• Українська
  • English
  • Русский
ISSN 2415-3400 (Online)
ISSN 1028-821X (Print)

PROCESSING A MONOCHROMATIC EARTH OBSERVATION IMAGE FOR BUILDINGS DETECTION

Gorobets, AN
Organization: 

V. N. Karazin Kharkiv National University
4 Svobody Sq., Kharkiv, 61022, Ukraine
E-mail: alex.n.gorobets@gmail.com

https://doi.org/10.15407/rej2017.04.011
Language: Russian
Abstract: 

The purpose of this work is to develop a new technique of image processing, in particular for buildings detection on monochromatic Earth-observation images of different types.
The method is based on the property of most man-made objects which consists in straight edges and mostly right angles. Representing an image separately as gradient value- and direction-layers allows to detect targets in both cases: a bright object on a dark background and a dark one on a light background. The developed 2D adaptive image filter allows to detect straight edges even if the given image fragment has a low contrast and is extremely noised. The next processing of line-segment list without image raster works faster and allows to detect a small set of possible targets.
The developed algorithm forms a limited set of objects which shape is close to anthropogenic by processing the original image.
The proposed method can be used as an image segmentation algorithm for formation of hypotheses and subsequent recognition using neural networks. The method is also useful as a means for automating and improving the efficiency of training dataset images preparing by an operator for a neural network, and thereby as optimizing this process.

Keywords: adaptive filter, Earth observation, image processing, straight lines finding

Manuscript submitted 18.10.2017
PACS 07.05.Pj
Radiofiz. elektron. 2017, 22(4): 11-18
Full text (PDF)

References: 
  1. Pashchenko, R. E. ed., 2006. Fractal analysis of processes, structures and signals. Kharkiv: EcoPerspectiva Publ. (in Russian).
  2. Woo, D.-M., Nguyen, Q.-D., Nguyen Tran, Q.-D., Park, D.-C., Jung, Y.-K., 2006. Building detection and reconstruction from aerial images. In: Proc. Int. Soc. for Photogrammetry and Remote Sensing (ISPRS). Beijing, China, July 3–11, 2008.
  3. Konstantinidis, D., Stathaki, T., Argyriou, V. and Grammalidis, N., 2015. A probabilistic feature fusion for building detection in satellite images. In: Proc. 10th Int. Conf. on Computer Vision Theory and Applications (VISAPP 2015). Vol. 2. Berlin, Germany, 11–14 March, 2015, pp. 205–212. SciTePress. DOI: https://doi.org/10.5220/0005260502050212
  4. Sirmacek, B. and Unsalan, C., 2009. Urban-area and building detection using SIFT keypoints and graph theory. IEEE Trans. Geosci. Remote Sens., 47(4), pp. 1156–1167.DOI: https://doi.org/10.1109/TGRS.2008.2008440
  5.  Singh, D., Maurya, R., Shukla, A., Sharma, M. and Gupta, P., 2012. Building extraction from very high resolution multispectral images using NDVI based segmentation and morphological operators. In: 2012 Students Conf. Engineering and Systems. Allahabad, Uttar Pradesh, India, 16–18 March 2012, pp. 1–5. DOI: https://doi.org/10.1109/SCES.2012.6199034
  6.  Hermosilla, T., Ruiz, L., Recio, J. and Estornell, J., 2011. Evaluation of automatic building detection approaches combining high resolution images and LiDAR data. Remote Sens., 3(6), pp. 1188–1210. DOI:https://doi.org/10.3390/rs3061188
  7. Theng L. B., 2006. Automatic building extraction from satellite imagery. [pdf] Eng. Lett., 13(3), 5 p. Aviable at: http://www.engineeringletters.com/issues_v13/issue_3/EL_13_3_5.pdf.
  8. Kahn, P., Kitchen, L., Riseman, E., 1990. Fast Line Finder for Vision-Guided Robot Navigation. IEEE Trans. Pattern Anal. Mach. Intell., 12(11), pp. 1098–1102. DOI: https://doi.org/10.1109/34.61710
  9. Haverkamp, D., 2004. Automatic building extraction from IKONOS imagery. In: Proc. ASPRS Annual Conf. Denver, CO, USA, 23–28 May 2004.
  10. Konstantinidis, D., Stathaki, T., Argyriou, V., Grammalidis, N., 2017. Building Detection Using Enhanced HOG–LBP Features and Region Refinement Processes. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., 10(3), pp. 888–905. DOI: https://doi.org/10.1109/RAST.2013.6581176
  11. Competitions data analysis [on-line]. Available at: http://dataring.ru/competitions/fpi-object-detection/ (in Russian).
  12. Hough, P., 1962. Method and means for recognizing complex patterns. U. S. Pat. 3,069,654.
  13. Canny, J., 1986. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell., PAMI-8(6), pp. 679–698. DOI: https://doi.org/10.1109/TPAMI.1986.4767851