Document Type : Research Paper

Authors

1 M.Sc., Student, Department of Remote Sensing and Geographic Information Systems, Kharazmi University, Tehran, Iran

2 Associate Professor, Department of Remote Sensing and Geographic Information Systems, Kharazmi University, Tehran, Iran

3 Assistant Professor, Department of Remote Sensing and Geographic Information Systems, Kharazmi University, Tehran, Iran

Abstract

Deep learning is a modern method of image processing and data analysis that has entered the field of urban management with promising results and high potential. The purpose of this study is to investigate data augmentation techniques in improving the results of segmentation of building using aerial images with high spatial resolution and deep learning method. For this purpose, MSB building data set and MapNet model were used. The model was trained and evaluated in three stages without data augmentation, with data augmentation of geometric transformations and with data augmentation of geometric and photometric transformations. The results of model evaluation showed that using geometric transformations as data enhancement techniques, F-1 and IoU score evaluation criteria have increased by 0.5 and 0.55%, respectively, and using data techniques Incremental geometric and photometric transformations increased by 1.41 and 1.57 percent. This increase was visually observed in the improvement of the segmentation of dense areas of the building and the discontinuity of large-scale buildings.

Keywords

Main Subjects

  1. Boonpooki, Y. Tan, and B. Xu. 2020."Deep learning-based multi-feature semantic segmentation in building extraction from images of UAV photogrammetry". International Journal of Remote Sensing. DOI 10.1080/01431161.2020.1788742.
  2. Zhu, Qing, C. Liao, H. Hu, X. Mei, and H. Li."MAP-Net: Multiple Attending Path Neural Network for Building Footprint Extraction from Remote Sensed Imagery". IEEE Transactions ongeoscience and remote sensing. https://arxiv.org/abs/1910.12060.
  3. Jianli, D. Chen, R. Wang, J. Peethambaran, P. T. Mathiopoulos, L. Xie, and T. Yun, “A novel framework for 2.5-d building contouring from large-scale residential scenes,” IEEE Transactions on Geoscience and Remote Sensing, vol. 57, no. 6, p.p. 4121–4145, 2019.
  4. Z hongbin, W. Shi, Q. Wang, and Z. Miao, “Extracting man-made objects from high spatial resolution remote sensing images via fast level set evolutions,” IEEE Transactions on Geoscience and  Remote  Sensing, vol. 53, no. 2, p.p. 883–899, 2014.
  5. Nitin. L, and S. K. Ghosh, “Automatic building footprint extraction from high-resolution satellite image using mathematical morphology,” European Journal of Remote Sensing, vol. 51, no. 1, p.p. 182–193, 2018.
  6. J-P. Burochin, B. Vallet, M. Br´edif, C. Mallet, T. Brosset, and N. Paparoditis, “Detecting blind building fac¸ades from highly overlapping wide angle aerial imagery,” ISPRS journal of photogrammetry and remote sensing, 96, p.p. 193–209, 2014.
  7. Cote and P. Saeedi, “Automatic rooftop extraction in nadir aerial imagery of suburban regions using corners and variational level set evolution,” IEEE transactions on geoscience and remote sensing, vol. 51, no. 1, p.p. 313–328, 2012.
  8. Awrangjeb, C. Zhang, and C. S. Fraser, “Automatic extraction of building roofs using LIDAR data and multispectral imagery,” ISPR journal of photogrammetry and remote sensing, vol. 83, p.p. 1–18, 2013.
  9. Shouji, Y. Zhang, Z. Zou, S. Xu, X. He, and S. Chen, “Automatic building extraction from LIDAR data fusion of point and grid-based features,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 130, p.p. 294–307, 2017.
  10. A. N. Gilani, M. Awrangjeb, and G. Lu, “An automatic building extraction and regularisation technique using lidar point cloud data and orthoimage,” Remote Sensing, vol. 8, no. 3, p.p. 258, 2016.
  11. Gunho, and I. Dowman, “Data fusion of igh-resolution satellite imagery and LIDAR data for automatic building extraction,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 62, no. 1, p.p. 43–63, 2007.
  12. Simonetto, H. Oriot, and R. Garello, “Rectangular building extraction from stereoscopic airborne radar images,” IEEE Transactions on Geoscience and remote Sensing, vol. 43, no. 10, p.p. 2386–2395, 2005.
  13. Chawda, J. Aghav. and S. Udar, "Extracting building footprints from satellite images using convolutional neural networks," In 2018 International Conference on Advances in Computing, Communications and Informatics(ICACCI), IEEE, p.p. 572-577, 2018.
  14. Bi, et al, “A multi-scale filtering building index for building extraction in very high-resolution satellite imagery,” Remote Sensing, vol.11, no. 5, p. 482, 2019.
  15. Cai, H. Ma, and L. Zhang, “A building detection method based on semi-suppressed fuzzy C-means and restricted region growing using airborne LiDAR,” Remote Sensing, vol. 11, no.7, p.p. 848, 2019.
  16. Rottensteiner, et al., “Building detection by fusion of airborne laser scanner data and multi-spectral images: Performance evaluation and sensitivity analysis,” ISPRS J. Photogrammetry and Remote Sensing, vol. 62, no. 2, p.p. 135–149, 2007.
  17. T. Vu, F. Yamazaki, and M. Matsuoka, “Multi-scale solution for building extraction from LiDAR and image data,” International Journal of Applied Earth Observation and Geoinformation, vol. 11, no. 4, p.p. 281–289 , 2009.
  18. Khoshboresh-Masouleh, F. Alidoost, and H. Arefi. "Multiscale building segmentation based on deep learning for remote sensing RGB images from different sensors," Journal of Applied Remote Sensing, vol. 14, no. 3 ,2020.
  19. C. Shorten and T. Khoshgoftaar, "A survey on Image Data Augmentation for Deep Learning," Jornal of Big Data, vol. 6, no.1, p.p 1-48, 2019, DIO 10.1186/s40537-019-0197-0.
  20. Chartock, L. Whitney, V. Singh, "Extraction of Building Footprints from Satellite Imagery". Stanford University Report, 2017.
  21. Muruganandham, "Semantic Segmentation of Satellite Images using Deep Learning". Space Engineering, masters level. Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, 2016.
  22. Patterson, and A. Gibson, "Deep Learning, A Pr Actitioner's Approach", O’Reilly Media, Inc., 1005 Gravenstein Highway North, Sebastopol, CA 95472. 532 pages. http://oreilly.com/safari
  23. T. Lindeberg, “Scale-space theory: a basic tool for analyzing structures at different scales,” Journal of applied statistics, vol. 21, no. 1-2, p.p 225-270,1994.