the process proposed by this research, the experimental results show that the overall classification accuracy is improved to 96%, and the vegetation area can be effectively selected.

1. 林彥廷,張喆,陳思恩,李豐佐,賴進松,韓仁毓(2018)。應用 UAV 影像於河岸基腳保護工辨識之研究。土木水利，45(3)，13-22。
   連結：
2. ImageNet: http://www.image-net.org/.
3. MS COCO: http://cocodataset.org/.
4. Cheng, G.,Han, J.,Lu, X.(2017).Remote sensing image scene classification: benchmark and state of the art.Proceedings of the IEEE
5. Cleve, C.,Kelly, M.,Kearns, F. R.,Moritz, M.(2008).Classification of the wildland– urban interface: a comparison of pixel-and object-based classifications using high-resolution aerial photography.Computers, Environment and Urban Systems,32,317-326.
6. Cook, Kristen L.(2017).An evaluation of the effectiveness of low-cost UAVs and structure from motion for geomorphic change detection.Geomorphology,278,195-208.
7. Donahue, J.,Jia, Y.,Vinyals, O.,Hoffman, J.,Zhang, N.,Tzeng, E.,Darrell, T.(2013).,未出版
8. Felzenszwalb, P. F.,Huttenlocher, D. P.(2004).Efficient graph-based image segmentation.International Journal of Computer Vision,59(2),167-181.
9. Fu, B.,Wang, Y.,Campbell, A.,Li, Y.,Zhang, B.,Yin, S.,Xing, Z.,Jin, X.(2017).Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data.Ecological Indicators,73,105-117.
10. Girshick, R.(2015).Fast R-CNN.Proceedings of the IEEE International Conference on Computer Vision
11. Gruszczyński, W.,Matwij, W.,Ćwiąkała, P.(2017).Comparison of low-altitude UAV photogrammetry with terrestrial laser scanning as data-source methods for terrain covered in low vegetation.ISPRS Journal of Photogrammetry and Remote Sensing,126,168-179.
12. He, K.,Gkioxari, G.,Dollár, P.,Girshick, R(2017).Mask R-CN.2017 IEEE International Conference
13. LeCun, Y.,Bengio, Y.,Hinton, G.(2015).Deep learning.Nature,521,436-444.
14. Liu, T.,Abd-Elrahman, A.,Jon, M.,Wilhelm, V. L.(2018).Comparing fully convolutional networks, random forest, support vector machine, and patch based deep convolutional neural networks for object-based wetland mapping using images from small unmanned aircraft system.GIScience & Remote Sens,55(2),243-264.
15. Long, J.,Shelhamer, E.,Darrell, T.(2015).Fully convolutional networks for semantic segmentation.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
16. Lu, B.,He, Y.(2017).Species classification using Unmanned Aerial Vehicle (UAV) - acquired high spatial resolution imagery in a heterogeneous grassland.ISPRS Journal of Photogrammetry and Remote Sensing,128,73-85.
17. Ma, X.,Wang, H.,Wang, J.(2016).Semisupervised classification for hyperspectral image based on multi-decision labeling and deep feature learning.ISPRS Journal of Photogrammetry and Remote Sensing,120,99-107.
18. Makantasis, K.,Karantzalos, K.,Doulamis, A.,Doulamis, N.(2015).Deep supervised learning for hyperspectral data classification through convolutional neural networks.Geoscience and Remote Sensing Symposium (IGARSS), 2015 IEEE International
19. Turner, D.,Lucieer, A.,De Jong, S. M.(2015).Time series analysis of landslide dynamics using an unmanned aerial vehicle (UAV).Remote Sensing,7(2),1736-1757.
20. Vasuki, Y.,Holden, E. J.,Kovesi, P.,Micklethwaite, S.(2014).Semi-automatic mapping of geological Structures using UAV-based photogrammetric data: An image analysis approach.Computers & Geosciences,69,22-32.
21. Xun, L.,Wang, L.(2015).An object-based SVM method incorporating optimal segmentation scale estimation using Bhattacharyya Distance for mapping salt cedar (Tamarisk spp.) with QuickBird imagery.GIScience & Remote Sensing,52(3),257-273.
22. Zhang, P.,Gong, M.,Su, L.,Liu, J.,Li, Z.(2016).Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images.ISPRS Journal of Photogrammetry and Remote Sensing,116,24-41.
23. Zhao, W.,Du, S.(2016).Learning multiscale and deep representations for classifying remotely sensed imagery.ISPRS Journal of Photogrammetry and Remote Sensing,113,155-165.
24. 吳信賢(2018)。臺北，國立政治大學資訊科學系。
25. 施介嵐(2003)。國立交通大學土木工程所。
26. 翁婕晞(2013)。臺北，國立台北大學不動產與城鄉環境學系。
27. 廖家玄,黃郁庭,沈子恩,林迪詒,謝嘉聲。利用 UAV影像結合大地資料監測柴山部落變動量。第三十六屆測量及空間資訊研討會，台南:
28. 賴念翔(2018)。臺中，國立中興大學資訊管理學系。

1. 陳首騎,馬國宸,林文苑(2023)。運用熱顯像無人機分析埤塘種電前後蒸發量變化之研究。中國土木水利工程學刊，35(6)，587-593。