Road extraction from satellite images by self supervised classification and perceptual grouping

Şahin, Eda
Road network extraction from high resolution satellite imagery is the most frequently utilized technique for updating and correcting geographic information system (GIS) databases, registering multi-temporal images for change detection and automatically aligning spatial datasets. This advance method is widely employed due to the improvements in satellite technology such as development of new sensors for high resolution imagery. To avoid the cost of the human interaction, various automatic and semi-automatic road extraction methods are developed and proposed in the literature. The aim of this study is to develop a fully automatized method which can extract road networks by using the spectral and structural features of the roads. In order to achieve this goal we set various objectives and work them out one by one. First bjective is to obtain reliable road seeds, since they are crucial for determining road regions correctly in the classification step. Second objective is finding most onvenient features and classification method for the road extraction. The third objective is to locate road centerlines which are defines the road topology. A number of algorithms are developed and tested throughout the thesis to achieve these objectives and the advantages of the proposed ones are explained. The final version of the proposed algorithm is tested by three band (RGB) satellite images and the results are compared with other studies in the literature to illustrate the benefits of the proposed algorithm.


Airplane Localization in Satellite Images by using Visual Attention
Ozyer, Gulsah Tumuklu; Yarman Vural, Fatoş Tunay (2013-04-26)
Automatic target detection from the satellite images is an important tool for various applications including mapping, city planning and defense industry. In this paper, we propose a new two-stage method to identify the airplane regions in the airport images by using visual attention. In the first stage, the interesting patches in the image is aimed to extract from the high resolution images. For that purpose, Itti-Koch visual attention model which is inspired from human vision system is used. In the second ...
Wegner, J. D.; Ok, Ahmet; Thiele, A.; Rottensteiner, F.; Soergel, U. (2010-09-03)
We investigate the potential of combined features of aerial images and high-resolution interferometric SAR (InSAR) data for building detection in urban areas. It is shown that completeness and correctness may be increased if we integrate both InSAR double-bounce lines and 3D lines of stereo data in addition to building hints of a single optical orthophoto. In order to exploit context information, which is crucial for object detection in urban areas, we use a Conditional Random Field approach. It proves to b...
Global appearance based airplane detection from satellite imagery
Arslan, Duygu; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2012)
There is a rising interest in geospatial object detection due to not only the complexity of manual processing of such huge amount of data provided by high resolution satellite imagery but also for military application needs. A fundamental and yet state-of-the art approach for object detection is based on methods that utilize the global appearance. In such a holistic approach, the information of the object class is aimed to be modeled as a whole in the learning phase. And during the classification, a decisio...
A Shadow based trainable method for building detection in satellite images
Dikmen, Mehmet; Halıcı, Uğur; Department of Geodetic and Geographical Information Technologies (2014)
The purpose of this thesis is to develop a supervised building detection and extraction algorithm with a shadow based learning method for high-resolution satellite images. First, shadow segments are identified on an over-segmented image, and then neighboring shadow segments are merged by assuming that they are cast by a single building. Next, these shadow regions are used to detect the candidate regions where buildings most likely occur. Together with this information, distance to shadows towards illuminati...
Building Detection in satellite images by textural features and Adaboost
CETIN, MELIH; Halıcı, Uğur (2010-08-24)
A method based on textural features and Adaboost for detecting buildings in satellite images is proposed. Several local textural features including mean and standard deviation of image intensity and gradient, Zernike moments, Circular-Mellin features, Haralick features, Fourier Power Spectrum, Wavelets, Gabor Filters, and a set features extracted from HSV color space are extracted. Adaboost learning algorithm is employed for both classification and determining the beneficial feature subset, due to its featu...
Citation Formats
E. Şahin, “Road extraction from satellite images by self supervised classification and perceptual grouping,” M.S. - Master of Science, Middle East Technical University, 2013.