Segmentation for detecting buildings in infrared space images
Keywords:image processing, computer vision, object detection, adaptive filtering, neural networks training
AbstractThe given work describes a new technique of image segmentation, in particular for building detection on radar or infrared Earth-observation images. The method is based on property of most man-made objects which consist in straight edges and mostly right angles. The developed 2D adaptive image filter assists to detect straight edges even if given image fragment has a low contrast and has been extremely noised, in addition, if an object edge has been distorted, for example, by interference in the SAR azimuth channel, the filter compensates for distortions which do not exceed the specified value. The next processing of line-segment list without image raster works faster and allows detecting a relatively small set of possible targets. This approach could be used as addition for neural networks as well as provide assistance in preparing of training data set.
V. Verba, L. Neronsky, I. Osipov, V. Turuk, Radiolokacionnie Systemi Zemleobzora Kosmicheskogo Bazirovaniya [in Russian]. Moscow: Radiotechnika, 2010.
A. Lebedev, N. Gorobets, A. Gorobets, V. Kiyko, V. Kupko, et al. “Raspredelennyie metrologicheskie sredstva dlya ocenki UEPR podstilayuschey poverhnosti,” in Proc. of 10th All-Russian Open Conf. on Sovremennie Problemi Distantsionnogo Zondirovaniya Zemli iz Kosmosa. Fizicheskie Osnovi, Metodi i Tehnologii Monitoringa Okruzhayushey Sredi, Potentsialno Opasnih Yavleniy i Ob'ektov. IKI RAN, November 2012, P. 147.
D.-M. Woo, Q.-D. Nguyen, Q.-D. Tran, D.-C. Park, Y.-K. Jung, “Building detection and reconstruction from aerial images,” Proc. of Int. Conf. on Radar, CIE, Oct. 2006, pp. 713-718.
D. Konstantinidis, T. Stathaki, V. Argyriou, and N. Grammalidis, “A probabilistic feature fusion for building detection in satellite images,” Proc. of 10th Int. Conf. on Computer Vision Theory and Applications, VISIGRAPP2015, pp. 205-212. DOI: http://doi.org/10.5220/0005260502050212.
B. Sirmacek and C. Unsalan, “Urban-area and building detection using SIFT keypoints and graph theory,” IEEE Trans. Geoscience and Remote Sensing, vol. 47, no. 4, pp. 1156-1167, April 2009. DOI: http://doi.org/10.1109/TGRS.2008.2008440.
R. Maurya, P. R. Gupta, A. S. Shukla, M. K. Sharma, “Building extraction from very high resolution multispectral images using NDVI based segmentation and morphological operators,” Proc. of Int. Conf. on Advances in Engineering, Science and Management, ICAESM, 30-31 Mar. 2012, Nagapattinam, Tamil Nadu, India. IEEE, 2012, pp. 1-5. URL: http://ieeexplore.ieee.org/document/6216065/.
T. Hermosilla, L. Ruiz, J. Recio, and J. Estornell, “Evaluation of automatic building detection approaches combining high resolution images and LiDAR data,” Remote Sensing, vol. 3, no. 6, pp. 1188-1210, 2011. DOI: http://doi.org/10.3390/rs3061188.
L. Theng, “Automatic building extraction from satellite imagery,” Engineering Letters, vol. 13, no. 3, Nov. 2006.
D. Haverkamp, “Automatic building extraction from IKONOS imagery,” Proc. of ASPRS, 2004.
D. Konstantinidis, T. Stathaki, V. Argyriou, N. Grammalidis “Building detection using enhanced HOG-LBP features and region refinement processes,” IEEE J. Selected Topics in Applied Earth Observations and Remote Sensing, vol. 10, no. 3, p. 888-905, Mar. 2017. DOI: http://doi.org/10.1109/JSTARS.2016.2602439.
G. Bradski, A Kaehler, Learning OpenCV. Sebastopol: O’Reilly Media, 2008.
J. Canny, “A computational approach to edge detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, p. 679-698, Nov. 1986. DOI: http://doi.org/10.1109/TPAMI.1986.4767851.
P. Hough, “Method and means for recognizing complex patterns,” U.S. Patent 3,069,654, Dec 1962.
P. Kahn, L. Kitchen, E. Riseman “Fast line finder for vision-guided robot navigation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 11, p. 1098-1102, Nov. 1990. DOI: http://doi.org/10.1109/34.61710.