Browsing by Subject "Remote sensing images"

Now showing 1 - 5 of 5

Open Access
Automatic detection of compound structures by joint selection of region groups from a hierarchical segmentation
(Institute of Electrical and Electronics Engineers, 2016) Akçay, H. G.; Aksoy, S.
A challenging problem in remote sensing image analysis is the detection of heterogeneous compound structures such as different types of residential, industrial, and agricultural areas that are composed of spatial arrangements of simple primitive objects such as buildings and trees. We describe a generic method for the modeling and detection of compound structures that involve arrangements of an unknown number of primitives in large scenes. The modeling process starts with a single example structure, considers the primitive objects as random variables, builds a contextual model of their arrangements using a Markov random field, and learns the parameters of this model via sampling from the corresponding maximum entropy distribution. The detection task is formulated as the selection of multiple subsets of candidate regions from a hierarchical segmentation where each set of selected regions constitutes an instance of the example compound structure. The combinatorial selection problem is solved by the joint sampling of groups of regions by maximizing the likelihood of their individual appearances and relative spatial arrangements. Experiments using very high spatial resolution images show that the proposed method can effectively localize an unknown number of instances of different compound structures that cannot be detected by using spectral and shape features alone.
Open Access
Hierarchical segmentation, object detection and classification in remotely sensed images
(2007) Akçay, Hüseyin Gökhan
Automatic content extraction and classification of remotely sensed images have become highly desired goals by the advances in satellite technology and computing power. The usual choice for the level of processing image data has been pixelbased analysis. However, spatial information is an important element to interpret the land cover because pixels alone do not give much information about image content. Automatic segmentation of high-resolution remote sensing imagery is an important problem in remote sensing applications because the resulting segmentations can provide valuable spatial and structural information that are complementary to pixel-based spectral information in classification. In this thesis, we first present a method that combines structural information extracted by morphological processing with spectral information summarized using principal components analysis to produce precise segmentations that are also robust to noise. First, principal components are computed from hyper-spectral data to obtain representative bands. Then, candidate regions are extracted by applying connected components analysis to the pixels selected according to their morphological profiles computed using opening and closing by reconstruction with increasing structuring element sizes. Next, these regions are represented using a tree, and the most meaningful ones are selected by optimizing a measure that consists of two factors: spectral homogeneity, which is calculated in terms of variances of spectral features, and neighborhood connectivity, which is calculated using sizes of connected components. Experiments on three data sets show that the method is able to detect structures in the image which are more precise and more meaningful than the structures detected by another approach that does not make strong use of neighborhood and spectral information.Then, we introduce an unsupervised method that combines both spectral and structural information for automatic object detection. First, a segmentation hierarchy is constructed and candidate segments for object detection are selected by the proposed segmentation method. Given the observation that different structures appear more clearly in different principal components, we present an algorithm that is based on probabilistic Latent Semantic Analysis (PLSA) for grouping the candidate segments belonging to multiple segmentations and multiple principal components. The segments are modeled using their spectral content and the PLSA algorithm builds object models by learning the objectconditional probability distributions. Labeling of a segment is done by computing the similarity of its spectral distribution to the distribution of object models using Kullback-Leibler divergence. Experiments on three data sets show that our method is able to automatically detect, group, and label segments belonging to the same object classes. Finally, we present an approach for classification of remotely sensed imagery using spatial information extracted from multi-scale segmentations. Different structuring element size ranges are used to obtain multiple representations of an image at different scales to capture different details inherently found in different structures. Then, pixels at each scale are grouped into contiguous regions using the proposed segmentation method. The resulting regions are modeled using the statistical summaries of their spectral properties. These models are used to cluster the regions by the proposed grouping method, and the cluster memberships assigned to each region at multiple scales are used to classify the corresponding pixels into land cover/land use categories. Final classification is done using decision tree classifiers. Experiments with three ground truth data sets show the effectiveness of the proposed approach over traditional techniques that do not make strong use of region-based spatial information.
Open Access
Mining of remote sensing image archives using spatial relationship histograms
(IEEE, 2008-07) Kalaycılar, Fırat; Kale, Aslı; Zamalieva, Daniya; Aksoy, Selim
We describe a new image representation using spatial relationship histograms that extend our earlier work on modeling image content using attributed relational graphs. These histograms are constructed by classifying the regions in an image, computing the topological and distance-based spatial relationships between these regions, and counting the number of times different groups of regions are observed in the image. We also describe a selection algorithm that produces very compact representations by identifying the distinguishing region groups that are frequently found in a particular class of scenes but rarely exist in others. Experiments using Ikonos scenes illustrate the effectiveness of the proposed representation in retrieval of images containing complex types of scenes such as dense and sparse urban areas. © 2008 IEEE.
Open Access
Modeling of remote sensing image content using attributed relational graphs
(Springer, 2006-08) Aksoy, Selim
Automatic content modeling and retrieval in remote sensing image databases are important and challenging problems. Statistical pattern recognition and computer vision algorithms concentrate on feature-based analysis and representations in pixel or region levels whereas syntactic and structural techniques focus on modeling symbolic representations for interpreting scenes. We describe a hybrid hierarchical approach for image content modeling and retrieval. First, scenes are decomposed into regions using pixel-based classifiers and an iterative split-and-merge algorithm. Next, spatial relationships of regions are computed using boundary, distance and orientation information based on different region representations. Finally, scenes are modeled using attributed relational graphs that combine region class information and spatial arrangements. We demonstrate the effectiveness of this approach in query scenarios that cannot be expressed by traditional approaches but where the proposed models can capture both feature and spatial characteristics of scenes and can retrieve similar areas according to their high-level semantic content. © Springer-Verlag Berlin Heidelberg 2006.
Open Access
Uydu görüntülerinde düzenli dikim alanlarının belirlenmesi
(IEEE, 2009-04) Yalnız, İsmet Zeki; Aksoy, Selim
Uydu görüntülerindeki dikim alanlarının belirlenmesi, bölütlenmesi, sınıflandırılması ve gözlemlenmesi, bu alanların ekonomik olarak daha iyi kullanım yollarının aranmasına yardımcı olmaktadır. Bir çok insan yapısı gibi, bitkiler de bir düzene göre tarlalarda veya bahçelerde dikilmektedir. Bu bildiride, görüntülerdeki düzen bilgisini kullanarak dikim alanlarını belirleyen bir yöntem önerilmiştir. Bu yöntemde, uydu görüntüsünde nokta filtresinin cevabı üzerinde pencereler gezdirilmekte ve bu pencerelerin izdüşüm vektörleri analiz edilmektedir. Daha sonra bütün pencereler için bir düzenlilik katsayısı belirlenmektedir. Bu düzenlilik katsayıları düzenli alanların daha yüksek değerler aldığı bir düzenlilik haritası çıkartmak için kullanılmaktadır. Bu düzenlilik haritası dikim alanlarının bölütlenmesi ve sınıflandırılması için kullanılabilir. Önerilen yöntem yüksek çözünürlüklü görüntülerde fındık bahçelerinin bulunmasında denenmiş ve sonuçlar tartışılmıştır. Detecting, segmenting and classifying agricultural fields in remote sensing images enable advanced planning of the land use economically. As most human structures, plants are cultivated in some order in orchards or farms. In this paper a regularity detection method is proposed for exploiting this order information. The method slides windows over the spot filter responses of satellite images and analyzes their projection vectors. A regularity coefficient is calculated for each window. These regularity coefficients are further used for creating a regularity map, where regular regions obtain higher scores. These regularity maps can later be employed for the segmentation and classification of cultivation lands. The proposed method is illustrated in the detection of hazelnut orchards in sample high resolution satellite images. ©2009 IEEE.