Now showing items 1-10 of 10

    • Building detection using directional spatial constraints 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2010)
      We propose an algorithm for automatic detection of buildings with complex shapes and roof structures in very high spatial resolution remotely sensed images. First, an initial oversegmentation is obtained. Then, candidate ...
    • Detection of compound structures by region group selection from hierarchical segmentations 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2016-07)
      Detection of compound structures that are comprised of different arrangements of simpler primitive objects has been a challenging problem as commonly used bag-of-words models are limited in capturing spatial information. ...
    • Detection of compound structures using clustering of statistical and structural features 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2012)
      We describe a new method for detecting compound structures in images by combining the statistical and structural characteristics of simple primitive objects. A graph is constructed by assigning the primitive objects to its ...
    • Detection of compound structures using multiple hierarchical segmentations 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2012)
      In this paper, our aim is to discover compound structures comprised of regions obtained from hierarchical segmentations of multiple spectral bands. A region adjacency graph is constructed by representing regions as vertices ...
    • Hierarchical segmentation of complex structures 

      Akçay, H. Gökhan; Aksoy, Selim; Soille P. (IEEE, 2010)
      We present an unsupervised hierarchical segmentation algorithm for detection of complex heterogeneous image structures that are comprised of simpler homogeneous primitive objects. An initial segmentation step produces ...
    • Image classification and object detection using spatial contextual constraints 

      Aksoy, Selim; Cinbiş, R. Gökberk; Akçay, H. Gökhan (Taylor & Francis, 2012)
      Spatial information plays a very important role in high-level image understanding tasks. Contextual models that exploit spatial information through the quantification of region spatial relationships can be used for ...
    • Kentsel yapıların biçimbilimsel bölütlenmesi 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2007-06)
      Yüksek çözünürlükteki uzaktan algılamalı uydu görüntülerinde bölütleme kent uygulamalarında önemli bir problemdir çünkü elde edilen bölütlemelerle sınıflandırma için piksel tabanlı spektral bilginin yanında uzamsal ve ...
    • Morphological segmentation of urban structures 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2007-04)
      Automatic segmentation of high-resolution remote sensing imagery is an important problem in urban applications because the resulting segmentations can provide valuable spatial and structural information that are complementary ...
    • A spatial data model for remote sensing image retrieval 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2013)
      Given a query region, our aim is to discover and retrieve regions with similar spatial arrangement and characteristics in other areas of the same large image or in other images. A Markov random field is constructed by ...
    • Tarım alanlarında doğrusal odunsu bitki gruplarının otomatik sezimi 

      Akçay, H. Gökhan; Aksoy, Selim (IEEE, 2009-04)
      Tarım alanlarının otomatik haritalanması ve izlenmesi önemli bir araştırma konusudur. Bu bildiride, çok yüksek çözünürlükteki uydu görüntülerinde doğrusal şeritler halindeki odunsu bitki gruplarının otomatik olarak sezilmesi ...