Several studies have already demonstrated the efficiency of utilizing spatial information in representation and interpretation of hyperspectral (HS) images. Texture and shape features are known as two important categories of spatial information in various applications of image processing. This study tries to utilize texture and shape features extracted from HS images, as well as spectral information, in order to reduce overall classification errors. These features include morphological profiles (MPs), global Gabor features, and features extracted from conventional and segmentation-based grey-level co-occurrence matrices (GLCMs). Various combinations of these spatial features along with spectral information are fed into a support vector machine (SVM) classifier, and the best combinations for different situations are determined. Experiments on the widely used Indian Pines, Pavia University, and Salinas HS data sets demonstrate the efficiency of the proposed framework in comparison with some recent spectral–spatial classification methods.
31 August 2015 in IEEE Transactions on Geoscience and Remote Sensing
This paper presents a new spectral-spatial classification method for hyperspectral (HS) images. The proposed method is based on integrating hierarchical segmentation results into Markov random field (MRF) spatial prior in the Bayesian framework. This work includes two main contributions. First, statistical region merging (SRM) segmentation algorithm is extended to a hierarchical version, HSRM. Second, a method for extracting a multilevel “fuzzy no-border/border” map from HSRM segmentation hierarchy is proposed, which are then exploited as weighting coefficients to modify the spatial prior of MRF-based multilevel logistic (MLL) model. The proposed method, named as MRF + HSRM, addresses the common problem of MRF-based methods, i.e., over-smoothing of classification result. Several experiments are conducted using real HS images to evaluate the performance of the proposed method in comparison with conventional MRF, and some state-of-the-art weighted MRF and object-based classifiers. To estimate the class conditional probability distribution in Bayesian framework, probabilistic support vector machine (SVM) and subspace multinomial logistic regression (MLRsub) classifiers are used. The experimental results demonstrate that the proposed method is able to generate more homogeneous regions similar to MRF-based methods, while preserving class boundaries as accurately as segmentation-based methods. The overhead computational burden of the proposed hierarchical segmentation stage is negligible considering the improvement it offers in classification results.
29 October 2014 in Journal of Environmental Health Science and Engineering
Background: One of the natural phenomena which have had considerable impacts on various regions of the world, including Iran, is "dust storm". In recent years, this phenomenon has taken on new dimensions in Iran and has changed from a local problem to a national issue. This study is an attempt to investigate the formation of the dust storms crossing the Western Iran. Methodology: To find the sources of the dust storms entering Iran, first we examine three determined dust paths in the region and their temporal activities, using MODIS satellite images. Then, four regions were identified as dust sources through soil, land cover and wind data. Finally, atmospheric analyses are implemented to find synoptic patterns inducing dust storms. Results and discussion: Source 1 has covered the region between the eastern banks of Euphrates and western banks of Tigris. Source 2 is in desert area of western and south-western Iraq. Finally source 3 is bounded in eastern and south-eastern deserts of Saudi Arabia called Rub-Al-Khali desert, or Empty Quarter. Moreover, south-eastern part of Iraq (source 4) was also determined as a secondary source which thickens the dust masses originating from the above mentioned sources. The study of synoptic circulations suggests that the dust storms originating from source 1 are formed due to the intense pressure gradient between the low-pressure system of Zagros and a high-pressure cell formed on Mediterranean Sea. The dust events in sources 2 and 3 are outcomes of the atmospheric circulations dominant in the cold period of the year in mid-latitudes.
In the present research we have used GLCM and Gabor filters to extract texture features in order to classify PAN images. The main drawback of GLCM algorithm is its time-consuming nature. In this work, we proposed a fast GLCM algorithm to overcome the mentioned weakness of traditional GLCM. The fast GLCM is capable of extracting approximately the same features as the traditional GLCM does, but in a really much less time (in the best case, 180 times faster, and in the worst case, 30 times faster). The other weakness of the traditional GLCM is its lower accuracies in the region near the class borders. As Gabor filters are more powerful in border regions, we have tried to combine Gabor features with GLCM features. In this way we would compensate the latter mentioned weakness of GLCM. Experimental results show good capabilities of the proposed fast GLCM and the feature fusion method in classification of PAN images.
1 January 2017 in European Journal of Remote Sensing
In this article, we propose a method for extracting spatio-spectral features from high spatial resolution hyperspectral (HS) images. The method is based on extracting two-dimensional moments from neighbourhoods of pixels. Three different types of moments are considered: geometric, complex Zernike and Legendre. Moments of a given type are extracted from a few principal components (PC) of HS data, and are stacked on the original HS data to form a joint spatio-spectral feature space. These features are classified using a support vector machine (SVM) classifier. The influence of the moments orders and the size of the neighbourhood window on the quality of the extracted features are analysed. A few experiments are conducted on two widely used HS data sets, Pavia University and Salinas. The results demonstrate high capabilities of the proposed method in comparison with some state-of-the-art spatio-spectral HS classification methods.