جستجوی مقالات مرتبط با کلیدواژه « طبقه بندی » در نشریات گروه « عمران »

The issue of urbanization and monitoring of urban expansion and land use changes using satellite images has become a basic focus in the society. Easy and stable access to satellite data has made it possible to monitor and monitor land changes more accurately; But for optimal use of these images, it is necessary to collect samples of images and then classify their pixels based on regional features and characteristics. This process faces challenges such as data dispersion, which can be solved by using appropriate classification methods. In this study, in order to evaluate the area of land uses in cities, various methods of machine learning have been used. Instead of using a fixed and absolute method for classifying pixels, four different machine learning methods are investigated separately for each image. These diverse methods of machine learning provide the possibility of choosing the best and most efficient method for each image, thus improving the ability to detect and classify pixels for land use areas in cities and increasing accuracy and efficiency.

In this research, the Landsat 9 satellite image has been used to study and analyze different areas of Tehran in 2023. First, the desired image was subjected to the necessary corrections and then four appropriate machine learning algorithms (which included K-nearest neighbor, support vector machine, random forest and maximum likelihood) were used to classify Landsat 9 satellite images related to four different areas of Tehran (including 2, 5 , 21, 22) were used. To evaluate the accuracy of the results, more than 200 check points were created on the image using the Stratified Random method, and then Google Earth Pro was used to check the check points. The overall classification accuracy and kappa coefficient were evaluated as evaluation criteria for the best classification method of image pixels. In the next step, the studied area was divided into equal blocks in order to better understand the area of land uses in that area. Then, using Zonal Statistics, the amount of land use area in each block was investigated.

Based on the methods used, the performance of the SVM method in this study achieved the highest possible accuracy, which is equal to 95%, and the Kappa coefficient, which is 89%. These results may be justified due to the non-uniformity of pixel areas in dense urban environments. In addition, different areas of land, including green areas with an area of 12 square kilometers, barren lands with an area of 64 square kilometers, and built-up areas with an area of 137 square kilometers were also examined in this analysis.

Through this approach, we have presented a highly accurate classification method for the analysis of satellite images related to the Landsat 9 satellite. This method enables a more accurate assessment of the area of land uses and provides urban decision makers and policy makers with a direct link with valuable insights for sustainable development in cities. This can play an effective role in the process of facilitating development plans to improve cities and citizens' lives, because it provides accurate and reliable information that helps strategic decisions in the field of urban development and enables more effective and targeted changes in urban policies and programs.

Three-dimensional classification of urban features is one of the important tools for urban management and the basis of many analyzes in photogrammetry and remote sensing. Therefore, it is applied in many applications such as planning, urban management and disaster management. In this study, dense point clouds extracted from dense image matching is applied for classification in urban areas. Applied images are acquired using a Micasense RedEdge multispectral camera to increase the classification accuracy. The band to band registration is one of the existing challenges of multi-spectral camera, which the SIFT algorithm is used to extract the corresponding features of each band. One band selected as reference and other bands are transferred to the reference band by projective transformation. Finally, the bands are combined to create a color image from each three bands. So, two point clouds are generated using dense image matching techniques from two sets of images. To produce a multi-spectral point cloud, the two set of point clouds have been integrated using nearest neighbor interpolation. The multi-spectral point clouds are classified by using random forest algorithm, structural and multi-spectral features. This process composed of three parts as structural information, multi-spectral information, and integration of both. Finally, the results are shown a 25% improvement in the accuracy of the integration of multi-spectral and structural information compared to multi-spectral information and 32% improvement in the accuracy of the integration of multi-spectral and structural information compared to structural information. Classification using visible information (RGB) instead of multispectral information resulted in an accuracy drop by 5%.

The ability of recording the high resolution spectral signature of earth surface would be the most important feature of hyperspectral sensors. On the other hand, classification of hyperspectral imagery is known as one of the methods to extracting information from these remote sensing data sources. Despite the high potential of hyperspectral images in the information content point of view, there are a numerous challenges in reliable extraction of information from these images. The issues such as 1- spectral similarity of different phenomena, 2- sensor noises and atmospheric effects, 3- the effects of high dimensionality in the pattern recognition algorithms, 4- the necessity of large number of training data to perform a reliable classification, and 5- spectral variability of similar phenomena could be considered as some of the challenges in hyperspectral data processing. Decreasing of the high dimensionality effects via the dimension reduction algorithms (e.g. band selection and feature extraction algorithms), as well as increasing the separability of the overlapped classes through the linear/non-linear mappings into the feature spaces with the higher dimensional are two opposite and conventional approaches of hyperspectral data processing. These approaches would be used based on the factors such as 1- complexities of classes in the imaging area, 2- spectral range of imaging sensor, and 3- the restrictions of processing algorithms. In this paper the fusion of these two approaches is used to perform an accurate hyperspectral image classification. To do so, a novel feature extraction method is proposed to be used in the hyperspectral image classification. The core of this method is the fusion of the linear, non-linear and sparse representation based features which is used to produce the effective features in the weighted K-Nearest Neighbors (KNN) classification method. In this procedure, a set of supervised and nonlinear features are extracted as the first step through the Nonlinear Principal Component Analysis (NLPCA). The supervised usage of NLPCA in order to extract features is known as one of the novelties of this paper. In this step, the spectral bands are usually mapped to a high dimensional feature space through the self-estimator artificial neural networks (ANNs) which are trained separately by ground truth data. In the second step, the previously extracted features are linearly transformed by the Linear Discriminate Analysis (LDA) method in order to reduce the dimension of the hypercube generated via supervised NLPCA to a separable feature space. In the last step, a set of features which is proportional to the number of classes is generated based on the sparse representation theory. The sparse representation features were hired to handle the effects of the inter-class variability. The precisions of the classified features in the two different hyperspectral images were on average shown 6 percent improvements in comparison with the spectral bands and the other combinations of extracted features. Furthermore, reach to the approximately 99% overall accuracies in the classes with the few training data could be considered as other achievements of the proposed method.

Land cover is defined as the physical material of the surface of the earth, including different vegetation covers, bare soil, water surface, various urban areas, etc. Land cover and its changes are very important and influential on the Earth and life of living organisms, especially human beings. Land cover change monitoring is important for protecting the ecosystem, forests, farmland, open spaces, water quality, wildlife habitat, and human health. Uncontrolled changes in land cover (deforestation, extensive agricultural activities, vast urban and exurban development, etc.) will not only destroy the natural environment and the ecosystem but also will affect different aspects of human life including the economy. As a result, various effective methods for land cover monitoring are always deliberated by researchers. Remote sensing based techniques, due to their unique capabilities and extensive data availability, have attracted great interest for decades. In addition, fully Polarimetric Synthetic Aperture Radar (PolSAR) images, due to the rich data and the ability of day-night and all weather condition data acquisition, has got high capability to study and monitor land cover changes. Recent developments of SAR sensors in acquiring fully polarimetric, continuous, and very high resolution data, besides enabling precise land cover monitoring, has necessitates the usage of more powerful and robust algorithms in different image processing steps. Classification algorithms are among the most fundamental tools of remote sensing image processing; and an increasing number of researches have been focused on developing novel and more robust classification methodologies for remote sensing data in recent years. Mid-level representations have also been introduced to the remote sensing data classification to enhance the reasonability and semantic rationality of the land cover classifications through remote sensing techniques. Bag of Visual Words (BOVW) model, originally inspired by the Bag of Words (BOW) model from text mining, is one of the most authoritative mid-level representation models which has achieved state-of-the-art results in different image processing tasks. BOVW representation model has recently been introduced to remote sensing data processing and proved to be very beneficial for high resolution remote sensing data representation. In the present paper, a novel segment-based BOVW framework has been developed for PolSAR data representation and classification. The obtained classified maps are quantitatively and qualitatively compared with the result of classification with well-known classifiers including Support Vector Machine (SVM), Artificial Neural Network (ANN), and Wishart Classification Algorithms. The main contributions of the current study are (i) covering the semantic gap between low-level features extracted from the PolSAR image and high-level concept of land cover in remote sensing data classification (ii) introducing novel segment-based BOVW framework for PolSAR image classification, and (iii) extensive evaluation of the performance of the BOVW model for PolSAR data classification in terms of the model parameters and low-level features selection. The experimental dataset is acquired by RADARSAR-2 from San Francisco Bay, California, in C band and at fine quad-pol mode, in 2008. The achieved overall accuracy, 90.1%, illustrates the capability of the proposed model for SAR image classification purposes. Moreover, the proposed segment-based framework for the BOVW model has decreased the undesired speckle effect of the SAR data, without speckle filtering.

Hyperspectral sensors have high capability in identifying objects by acquiring a large number of adjacent electromagnetic bands. Although This large number of bands makes it possible to approximate the more precise spectral curve of the material, it also brings some challenges. The difficulty in data transfer, the weak performance of conventional statistical classifications due to the limited number of training data, and the high processing time are the most important ones. Hence, different methods of dimensionality reduction are proposed for hyperspectral images. In the following article, an unsupervised feature extraction method is proposed based on the bands clustering technique. In the proposed method, after the prior image clustering and forming the prototype space with the aid of the clusters’ averages, the bands are clustered using the K-medoids clustering algorithm. In each cluster, four types of central tendency measures, mean, geometric mean, harmonic mean, and median are used to extract the final features. The experiments are conducted on the three real hyperspectral images with medium and high spatial resolution. Final results indicate that the classification results of the proposed method can reach (72.12) which is 7% higher than the other four competitive methods, principal component analysis (PCA) (64.39), wavelet (64.58), feature selection method based on bands clustering based on variance (65.30) and non-parametric weighted features extraction (NWFE) (64.12) .

Information of the land uses is important for many activities, including the planning and the land management such territorial planning changes from recent decades to now. In this research has been afforded that the different land uses changes to be investigated and analyzed. For this purpose, using the satellite images from 1991 to 2016 and using the classification method of maximum likelihood, the map of land uses for the mentioned years was prepared. Then with LCM program, the changes of the different land uses from 1991 to 2016 to be analyzed. Results showed that the uses of rainfed lands by a minimum of 352 ha and a maximum of 365 ha and 717 ha total changes had the most changes, and the residential land by a minimum of 1 ha and a maximum of 56 ha increased and 57 ha total changes had the fewest changes among the uses studied. Furthermore, the general monitoring of changes showed the decrease of 506 ha pastures and increased 344 ha of the irrigated agriculture. Results showed that the natural areas was destructed and transformed into human-made areas. It is suggested that in order to conserve the natural resources, take decisions by the managers in planning

The last few decades witnessed high urban growth rates in many countries. Urban growth can be mapped and measured by using remote sensing data and techniques along with several statistical measures. The purpose of this research is to detect the urban change that is used for urban planning. Change detection using remote sensing images can be classified into three algebra-based, transformation-based and classification-based. By using any of these methods and applying them to SAR and optical data has advantages and disadvantages. Fusion of these methods and datasets can give us this opportunity to overcome their disadvantages and complement each other. For this purpose, here, a decision level fusion technique based on the majority voting algorithm is proposed for integrating the change maps extracted by different methods. After extracting features for optical and polarimetric data, object-based and pixel-based classification methods applied to optic images and also Wishart and SVM classification methods applied on SAR data. Change maps extracted from applying different CD methods such as post-classification, image differencing and principal component analysis. In order to evaluate the efficiency of the proposed method, various optical and radar remote sensing images from before and after of urban growth, acquired by QuickBird and UAVSAR, were utilized. In order to clarify the importance of using both optical and polarimetric images, the majority voting fusion algorithm on the change maps extracted by optical and polarimetric images was also applied separately. The results show that by fusing optical and polarimetric data at the decision level, it is possible to obtain a better accuracy because these two types of data, due to differences, can detect changes in a different way, thus covering each other's deficiencies. Polarimetric images better detect changes in altitude changes, and optical images better detect changes resulting from spectral changes. In order to perform a comparative evaluation, the accuracy of the change map obtained using optical images (total accuracy: 80.86% and kappa: 0.67), polarimetric images (overall accuracy: 75.43% and kappa: 0.5), simultaneous applying both datasets (overall accuracy: 88.48% and kappa: 0.79), as well as using the change maps of both data sets with the highest accuracy (overall accuracy: 88.81% and kappa: 0.79) have been obtained. In the end, due to the noise characterization of the post-classification method, the obtained change map improves with an overall accuracy of 90.11% and a kappa of 0.82.

Hyperspectral images are widely used in various fields such as agriculture, geology and mining, urban management, military, target detection. Classification is one of the most important fields of hyperspectral data processing which traditionally performed with spectral features. Various studies have shown that the use of spatial features along with spectral features can increase the accuracy of the classification. In this research, a method has been developed for the spatial-spatial classification of hyperspectral images. In this method, after a feature extraction step based on the minimum noise fraction (MNF) method, the geometric moments as spatial features are generated from first few MNF components in the different window seizes. In the next step, these features are stacked with spectral features and genetic algorithm is used to select the appropriate combination. Finally, a majority voting filter is used in order to remove the wrong pixels in each class, and increasing the homogeneity of labels and classification accuracy. Using the MNF transform to generate geometric moment features of the image, the use of genetic algorithm for selecting appropriate spectral-spatial features and post-processing step based on the majority voting filter are the innovative points of this paper. The results of the implementations on a real hyperspectral image from the semi-urban agricultural area named Indian Pines show that the proposed algorithm can reach the classification accuracy above 94% which is 40% better than conventional method.

Building detection from remote sensing images has significant importance in updating the maps, urban monitoring, and a wide range of other applications. The high spatial resolution images are an important data source for geospatial information extraction. These images provide extraordinary facilities for feature extraction like buildings and spatial analysis in urban areas. However this task suffers from some problems due to spectral complexity in the image scene. Since high resolution images contain a lot of details about the scene such as; non-homogeneity of the roof of the buildings, sloping and flatness, it can create various spectral properties among other issues. Also, due to the use of similar materials, some buildings can’t be completely separated from the streets and parking. To overcome these issues, the use of neighborhood and height information is essential. Accordingly, the major part of this research is the use of spatial features of adjacent pixels in a multispectral image and elevation data to increase the accuracy of building classification. In this regard, on the one hand, with the expansion of the feature space in a quasi-deep method, the goal was to train the classification algorithm in higher level and more comprehensive information. But all the features available to distinguish between buildings and non-buildings are not useful. On the other hand, due to the large amount of input data and the increased computing time and memory required, to reduce the processing cost, it is necessary to perform the feature selection operation. Despite many efforts that have been made over the past decades to develop the methods for automatic building detection from these images, high-performance methods are still unavailable because of the uncertainties like optimal feature selection. Therefore, in this study, with a view to improving the automatic detection of the building from remote sensing data, a new hybrid approach is proposed to select the optimal features of the large dataset in a reasonable time. The proposed method of this research firstly extracts high-level features for optimal building detection by using quasi-deep texture structures. Then, it selects the optimal features based on the integration of the developed AdaBoost algorithm (Confidence Based AdaBoost) with the optimized support vector machines by particle swarm optimization (CB-SVMpso), and performs the binary classification of the building and background. The experiments were performed on the standard data set of Vaihingen in Germany and then the results of the proposed method were compared with efficient methods of machine learning. Also, a comparison was made between the quasi-deep feature sets with the traditional method of GLCM textures. In experiments, in order to purify the final results, no pre-processing and post-processing steps have been interfered. The experimental results showed that on average, the highest overall accuracy and kappa coefficient obtained from the proposed method were 93.25% and 83.06%, respectively, and in comparison to conventional methods, the accuracy of kappa coefficient has increased by 7.27%, as well as the computational time reduction by half, indicating the reliability and efficiency of the proposed method in detecting the majority of buildings.

Nowadays, SAR imaging is a well-developed remote sensing technique for providing high spatial resolution images of the Earth’s surface which provides a vast amount of information for environmental monitoring. Fully polarimetric (FP) SAR systems alternately transmit two orthogonal polarizations and receive the response of the scatters to each of them by two antennas with orthogonal polarizations. Transmitting two interleaved electromagnetic waves requires doubling the pulse repetition frequency which implies immediately that the image swath must be only half of the width of a single-polarized or dual-polarized SAR. In order to achieve a better swath width, and coincidentally reduce average power requirements and simplify transmitting hardware, compact polarimetric (CP) systems have been proposed with the promise of being able to maintain many capabilities of fully polarimetric systems (Souyris et al., 2005). One of the most important CP configurations is dual circular polarimetric (DCP) mode.In order to extract the physical scattering mechanism (PSM) of targets using polarimetric data many classification methods have been presented. One of the most common such methods is H-α decomposition (Cloude and Pottier, 1998) that is proposed for FP data. Its principle relies on the analysis of eigenvalues and eigenvectors of the coherency matrix. The space of scattering entropy (H) and mean alpha angle (α) namely H-α plane is used to classify the polarimetric image into 8 canonical PSMs.In recent years two approaches have been proposed in order to find dual H-α classification zones for DCP data. (Guo et al., 2012) proposed an H-α classification space by mapping the points of each PSM from the original FP data into the space of H-α for CP data and subsequently (Zhang et al., 2014) proposed an H-α space on the basis of the distribution centers and densities of different PSMs. Experimental results showed that the classification accuracy of each PSM is improved compared with the results of Guo’s H-α space, however Zhang’s method is not well accurate and there are still overlaps between different PSMs. The results of Zhang’s method for H- α boundaries is highly dependent on the choice of data. For example, in one data it might exist a special class of plants that are dominant in the image and in another one another class might be dominant. So, the maximum distribution densities of these two images are different from each other. Furthermore, the specifications of different sensors are different. For example, the base noise of each sensor is different and entropy is dependent on this parameter. So, for each specific sensor its own optimum boundaries should be found.
According to the fact that fully polarimetric data contains maximum polarimetric information, the efforts of the researchers in this field is to achieve the nearest information from CP data to FP data. Therefore, in this research we have found the H-α boundaries of DCP data which maximize the total class agreement of classification results of the DCP and FP data for RADARSAT-2 sensor. Two images over San Francisco and Vancouver acquired by Radarsat-2 at C-band in quad polarization mode, with the image size being 1151×1776 and 1766×1558 respectively have been used for this study. In order to evaluate the ability of the proposed H-α zones in comparison with Zhang’s zones, Each experimental image is classified into eight PSMs. Confusion matrices have been achieved and the resultant mean agreements have been calculated. It has been shown that the proposed boundaries have increased the mean agreements of the results by 3%.
In order to extract the physical scattering mechanism (PSM) of targets using polarimetric data many classification methods have been presented. One of the most common such methods is Cloude–Pottier H-α decomposition that is proposed for FP data. Its principle relies on the analysis of eigenvalues and eigenvectors of the coherency matrix. Entropy and α-angle are two important parameters for the interpretation of fully polarimetric data which are extracted from this method. They indicate the randomness of the polarisation of the back scattered waves and the scattering mechanisms of the targets respectively. For fully polarimetric data an H-α classification space has been presented. This H-α classification space is devided by H and α borders and cllassifies 8 feasible PSM regions without the need for training data.
In recent years two approaches have been proposed in order to find dual H-α classification zones for DCP data. In 2012, Guo proposed an H-α classification space by mapping the points of each PSM from the original FP data into the space of H-α for DCP data and extract approximate borders. Subsequently, in 2014 Zhang proposed an H-α space on the basis of the distribution centers and densities of different PSMs. Experimental results showed that the classification accuracy of each PSM is improved compared with the results of Guo’s H-α space, however Zhang’s method is not well accurate and there are still overlaps between different PSMs. Both Zhang’s and Guo’s methods are not based on an optimization method. Therefore, they do not present optimum H-α borders for classification of DCP data. Furthermore, each sensor has its own specifications. One of which is the system noise floor which affects entropy borders for classification. Thus, it is important to find optimum H-α boundaries for each sensor separately.
In this paper we have proposed a novel approach for finding optimum H/α classification borders for DCP data. The optimum borders have been found in such a way to maximize the agreement of the H-α classification results of DCP data with the H-α classification results of FP data. ‘Mean class agreement’ is introduced and the borders which maximize this parameter have been found. The results of classification using the proposed borders have been compared with the rival method and the superiority of the proposed method has been revealed.

Classification is one of the prominent issue in processing of Hyperspectral images because of their variety applications such as urban planning, mining and military. Hyperspectral imaging due to high spectral resolution can provide much more information about the surveyed area. Ability of classifying objects in the scene can raise by using their spectral properties. However, the classification of Hyperspectral image is a very challenging issue because of their huge number of band. The large number of spectral bands in Hyperspectral data not only increases the computational burden but also can reduce classification accuracy. Moreover, there are usually high correlation between bands. Dimensionality reduction has become a crucial step for successfully classify Hyperspectral image and getting better results. Feature extraction by using the intrinsic dimensionality of the data is one useful approach to decrease the dimensionality. In this paper, Principle component analysis method using intrinsic dimension used as a pre-processing step to improve classification result. By using intrinsic dimension Estimation, can recognize proper bands number for processing and by PCA can extract optimal bands to perform classifications SVM, ANN and C4.5. The results reveal the implemented method can improve the overall accuracy of classified imagery nearly 5-10 %. ANN method with accuracy about 0.95 have highest accuracy among all methods.

Hyperspectral image contains hundreds of narrow and contiguous spectral bands. Because of this high spectral resolution, hyperspectral images provide valuable information from the earth surface materials and objects. By advances in remote sensing technology and production of hyper spectral data with high spatial and spectral information, using such data for a detailed study of the phenomenon is spreading quickly. One of the most important applications of hyperspectral data analysis is either supervised or unsupervised classification for land cover mapping. Among different unsupervised methods, Gaussian mixture model has attracted a lot of attention, due to its performance and efficient computational time. Gaussian Mixture Models (GMMs) have been frequently applied in hyperspectral image classification tasks. The problem of estimating the parameters in a Gaussian mixture model has been studied in the literature. Gibbs sampler is one of the methods that can be applied for this problem. Another method for estimation the parameters of a Gaussian mixture model is Expectation-Maximization (EM) algorithm. EM is a general method for optimizing likelihood functions and is useful in situations where data might be missing or simpler optimization methods fail .On the other hand, the large number of bands in a hyperspectral images leads into estimation of a large number of parameters. In the other point of view, the enormous amount of information provided by hyperspectral images increases the computational burden as well as the correlation among spectral bands. Thus, dimensionality reduction is often conducted as one of the most important steps before target detection to both maximize the detection performance and minimize the computational burden. In this paper, we use PCA and Random Projection (RP) for solving the high dimensionality of the data. In order to evaluate the proposed algorithm in real analysis scenarios, we used two benchmark hyperspectral data sets collected by AVIRIS and Reflective Optics System Spectrographic Imaging System (ROSIS). In order to evaluate the effectiveness of the proposed method which is based on the using GMMS and its parameter are estimated using Gibbs sampler method we used two well-known dataset ROSIS and AVIRIS hyperspectral images which they are acquired from a urban and agricultural area, respectively. Moreover, for better evaluation we used a simulated data which is attained using a toolbox which is known as HYDRA project. Investigations on the simulated dataset and two real hyperspectral data showed that the case in which the number of bands has been reduced in the pre-processing stage using either RP or PCA in the feature space, can result the highest accuracy and efficiency for thematic mapping. We also demonstrated that the superiority of the Gibbs sampler in comparison with EM algorithm for estimating the GMM parameters. For instance, in Pavia university dataset, the overall accuracy and Kappa coefficient was 88.80 and 0.84, respectively for GMM-Gibbs-RP method and for GMM-EM-RP method the overall accuracy and kappa coefficient was 84.21 and 0.80, respectively. In other view point, in urban area (Pavia university dataset) with small structures, the amount of improvement in by Gibbs sampler in comparison with EM algorithm was more than the AVIRIS dataset which is related to agricultural area with bigger regions. This shows the capability of Gibbs sampler in confronting with singularities.

Photogrammetry and Remote sensing researchers pay attention to urban phenomenon detection; such as building and tree from aerial and satellite image with LiDAR data in the recent decades. Different classification and detection methods in order to use in urban area faced with complex problems, such as small trees and buildings, unfavorable boundary crown, roof covered with vegetation , buildings that are surrounded by trees and vegetation located in the shadow. In this research to improve the problem mentioned above, in the first step the following works has been carried out, preprocessing LiDAR data That in the preprocessing step, noise and outliers of the LiDAR data detected by using Frist and Last Range images and then to calculate the proper height for them used the weighted averaging method than the distance, then at this step generation digital terrain model and normalized digital surface model that for generating digital terrain model the method local base filtering is used that has two stage 1- select training data 2- applying filter with using training data that all part of the first step is implemented in the MatLab 7.12 . In the second step geometrical, spectral, textural and combined features have been produced according to the mentioned problems that to produce these features used from normalized digital surface model and first range of LiDAR data. Then these features by using the SVM_GA algorithm for detecting suitable they are used. SVM_GA algorithm implementation is done in tow rounds, that in first round same features are evaluated with each other and in the second round selected features in first round are evaluated with each other. Finally after three times running SVM_GA algorithm 27 features are selected. From the production features vegetation index combined with shadow area and geometrical features produced from LiDAR data have crucial role for trees detection. In the third step support vector machine classification has been used in order to trees and building detection in the object-based and pixel-based levels with using suitable and selected features. Training data for pixel level classification with using SVM classifier are selected semi-automatically in four classes include road, tree, building and vegetation. For this purpose, the following features are used nDSM, Laplacian and Combined_IndexNDVI . for object-based classification with SVM classifier we use training data that they were selected manually and for segmentation of image we use multi resolution segmentation in eCognition 8 software by using the flowing layers, green, red, NIR and Frist range that segmentation parameters are set manually. In order to improving the results of each levels of classification in fourth step we improved with post-processing methods that in this step for both level of classification we have used erosion and dilation morphological filter with different size, so that in object-based level classification, segments of buildings divided into two group: high and low buildings so that for each group of buildings employed morphological filter with different size Separately and then for results of object-based classification we have used a conceptual process for improving object-based level classification. Due to high spectral similarity between two group buildings-roads and vegetation-trees and miss-classification, accuracy, correctness and quality of results have reduced. To improving results have been used neighborly relations and conceptual thresholds in five steps.In fifth step due to the power of each level classification, we try to improve buildings and trees detection with use to fusion object-based and pixel-based classification results, that in this step for building and tree classes have been used different fusion algorithms. The main basis of fusion for building’s class voting results of two level classification and for trees class height pixels in segments and again voting. Results show that fusion of pixel-based and object-based classification improve buildings and trees detection accuracy especially in small and low objects of trees and building also improve crown detection. Fusion the classification results for trees class has more improvement compared to buildings class. Object-based classification level due to using the segments and similarity between trees and vegetation leads to pixels of vegetation not be detected, that in the segments of trees and with use to fusion method for both level of classification, can be detected low and little trees. Results of this method with regards to improving detection in boundary of trees and buildings have positive effect for object extraction. Also suggested method can be detected building with low height and area. After post-processing for detected trees and building classes specified pixel level can be show more capable than object level in detect small object. Finally, results of detection and each levels classification evaluated with reference data, That buildings and trees detection in object level have correctness 0.961 and 0.65 and they have overall accuracy 0.97 and 0.943 respectively, and in pixel-based level they have correctness equal to 0.953 and 0.632 and overall accuracy 0.961 and 0.94 respectively. After the fusion they have correctness 0.971 and 0.718 and they have overall accuracy 0.975 and 0.957 respectively.

Most of common classification algorithms in remote sensing are based on spectral characteristics of pixels. These approaches ignore the spatial information of data, such as texture, in classification process. Simultaneous usage of texture and spectral information is a new trend in remote sensing image classification which has been considered in this study. We have evaluated the efficiency of gray-level co-occurrence matrix texture features (GLCM) extracted from panchromatic (PAN) image of ALI detector in improving the classification accuracy of Hyperion hyperspectral (HS) data in urban regions of Tehran. Classification is performed using a support vector machine (SVM) classifier with a Gaussian kernel. In our experiments, we have considered three different cases: a) classifying original Hyperion data, b) classifying Hyperion data pansharpened by color normalized transform (CNT), and finally, c) simultaneous use of GLCM texture features of panchromatic data and the spectral features of pansharpened data in classification process.In case b and c, for pansharpening HS data we have performed the following steps:1.Registering HS data with PAN data using ◦nineteen ground control points,◦polynomial warping of second order, and◦Nearest neighbor interpolation.1.Selecting a subset of HS bands which spectrally overlap with PAN image.1.Fusing the spatial information of PAN image into the HS subset bands, obtained in step 2, using CNT method.Moreover, as GLCM features, we have extracted 8 texture features from GLCM matrices: mean, variance, homogeneity, contrast, dissimilarity, entropy, angular second moment, and correlation. In order to assess the influence of the size of GLCM extraction window on the quality of texture features, we have considered various window sizes: 3×3, 5×5, 7×7, and 9×9.At the first phase of our experiments, we compared classification results obtained using the original HS data with the results obtained from the pansharpened HS subset – see Table 1. The results showed an increase of about 15% in the average classification accuracy when using the pansharpened data. At the second phase, we combined each of the texture features individually with the pansharpened HS subset. The results are given in Table 2. As the table suggests, regardless of the type of texture feature and the size of the GLCM extraction window, the combinations improve the overall classification accuracy (OA) of data. However, texture features show better quality when extracted from GLCM matrices obtained using 9×9 neighborhood windows. In addition, we observe that regardless of the size of GLCM window, dissimilarity feature delivers the best results.To summarize, by using the pansharpened HS subset instead of the original HS data, we achieved about 15% gain in the classification accuracy. Moreover, combining dissimilarity texture features –extracted from GLCM matrices obtained using 9×9 neighborhood windows– with the pansharpened HS subset improved classification results. In our experiments, we achieved about 5% increase in OA compared to that of using pansharpened HS subset alone.

Because of using the different polarization of electromagnetic wave in Polarimetric imagery، it provides a rich source of information from the several aspects of targets. Recently، Polarimetric images as a powerful and efficient tool have been interested to identify the various objects in the complex geographic areas. In order to extracting information، classification of Polarimetric image has an important effect. Support Vector Machines (SVMs) due to their operation based on geometrical characteristics and robustness in high dimensional space، are considered as a suitable case for classification of Polarimetric images. However، the performance of SVMs classifier is strongly influenced by its parameters. Therefore، the optimum values for SVMs parameters should be determined to achieve SVMs classifier with maximum efficiency. Traditional optimization techniques because of computational complexities in the large search space usually trap in local optimum. Thereby، it is inevitable to apply Meta -heuristic Algorithms which performe exploration and exploitation to obtain global optimum. In this paper، the potential of Genetic، Bees and Particle Swarm Optimization (PSO) Algorithms as powerfull techniques in determining the optimum SVMs parameters are evaluated. Comparing the results، demonstrates the superior performance of PSO Algorithm in terms of classification accuracy and speed of convergence.

To design path corridor based on construction cost, designers mainly notice to geometricaldesign factors and primary construction cost, while some other effectivefactors may be ignored. Environmental condition is another effective factor thathas a significant effect on recognition, selection and determination of path corridor.Examination of all environmental parameters is very important and if they can beprocessed simultaneously with other effective factors, many useful results will beextracted for optimum design. According to the proposed model in this study, asite in frame of GIS system was considered regarding to frequency of informationlayers and effective factors on recognition and determination of path corridor. Allgraphical maps and descriptive information for the site between two path ends wasentered as separate layers, and each layer was weighted proportional to its effectin decision-making, and money value is assigned to their components. Then alldescriptive and graphical information are classified by the software and processedby mathematical analytical methods and will be modified to cost map or total effectivevalue. Then a vector network is constructed onto this map by software, andinformation on cost map is transferred to the vector network upon view of designer.Finally, the best and the cheapest path is selected by the software upon differentalgorithms. This method increases precision of recognition of optimum variant orderly,introduces all possible variants in details, decreases evaluation time of variantsand cost significantly.