Akçay, H. G.Aksoy, S.2016-02-082016-02-082008-070196-2892http://hdl.handle.net/11693/23067The object-based analysis of remotely sensed imagery provides valuable spatial and structural information that is complementary to pixel-based spectral information in classification. In this paper, we present novel methods for automatic object detection in high-resolution images by combining spectral information with structural information exploited by using image segmentation. The proposed segmentation algorithm uses morphological operations applied to individual spectral bands using structuring elements in increasing sizes. These operations produce a set of connected components forming a hierarchy of segments for each band. A generic algorithm is designed to select meaningful segments that maximize a measure consisting of spectral homogeneity and neighborhood connectivity. Given the observation that different structures appear more clearly at different scales in different spectral bands, we describe a new algorithm for unsupervised grouping of candidate segments belonging to multiple hierarchical segmentations to find coherent sets of segments that correspond to actual objects. The segments are modeled by using their spectral and textural content, and the grouping problem is solved by using the probabilistic latent semantic analysis algorithm that builds object models by learning the object-conditional probability distributions. The automatic labeling of a segment is done by computing the similarity of its feature distribution to the distribution of the learned object models using the Kullback-Leibler divergence. The performances of the unsupervised segmentation and object detection algorithms are evaluated qualitatively and quantitatively using three different data sets with comparative experiments, and the results show that the proposed methods are able to automatically detect, group, and label segments belonging to the same object classes. © 2008 IEEE.EnglishHierarchical segmentationImage segmentationObject-based analysisUnsupervised object detectionBoolean functionsFeature extractionImage processingInformation theoryLearning algorithmsMathematical morphologyProbabilityProbability distributionsRisk assessmentSet theoryApplied (CO)Automatic detectionAutomatic labellingComparative experimentsConditional probability distributionsConnected componentsData setsDifferent scalesFeature distributionGeneric algorithmsGeo spatial objectsGrouping problemsHigh-resolution (HR) imagesIndividual (PSS 544-7)Kullback leibler divergence (KLD)Morphological operationsNew algorithmNovel methodsObject classesObject detectionObject detection algorithmsObject modellingObject-basedProbabilistic latent semantic analysis (PLSA)Remotely sensed imagery (RSI)Segmentation algorithmsSpectral bandingSpectral informationsStructural informationsStructuring element (SE)Unsupervised segmentationObject recognitionAlgorithmsImage analysisInformation retrievalLabelsMathematical modelsRemote sensingArticle10.1109/TGRS.2008.916644