(44-6) 12 * << * >> * Russian * English * Content * All Issues

Building detection by local region features in SAR images
S.P. Ye 1,2, C.X. Chen 1, A. Nedzved 3, J. Jiang 1,4

College of Information Science and Technology, Zhejiang Shuren University, Zhejiang, China,
School of Earth Sciences, Zhejiang University, Zhejiang, China,
Department of Computer Applications and Systems, Belarusian State University, Minsk, Belarus,
College of Information Science and Electronic Engineering, Zhejiang University, Zhejiang, China

 PDF, 3111 kB

DOI: 10.18287/2412-6179-CO-703

Pages: 944-950.

Full text of article: English language.

The buildings are very complex for detection on SAR images, where the basic features of those are shadows. There are many different representations for SAR shadow. As result it is no possible to use convolutional neural network for building detection directly. In this article we give property analysis of SAR shadows of different type buildings. After that, each region (ROI) prepared for training of building detection is corrected with its own SAR shadow properties. Reconstructions of ROI will be put in a modified YOLO network for building detection with better quality result.

SAR images, building detection, YOLO network.

Ye SP, Chen CX, Nedzved A, Jiang J. Building detection by local region features in SAR images. Computer Optics 2020; 44(6): 944-950. DOI: 10.18287/2412-6179-CO-703.

The work was partially funded by Public Welfare Technology Applied Research Program of Zhejiang Province under Grant (No.LGJ18F020001, LGF18F030004, LGJ19F020002, and LGF19F020016), and by National introduction project of senior foreign experts under Grant No.G20200216025. Introduction Project of Zhejiang Province under Grant (No.100), and project of BRFFI F18R-218 "Development and experimental research of descriptive methods for automatization of biomedical images analysis".


  1. Cheng G, Han J. A survey on object detection in optical remote sensing images. ISPRS 2016; 117: 11-28.
  2. Ghaffarian Salar, Ghaffarian Saman. Automatic building detection based on supervised classification using high resolution google earth images. Int Arch Photogramm Remote Sens Spat Inf Sci 2014; 40(3): 101-106. DOI: 10.5194/isprsarchives-XL-3-101-2014.
  3. Zhuo X, Fraundorfer F, Kurz F, Reinartz P. Building detection and segmentation using a CNN with automatically generated training data. 2018 IEEE International Geoscience and Remote Sensing Symposium 2018: 3461-3464. DOI: 10.1109/IGARSS.2018.8518521.
  4. Shahzad M, Maurer M, Fraundorfer F, Wang Y, Zhu X. Buildings detection in VHR SAR images using fully convolution neural networks. IEEE Trans Geosci Remote Sens 2019; 57(2): 1100-1116. DOI: 10.1109/TGRS.2018.2864716.
  5. Kim S, et al. Double weight-based SAR and infrared sensor fusion for automatic ground target recognition with deep learning. Remote Sens 2018; 10: 72.
  6. Canty MJ. Image analysis, classification and change detection in remote sensing. 3rd ed. Boca Raton, London, New York: CRC Press; 2014.
  7. Zhao L, Zhou X, Kuang G. Building detection from urban SAR image using building characteristics and contextual information. EURASIP J Adv Signal Process 2013; 56: 1687-6180. DOI: 10.1186/1687-6180-2013-56.
  8. Zhao J, Guo W, Cui S, Zhang Z, Yu W. Convolutional neural network for SAR image classification at patch level. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2016: 945-948.
  9. Wang Z, Jiang L, Lin L, Yu W. Building height estimation from high resolution SAR imagery via model-based geometrical structure prediction. Prog Electromagn Res M 2015; 41: 11-24.
  10. Manickam S, Bhattacharya A, Singh G, Yamaguchi Y. Estimation of snow surface dielectric constant from polarimetric SAR data. IEEE J Sel Top Appl Earth Obs Remote Sens 2017; 10(1): 211-218. DOI: 10.1109/JSTARS.2016.2588531.
  11. Ferro A, Brunner D, Bruzzone L, Lemoine G. On the relationship between double bounce and the orientation of buildings in VHR SAR images. IEEE Geosci Remote Sens Lett 2011; 8(4): 612-616.
  12. Liu W, Yamazaki F. Building height detection from high-resolution TerraSAR-X imagery and GIS data. CD-ROM. Proc 2013 Joint Urban Remote Sens Event 2013: 33-36.
  13. McNairn H, Shang J. A review of multitemporal synthetic aperture radar (SAR) for crop monitoring. In Book: Ban Y, ed. Multitemporal remote sensing. Methods and applications. Cham: Springer; 2016.
  14. Saatchi S. SAR methods for mapping and monitoring forest biomass. In Book: Flores A, Herndon K, Thapa R, Cherrington E, eds. SAR handbook: Comprehensive methodologies for forest monitoring and biomass estimation. Chap 5. Huntsville, AL: National Space Science and Technology Center; 2019: 207-246.
  15. Allain S, Ferro-Famil L, Pottier E. Surface parameter retrieval from polarimetric and multi-frequency SAR data. Proc IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2003); 2: 1417-1419. DOI: 10.1109/IGARSS.2003.1294128.
  16. Metz CE. Basic principles of ROC analysis. Semin Nucl Med. 1978; 8(4): 283-298.
  17. Powers DMW. Evaluation: From precision, recall and f-measure to ROC, informedness, markedness & correlation. J Mach Learn Technol 2011; 2(1): 37-63.
  18. Bittner K, Cui S, Reinartz P. Building extraction from remote sensing data using fully convolutional networks. ISPRS 2017; XLII-1/W1: 481-486.
  19. Zhao K, Kang J, Jung J, et al. Building extraction from satellite images using mask R-CNN with building boundary regularization. 2018 IEEE/CVF CVPRW 2018: 242-2424. DOI: 10.1109/CVPRW.2018.00045.
  20. Hamaguchi R, Hikosaka S. Building detection from satellite imagery using ensemble of size-specific detectors. 2018 IEEE/CVF CVPRW 2018; 1: 223-2234. DOI: 10.1109/CVPRW.2018.00041.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20