Comparative Study on Detection and Classification Approaches on Man-Made Objects from Satellite Images
DOI:
https://doi.org/10.26438/ijcse/v6i10.835844Keywords:
Building Extraction, Vegetation, Non-Vegetation, Wavelet Shrinkage, FCM, K-Means, ABC, LBP, KNN, SVM, ELMAbstract
Automatic extraction of buildings and change detection of buildings from satellite images is an important tool for city management and planning. The discovery of changes is the process of identifying differences in the state of the objects extracted from the remote image by observing different time periods. The main objective of this paper is to extract the manmade objects (buildings) from the given input satellite images and detect the changes in the extracted building map. This work presents the Region of Interest (ROI) and extraction of the building using K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and Extreme Learning Machine (ELM) techniques. Initially, the input satellite image is de-noised by using the Wavelet Shrinkage de-noising approach. Then the K-Means, Fuzzy C-Means (FCM) and Artificial Bee Colony (ABC) approaches are applied to the de-noised image to segment the vegetation and non-vegetation areas and then extract the features using Local Binary Pattern (LBP) Technique. Finally, the extracted features are given to the KNN, SVM and ELM classifier to get the building map and then the change detection process is applied. In this paper, the comparison is made on three clustering approaches and three classifier approaches to find the best approach for manmade object extraction. From the experimental result, it is shown that the ABC approach performs better than K-Means and FCM in clustering and ELM provides the best result than the KNN and SVM in classifiers
References
[1] L. Theng, “Automatic building extraction from satellite imagery,” Eng. Lett., vol. 13, no. 3, pp. 1–5, Nov. 2006.
[2] K. Karantzalos and D. Argialas, “A region-based level set segmentation for automatic detection of man-made objects from aerial and satellite images,” Photogramm. Eng. Remote Sens., vol. 75, no. 6, pp. 667–677, 2009.
[3] D. Singh, R. Maurya, A. Shukla, M. Sharma, and P. Gupta, “Building extraction from very high resolution multispectral images using NDVI based segmentation and morphological operators,” in Proc. Students Conf. Eng. Syst., Mar. 2012, pp. 1–5.
[4] T. Hermosilla, L. Ruiz, J. Recio, and J. Estornell, “Evaluation of automatic building detection approaches combining high resolution images and LiDAR data,” Remote Sens., vol. 3, no. 6, pp. 1188–1210, 2011.
[5] B. Sirmacek and C. Unsalan, “Urban-area and building detection using SIFT keypoints and graph theory,” IEEE Trans. Geosci. Remote Sens., vol. 47, no. 4, pp. 1156–1167, Apr. 2009.
[6] B. Sirmacek and C. Unsalan, “A probabilistic framework to detect buildings in aerial and satellite images,” IEEE Trans. Geosci. Remote Sens., vol. 49, no. 1, pp. 211–221, Jan. 2011.
[7] P. Hough, “Method and means for recognizing complex patterns,” U.S. Patent 3 069 654, Dec. 18, 1962.
[8] T. Kim and J. Muller, “Development of a graph-based approach for building detection,” Image Vision Comput., vol. 17, no. 1, pp. 3–14, 1999.
[9] D. Haverkamp, “Automatic building extraction from IKONOS imagery,” in Proc. Amer. Soc. Photo Remote Sens., 2004, pp. 23–28.
[10] D. Woo, Q. Nguyen, Q. N. Tran, D. Park, and Y. Jung, “Building detection and reconstruction from aerial images,” in Proc. Int. Soc. Photogramm. Remote Sens. Congr., Beijing, China, 2008, pp. 713–718.
[11] S. Vinson, L. Cohen, and F. Perlant, “Extraction of rectangular buildings in aerial images,” in Proc. Scand. Conf. Image Anal., 2001.
[12] K. Karantzalos and N. Paragios, “Recognition-driven two-dimensional competing priors toward automatic and accurate building detection,” IEEE Trans. Geosci. Remote Sens., vol. 47, no. 1, pp. 133–144, Jan. 2009.
[13] O. Benarchid et al., “Building extraction using object-based classification and shadow information in very high resolution multispectral images, a case study: Tetuan, Morocco,” Can. J. Image Process. Comput. Vision, vol. 4, no. 1, pp. 1–8, Jan. 2013.
[14] S. Kluckner and H. Bischof, “Image-based building classification and 3d modeling with super-pixels,” in Proc. Int. Soc. Photogramm. Remote Sens. Photogramm. Comput. Vis. Image Anal., 2010, pp. 291–296.
[15] A. Shackelford and C. Davis, “A combined fuzzy pixel-based and objectbased approach for classification of high-resolution multispectral data over urban areas,” IEEE Trans. Geosci. Remote Sens., vol. 41, no. 10, pp. 2354–2363, Oct. 2003.
[16] Z. Sheng-hua, H. Jian-jun, and X. Wei-xin, “A new method of building detection from a single aerial photograph,” in Proc. 9th Int. Conf. Signal Process., Oct. 2008, pp. 1219–1222.
[17] C. Senaras, M. Ozay, and F. T. Y. Vural, “Building detection with decision fusion,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 6, no. 3, pp. 1295–1304, Jun. 2013.
[18] D. Chai, W. Forstner, and M. Y. Yang, “Combine Markov random fields ¨ and marked point processes to extract building from remotely sensed images,” in Proc. ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., 2012, pp. 1219–1222.
[19] O. ¨ O. Karada ¨ g, C. Senaras, and F. T. Y. Vural, “Segmentation fusion for ˘ building detection using domain-specific information,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 8, no. 7, pp. 3305–3315, Jul. 2015.
[20] J. Femiani, E. Li, A. Razdan, and P. Wonka, “Shadow-based rooftop segmentation in visible band images,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 8, no. 5, pp. 2063–2077, May 2015.
[21] D. Konstantinidis, T. Stathaki, V. Argyriou, and N. Grammalidis, “A probabilistic feature fusion for building detection in satellite images,” in Proc. 10th Int. Conf. Comput. Vision Theory Appl., 2015, pp. 205–212.
[22] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE Conf. Comput. Vision Pattern Recognit., Jun. 2005, vol. 1, pp. 886–893.
[23] T. Ojala, M. Pietikainen, and D. Harwood, “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions,” in Proc. Int. Conf. Pattern Recognit., Oct. 1994, vol. 1, pp. 582–585.
[24] T. Ojala, M. Pietikainen, and D. Harwood, “A comparative study of texture measures with classification based on featured distributions,” Pattern Recognit., vol. 29, no. 1, pp. 51–59, Jan. 1996.
[25] X. Wang, T. Han, and S. Yan, “An HOG-LBP human detector with partial occlusion handling,” in Proc. Int. Conf. Comput. Vision, Sep. 2009, pp. 32–39.
[26] J. Zhang, K. Huang, Y. Yu, and T. Tan, “Boosted local structured HOGLBP for object localization,” in Proc. Int. Conf. Comput. Vision Pattern Recognit., Jun. 2011, pp. 1393–1400.
[27] A. Fitch, A. Kadyrov, W. Christmas, and J. Kittler, “Fast robust correlation,” IEEE Trans. Image Process., vol. 14, no. 8, pp. 1063–1073, Aug. 2005.
[28] A. Dempster, N. Laird, and D. Rubin, “Maximum likelihood from incomplete data via the EM algorithm,” J. Roy. Statist. Soc. B, vol. 39, no. 1, pp. 1–38, 1977.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
