No description available.

Apart from classical pattern recognition techniques applied for automated building detection in satellite images, a robust building detection methodology is proposed, where self-supervision data can be automatically extracted from the image by using shadow and its direction as an invariant for building object. In this methodology / first the vegetation, water and shadow regions are detected from a given satellite image and local directional fuzzy landscapes representing the existence of building are generated from the shadow regions using the direction of illumination obtained from image metadata. For each landscape, foreground (building) and background pixels are automatically determined and a bipartitioning is obtained using a graph-based algorithm, Grabcut. Finally, local results are merged to obtain the final building detection result. Considering performance evaluation results, this approach can be seen as a proof of concept that the shadow is an invariant for a building object and promising detection results can be obtained when even a single invariant for an object is used.

In this study, an automated building extraction system, which is capable of detecting buildings from satellite images using only RGB color band is implemented. The approach used in this work has four main steps: local feature extraction, feature selection, classification and post processing. There are many studies in literature that deal with the same problem. The main issue is to find the most suitable features to distinguish a building. This work presents a feature selection scheme that is connected with the classification framework of Adaboost. As well as Adaboost, four SVM kernels are used for classification. Detailed analysis regarding window type and size, feature type, feature selection, feature count and training set is done for determining the optimal parameters for the classifiers. A detailed comparison of SVM and Adaboost is done based on pixel and object performances and the results obtained are presented both numerically and visually. It is observed that SVM performs better if quadratic kernel is used than the cases using linear, RBF or polynomial kernels. SVM performance is better if features are selected either by Adaboost or by considering errors obtained on histograms of features. The performance obtained by quadratic kernel SVM operated on Adaboost selected features is found to be 38% in terms of pixel based performance criteria quality percentage and 48% in terms object based performance criteria correct detection with building detection threshold 0.4. Adaboost performed better than SVM resulting in 43% quality percentage and 67% correct detection with the same threshold.

This study presents an integrated framework for the automatic generation of the photorealistic 3-d building models from satellite and ground-level imagery. First, the 2-d building patches and the corresponding footprints are extracted from a high resolution imagery using an adaptive fuzzy-genetic algorithm approach. Next, the photorealistic facade textures are automatically extracted from the single ground-level building images using a developed approach, which includes facade image extraction, rectification, and occlusion removal. Finally, the textured 3-d building models are generated automatically by mapping the corresponding textures onto the facades of the models. The developed 2-d building extraction and delineation approach was implemented on a selected urban area of the Batikent district of Ankara, Turkey. The building regions were extracted with an approximate detection rate of 93%. Moreover, the overall delineation accuracy was computed to be 3.9 meters. The developed concept for facade image extraction was tested on two distinct datasets. The facade image extraction accuracies were computed to be 82% and 81% for the Batikent and eTrims datasets, respectively. As to rectification results, 60% and 80% of the facade images provided errors under ten pixels for the Batikent and eTrims datasets, respectively. In the evaluation of occlusion removal, the average scores were computed to be 2.58 and 2.28 for the Batikent and eTrims datasets, respectively. The scores are ranked between 1 (Excellent) to 6 (Unusable). The modeling of the total 110 single buildings with the photorealistic textures took about 50 minutes of processor running time and yielded a satisfactory level of accuracy.

A method for detecting the buildings from high resolution aerial images is proposed. The aim is to extract the buildings from high resolution aerial images using the Hough transform and the model based perceptual grouping techniques.The edges detected from the image are the basic structures used in the building detection procedure. The method proposed in this thesis makes use of the basic image processing techniques. Noise removal and image sharpening techniques are used to enhance the input image. Then, the edges are extracted from the image using the Canny edge detection algorithm. The edges obtained are composed of discrete points. These discrete points are vectorized in order to generate straight line segments. This is performed with the use of the Hough transform and the perceptual grouping techniques. The straight line segments become the basic structures of the buildings. Finally, the straight line segments are grouped based on predefined model(s) using the model based perceptual grouping technique. The groups of straight line segments are the candidates for 2D structures that may be the buildings, the shadows or other man-made objects. The proposed method was implemented with a program written in C programming language. The approach was applied to several study areas. The results achieved are encouraging. The number of the extracted buildings increase if the orientation of the buildings are nearly the same and the Canny edge detector detects most of the building edges.If the buildings have different orientations,some of the buildings may not be extracted with the proposed method. In addition to building orientation, the building size and the parameters used in the Hough transform and the perceptual grouping stages also affect the success of the proposed method.

Interpreting a Synthetic Aperture Radar (SAR) image and detecting buildings can be a difficult task visually. In order acquire an overview of an area that has been affected by a disaster, such as an earthquake, SAR is useful due to its independence of weather conditions and the time of the day. GeoRaySAR, a simulator that has been developed by German Aerospace Center (DLR) and the Technical University of Munich (TUM), uses prior knowledge about the geometry extracted, from e.g. a Digital Surface Model (DSM), in order to identify buildings in high resolution SAR data. The simulator has previously utilized DSMs generated from Light Detection And Ranging (LiDAR) data with a vertical and horizontal resolution of 0.1 meters and 1 meter respectively without vegetation. However, DSMs of such high quality is not available everywhere. The objective of this thesis is to evaluate DSMs generated from high-resolution optical data for identifying building in high resolution SAR data in GeoRaySAR. Specifically, images from the spaceborne sensor WorldView-2 have been utilized in this thesis for the extraction of the geometry. The DSMs have been preprocessed in terms of removal of vegetation and reduction of the noise level. The SAR images, acquired from TerraSAR-X, were utilized in GeoRaySAR in order to detect buildings with the assistance of the DSM. An image size limitation that existed in GeoRaySAR has been addressed by adding tiling, which is based on the size of the study scene. Normalized DSM (nDSM) can be determined by calculating the difference between a DSM and a DTM. A nDSM, that received some adjustments, was used as input to GeoRaySAR and compared with the results from the normal DSM. Study areas in three cities, Munich, London and Istanbul, have been used to determine the advantages and limitations of GeoRaySAR and the impact the quality of the DSM has on the building extraction results. The results indicate that building extents can be detected with DSMs generated from optical data with various success, dependent on the quality of the DSM and on which incidence angle the SAR image was acquired in. The ability to interpret a scene increases with the usage of DSMs of higher quality and with SAR images taken in less steep incidence angles. The building DSM depends heavily on the quality of the DTM, but indicates good results and little data loss in study scenes where the DTM successfully removed all objects above ground.

No description available.

No description available.

A method for detecting buildings from satellite/aerial images is proposed in this study. The aim is to extract rectilinear buildings by using hypothesize first verify next manner. Hypothesis generation is accomplished by using edge detection and line generation stages. Hypothesis verification is carried out by using information obtained both from the color segmentation of HSV representation of the image and the shadow detection stages&rsquo / output. Satellite/aerial image is firstly filtered to sharpen the edges. Then, edges are extracted using Canny edge detection algorithm. These edges are the input for the Hough Transform stage which will produce line segments according to these extracted edges. Then, extracted line segments are used to generate building hypotheses. Verification of these hypotheses makes use of the outputs of the HSV color segmentation and shadow detection stages. In this study, color segmentation is processed on the HSV representation of the satellite/aerial image which is less sensitive to illumination. In order to perform the shadow detection, the basic information which is shadow areas have higher value of saturation component and lower value of value component in HSV color space is used and according to this information a mask is applied to the HSV representation of the image to produce shadow pixels. The proposed method is implemented as software written in MATLAB programming software. The approach was tested in several different areas. The results are encouraging.

Rectangular-shaped building detection from high resolution aerial/satellite images is proposed for two different methods. Shadow information plays main role in both of these algorithms. One of the algorithms is based on Hough transformation, the other one is based on mean shift segmentation algorithm. Satellite/aerial images are firstly converted to YIQ color space to be used in shadow segmentation. Hue and intensity values are used in computing the ratio image which is used to segment shadowed regions. For shadow segmentation Otsu&rsquo / s method is used on the histogram of the ratio image. The segmented shadow image is used as the input for both of two building detection algorithms. In the proposed methods, shadowed regions are believed to be the building shadows. So, non-shadowed regions such as roads, cars, trees etc. are discarded before processing the image. In Hough transform based building detection algorithm, shadowed regions are firstly segmented one by one and filtered for noise removal and edge sharpening. Then, the edges in the filtered image are detected by using Canny edge detection algorithm. Then, line segments are extracted. Finally, the extracted line segments are used to construct rectangular-shaped buildings. In mean shift based building detection algorithm, image is firstly segmented by using mean shift segmentation algorithm. By using shadow image and segmented image, building rooftops are investigated in shadow boundaries. The results are compared for both of the algorithms. In the last step a shadow removal algorithm is implemented to observe the effects of shadow regions in both of two implemented building detection algorithms. Both of these algorithms are applied to shadow removed image and results are compared.