@article { author = {Kiani Shahvandi, Mostafa and Chegini, Nabi}, title = {Ellipsoidal spline functions for gravity data interpolation and smoothing}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {1-11}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.290542.1065}, abstract = {The aim of this paper is to study the theory of spline interpolation and smoothing problems on the surface of a triaxial ellipsoid for the Consecutive Iterated Helmholtz operator and a set of linearly independent evaluation functionals. Spline functions were introduced based on the minimization of a semi-norm in the context of a semi-Hilbert space whose domain was the surface of the ellipsoid. The semi-Hilbert space was decomposed into two different subspaces, a particular Hilbert space and the null space of the desired operator. Using surface Green’s functions for the Consecutive Iterated Helmholtz operator, the reproducing kernel for the Hilbert subspace was constructed. Spline and smoothing functions were explicitly represented based on the reproducing kernel and the evaluation functionals. An approximation formula was derived to facilitate the potential use in Earth’s gravity field data interpolation and smoothing. An application of this technique was presented to show the interpolation of potential fields over Iran. Ellipsoidal and spherical splines were compared as well. It revealed the ellipsoidal splines to be more accurate than the spherical counterparts.}, keywords = {Spline interpolant,Consecutive Iterated Helmholtz Operator,Minimization problem, Surface Green's functions, Evaluation functionals}, url = {https://eoge.ut.ac.ir/article_75662.html}, eprint = {https://eoge.ut.ac.ir/article_75662_9fd478aed2776b7fdc22895e66145243.pdf} } @article { author = {Afsharnia, Hamed and Arefi, Hossein}, title = {A quality assessment on the DEM matching-based RPC bias correction}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {12-23}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.286773.1059}, abstract = {Rational polynomial coefficients delivered by satellite image vendors facilitate the geometric processing of images. However, compensating the inherent bias of these coefficients requires in-situ ground control collection. Existing global digital elevation models are an alternative for in-situ control data collection. In this regard, the well-known DEM matching technique can be applied for aligning the image-driven DEMs with the existing global elevation models. In this study, three image-driven DEMs were generated using a commercial programming application. The commercial software, similar to the majority of other software packages, performs epipolar resampling using vendor-provided RPCs before image matching. These generated DEMs were imported to the DEM matching technique and the estimated matching parameters were utilized for correcting the bias of RPCs on the ground. We showed that epipolar resampling with vendor-provided RPCs imposes some geometric distortions to the generated DEMs and therefore, estimated that DEM matching parameters cannot be employed for RPC bias correction. In two study areas, while the geopositioning accuracy after bias correction was improved 95.6% and 93.1% using the commercial software, we achieved 97.8% and 97.4% improvement using the programming.}, keywords = {Satellite stereo images,RPC bias correction,Digital Elevation Models,DEM matching}, url = {https://eoge.ut.ac.ir/article_75663.html}, eprint = {https://eoge.ut.ac.ir/article_75663_bf3db620b92ed008226eead087b0d550.pdf} } @article { author = {Sahebkheir, Sanaz and Esmaeily, Ali and Saba, Mohammad}, title = {A new super resolution and deblurring algorithm for Magnetic Resonance images based on sparse representation and dictionary learning}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {24-38}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.285600.1055}, abstract = {Magnetic Resonance Imaging (MRI) provides a non-invasive manner to aid clinical diagnosis, while its limitation is the slow scanning speed. Recently, due to the high costs of health care and taking account of patient comfort, some methods such as Parallel MRI (pMRI) and compressed sensing MRI have been developed to reduce the MR scanning duration under the sampling process. It is almost unavoidable to accept some doses of X-rays in computed tomography (CT scans). If one could find a more efficient way to represent the required visual information, the tasks of image processing and medical imaging would become easier and less troublesome. In this paper, first, we used pMRI on complex double data of brain magnetic resonance image. pMRI significantly reduces the number of measurements in the Fourier domain because each coil only acquires a small fraction of the whole measurements. It is important to reconstruct the original MR image efficiently and precisely for better diagnosis. In this research, we proposed a new super resolution and deblurring algorithm with dictionary learning, based on assuming a local Sparse-Land model on image patches, serving as regularization, then we validated the proposed method by using another one called the adaptive selection of sub dictionaries- adaptive reweighted sparsity regularization. Visual comparison and significant difference in psnr calculation (0.8111db) and time complexity showed that the proposed method had much better results.}, keywords = {image processing,Magnetic resonance imaging,Sparse representation,Super resolution, Dictionary learning}, url = {https://eoge.ut.ac.ir/article_75664.html}, eprint = {https://eoge.ut.ac.ir/article_75664_3c82c7e9c86d06fb4f0dc5149b13812d.pdf} } @article { author = {Babaei, Ali and Saadat Seresht, Mohammad}, title = {Optimal selection of distortion model parameters for projection lenses ssing phasogrammetric self-calibration}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {39-50}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.286355.1058}, abstract = {Three-dimensional measurement of coordinates in different optical metrology techniques involves the measurement of image coordinates and/or phase values as observations as well as system parameters. These system parameters are usually determined through a calibration process. Self-calibration of digital fringe projection systems takes advantage of the fringe projection technique in a photogrammetric mathematical model. Many pieces of research have shown the capability of this technique which is called phasogrammetry, to achieve high accuracy and reliability. However, the difference between projection lenses and imaging lenses has not been investigated yet. In this paper, a set of experiments is performed to analyze the behavior of systematic errors in digital projectors as the basic component of this method. The results indicate that the well-known physical model of camera in close range photogrammetry might be used for digital projectors. The best results if the 3D measurement of the test object achieved where the first term of radial distortion K1 and the first in-plane distortion parameter B1 are involved in the self-calibration of the digital fringe projection system.}, keywords = {3D RECONSTRUCTION,Digital fringe projection,Self-calibration,Projection lens,Additional parameters}, url = {https://eoge.ut.ac.ir/article_75665.html}, eprint = {https://eoge.ut.ac.ir/article_75665_dd3e74482085b72c0c4041d75bc0c426.pdf} } @article { author = {Behzadi, Saeed and Mousavi, Zahra}, title = {A novel agent-based model for forest fire prediction}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {51-63}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.283932.1051}, abstract = {In recent years, forest fires have increased drastically due to global warming. Forest fire prediction is the best way to control the spread of fire. Therefore, several studies have focused on developing models that predict the behavior of forest fires. Predicting fire spread and its behavior is crucial to mitigate the adverse effects on weather conditions, environment, and human activities. Improving forest fire prediction using higher quality data can be expensive. In some cases, obtaining or even precise estimation of these data is difficult. On the other hand, using prediction models are more reasonable and feasible to increase prediction accuracy. In this paper, we introduced a novel Belief-Desire-Intention (BDI) agent-based model to predict the behavior of forest fires in the Mazandaran region in the north of Iran. This paper attempted to map the concepts of BDI agent architecture into generic GIS. A novel BDI-GIS model was then proposed in which an agent’s belief, desire, and intention were defined based on spatial or non-spatial data and GIS functions. Therefore, an agent-based model was developed to determine the prediction of forest fires and implemented it on a real dataset. The experimental results showed that the proposed model could be successfully applied to the real-world scenarios with a Kappa Coefficient of more than 68.2%.}, keywords = {GIS,Agent-based model,Forest fire prediction}, url = {https://eoge.ut.ac.ir/article_75666.html}, eprint = {https://eoge.ut.ac.ir/article_75666_bb57c46ecf25f291233a8e89e59b2a88.pdf} } @article { author = {Mahmoudizadeh, Saeid and Esmaeily, Ali}, title = {Development of a non-supervised and automatic method for detecting land cover changes in urban areas by using radar and optic data}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {64-76}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.288831.1062}, abstract = {Collecting updated and accurate land cover changes in urban areas have a significant impact on urban planning and management. In recent decades, remote sensing data have been used as valuable sources for detecting land cover changes. Given the different information that optical and radar sensors have received from any phenomenon on earth's surface, remote sensing data are assumed as complementary tools, and the integration of these two kinds of data will improve the results in detecting changes, especially in urban areas. In this research, a non-supervised and automatic method was developed to improve the detection of land cover changes in urban areas by integrating radar and optics data. Different spectral indices and radar polarizations were used to develop the CVA technique, known as an efficient non-supervised method for detecting the variations. In the implementation section, Sentinel 1 and 2 satellite data were used for the period of 2106 to 2018, captured from the northwest of Mashhad city, Iran. The developed technique was compared with other change detection methods. The findings of this study indicated the effectiveness and accuracy of the developed technique for detecting the changes. The estimated ratio of detected pixels to total pixels was 82%, which was promising. The overall classification accuracy and the kappa coefficient with values of 90.17 and 0.8016 were highest among the other methods used in the present study. The non-supervised approach and the verification results of the proposed method revealed its usefulness in detecting the changes, especially in urban areas.}, keywords = {Change detection,Image Fusion,Radar Polarizatio,Otsu,Change Vector Analysis}, url = {https://eoge.ut.ac.ir/article_75781.html}, eprint = {https://eoge.ut.ac.ir/article_75781_9db7151bf23f64da871fe62ac1c74b5f.pdf} } @article { author = {Damavandi, Hoorsana and Abdolvand, Neda and Karimipour, Farid}, title = {Utilizing location-based social network data for optimal retail store placement}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {77-91}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.271740.1041}, abstract = {Finding an optimized place is undeniably a momentous subject in establishing the marketing strategies of a retail store. Based on the existing literature, the process of selecting an optimized location for a business can be defined as a ranking problem that compares and rates existing or potential sites based on their ability to attract customers. Consequently, this article is concentrated on the evaluation of machine learning ranking methods in ranking existing retail stores based on the data derived from LBSNs. Using feature engineering techniques, we defined and calculated a set of features for 239 retail store branches in Tehran, from the venue data obtained from the Foursquare API. Additionally, we derived a rank for each store representing store popularity via user-generated data from Foursquare, Dunro, and Google Maps. Next, we implemented a number of classification and “learn-to-rank” algorithms to rate these stores. Finally, by evaluating the prediction precision and ranking precision of the algorithms used, we analyzed the fit and prediction power of all ranking algorithms. The outcomes of this research suggest that most algorithms used are, in fact, reliable methods for ranking retail store sites. Therefore, such algorithms can be used as a technique for retail store site selection, given a list of existing or potential sites for a store. Additionally, our results clearly suggest a superiority in the ranking precision of “learn-to-rank” algorithms for retail store placement. Out of all algorithms used, with a ranking precision of 0.854, MART is the most powerful algorithm for ranking retail store sites.}, keywords = {Retailing,LBSN,Geomarketing,Feature Selection,Machine learning}, url = {https://eoge.ut.ac.ir/article_75927.html}, eprint = {https://eoge.ut.ac.ir/article_75927_77b93d9b7e4d889d8e7dbeb42190a294.pdf} } @article { author = {Niazmardi, Saeid}, title = {A spatial-spectral classification strategy for very high-resolution images using region covariance descriptors and multiple kernel learning algorithms}, journal = {Earth Observation and Geomatics Engineering}, volume = {3}, number = {2}, pages = {92-98}, year = {2019}, publisher = {University of Tehran}, issn = {2588-4352}, eissn = {2588-4360}, doi = {10.22059/eoge.2020.285999.1057}, abstract = {Extracting and modeling the spatial information content of very high resolution (VHR) images can dramatically increase the performances of urban area classification. However, extracting spatial features is a highly challenging task. During the years, several spatial feature extraction methods have been proposed, most of which are mainly designed for grayscale images. To use these methods for a multispectral image, usually, a dimensionality reduction step is required. As a result, these methods cannot optimally extract the spatial information contents of different bands of a multispectral image. To address this issue, we proposed the use of the region covariance descriptor (RCD) for spatial feature extraction from VHR images. The RCD features consider the covariance matrix of a local neighborhood of each pixel as the features. These features can model both the spatial information and the spectral relationship between bands. The RCD features lie in a Riemannian manifold, on which the common classification algorithms cannot be applied. To overcome this, we used Riemannian kernel functions. Also, we proposed a multiple kernel learning strategy for combining RCD and spectral features. The proposed strategy was evaluated for classifying a VHR image acquired over the urban area of Tehran, Iran. Furthermore, its obtained results were compared with those of ten other common spatial feature extraction methods. The results showed that the proposed classification strategy using the RCD features yielded at least 5% higher accuracies than the other feature extraction methods.}, keywords = {Covariance descriptors,Region covariance descriptors,Multiple kernel learning,high resolution,Urban classification}, url = {https://eoge.ut.ac.ir/article_76072.html}, eprint = {https://eoge.ut.ac.ir/article_76072_fde4feef3e5dd8d9d7b8744cf32f07a2.pdf} }