A new method for detecting rooftops in satellite images is presented. The proposed method is based on a combination of machine learning techniques, namely, k-means clustering and support vector machines (SVM). Firstly k-means clustering is used to segment the image into a set of rooftop candidates—these are homogeneous regions in the image which are potentially associated with rooftop areas. Next, the candidates are submitted to a classification stage which determines which amongst them correspond to “true” rooftops. To achieve improved accuracy, a novel two-pass classification process is used. In the first pass, a trained SVM is used in the normal way to distinguish between rooftop and nonrooftop regions. However, this can be a challenging task, resulting in a relatively high rate of misclassification. Hence, the second pass, which we call the “histogram method,” was devised with the aim of detecting rooftops which were missed in the first pass. The performance of the model is assessed both in terms of the percentage of correctly classified candidates as well as the accuracy of the estimated rooftop area. 1. Introduction Automatic rooftop detection from satellite/aerial images is an important task in a variety of applications. Interesting examples include change detection in urban monitoring, the production of digital maps, land use analysis, verification, and updating GIS databases and route planning [1, 2]. For example, accurate identification and localization of rooftops in urban images are a key step in territorial planning and city modeling. Similarly, knowledge of the location, profile, and density of buildings can be very useful in estimating the distribution of a city’s population. In particular, rooftop detection can be used to analyze the size and location of human settlements in slums and other disorganized areas [2]. However, detecting rooftops from aerial or satellite images can be very challenging. One reason is that the images used often differ in terms of lighting conditions, quality, and resolution. Another reason is that buildings may have diverse and complicated shapes and structures and as such can be easily confused with similar objects such as cars, roads, and courtyards. The result of these complications is that there are currently no algorithms or features that are universally applicable, that is, which can be used to detect roofs in all or even a majority of aerial and satellite images. Much of the earlier work on rooftop detection has depended on computer vision and image processing techniques such as edge detection, corner
References
[1]
H. V. Guducu, “Building Detection from Satellite Images Using Shadow and Color Information,” 2008.
[2]
H. G. Ak？ay and S. Aksoy, “Building detection using directional spatial constraints,” in Proceedings of the 30th IEEE International Geoscience and Remote Sensing Symposium (IGARSS '10), pp. 1932–1935, July 2010.
[3]
K. Ren, H. Sun, Q. Jia, and J. Shi, “Building recognition from aerial images combining segmentation and shadow,” in Proceedings of the IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS '09), pp. 578–582, chn, November 2009.
[4]
M. S. Nosrati and P. Saeedi, “A novel approach for polygonal rooftop detection in satellite/aerial imageries,” in Proceedings of the 16th IEEE International Conference on Image Processing (ICIP '09), pp. 1709–1712, November 2009.
[5]
M. Izadi and P. Saeedi, “Automatic building detection in aerial images using a hierarchical feature based image segmentation,” in Proceedings of the 20th International Conference on Pattern Recognition (ICPR '10), pp. 472–475, August 2010.
[6]
D. Comaniciu and P. Meer, “Mean shift: a robust approach toward feature space analysis,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603–619, 2002.
[7]
X. Jin and C. H. Davis, “Automated building extraction from high-resolution satellite imagery in Urban areas using structural, contextual, and spectral information,” EURASIP Journal on Applied Signal Processing, vol. 2005, no. 14, pp. 2196–2206, 2005.
[8]
M. A. Maloof, P. Langley, T. O. Binford, R. Nevatia, and S. Sage, “Improved rooftop detection in aerial images with machine learning,” Machine Learning, vol. 53, no. 1-2, pp. 157–191, 2003.
[9]
W. Xin, “A new classification method for LIDAR data based on unbalanced support vector machine,” in Proceedings of the International Symposium on Image and Data Fusion (ISIDF '11), August 2011.
[10]
J. Secord and A. Zakhor, “Tree detection in urban regions using aerial lidar and image data,” IEEE Geoscience and Remote Sensing Letters, vol. 4, no. 2, pp. 196–200, 2007.
[11]
P. Li, B. Song, and H. Xu, “Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information,” in Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS '11), pp. 1409–1412, July 2011.
[12]
P. Li, H. Xu, S. Liu, and J. Guo, “Urban building damage detection from very high resolution imagery using one-class SVM and spatial relations,” in Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS '09), pp. V112–V114, July 2009.
[13]
K. Alsabti, S. Ranka, and V. Singh, “An efficient k-means clustering algorithm,” in Proceedings of the IPPS/SPDP Workshop on High Performance data Mining, April 1998.
[14]
C. Tomasi and R. Manduchi, “Bilateral filtering for gray and color images,” in Proceedings of the 1998 IEEE 6th International Conference on Computer Vision, pp. 839–846, January 1998.
[15]
A. H. Al-Fayadh, H. R. Mohamed, and R. S. Al-Shimsah, “CT angiography image segmentation by mean shift algorithm and contour with connected components image,” International Journal of Scientific and Engineering, vol. 3, no. 8, pp. 4–9, 2012.
