It is necessary to know about the quantity of urban tree canopy cover due to its role in air and noise pollution reduction, wind prevention, saving rain water, and runoff control. Being expensive and time consuming, the manual extraction of tree canopy has been replaced by remote sensing techniques conducted on the images, digitally. There are several parameters which must be optimized prior to use of Object oriented classification. One of these parameters is Scale affecting the segmentation results, significantly. Scale is usually set by trial and error which is an experimental approach. One of the aims of this study is to optimize Scale parameter, automatically. In addition, after segmentation process based on a proper Scale, it is required to classify the identified segments based on the attributes which are extracted from these segments. In this stage, the selection of suitable classification method fed by the proper attributes is critical. In this research, LiDAR data and aerial image acquired on Vaihingen, Germany, were utilized for segmenting the urban area. In order to identify suitable attributes, random forest feature selection was applied on the attributes derived from the identified segments. Machine learning methods including support vector machine, random forest, and decision tree were compared for classifying the segments based on their suitable attributes into two classes including tree canopy cover and others. The results indicated that Scale of 25 is the best one to segment this area. Also, the tree canopy cover map derived from support vector machine with quality index of 79.90 showed the best performance among different classifiers used in this study.

Damage caused by the sand dunes movement is one of the most important environmental and socio-economic issues in desert region. erosion and wind processes study began with the work of Bagnold (1954). After significant advances in laboratory and physical approaches to the elements and forces involved in wind erosion and at the contemporary with the development of remote sensing tools and data and changes in methods and algorithms for interpreting aerial photographs and satellite images, the rapid emergence of planetary geomorphology and the search for analogies and similarities on other planets. Rapid developments in the geomorphology of wind processes took place. Using Landsat, ASTER and Quick bird images and LIDAR data, many studies have been done to classify sand dunes. After the launch of two ERS remote sensing radar satellites in 1991 and 1995, the value of CCD Was considered. But in Iran, most of the studies conducted in the desert region, such as the Damghan playa, have studied the changes in long-term periods, which are mainly of sediment origin and classified sand dunes using multispectral satellite data. The aim of this study was to use Sentinel-1 IW SAR time series data in arid regions to detect surface changes in the short term due to wind morph dynamic activity and on the other hand to evaluate the effectiveness of using both radar and optical data and Object-oriented classification model in the events and morphological changes detection of sand surfaces and forms. the results obtained from the processing of remote sensing data and classification and achieving the dimensions of sand dune mobility with the results of wind data analysis will be evaluated and verified. Materials and methodsDamghan plain located in Damghan plain with longitude 54 10 to 54 40 east and latitude 36 36 to 36 10 north has a hot and dry desert climate and an average rainfall of 100 mm per year, which due to the desert nature, is prone to wind morph dynamic performance. Therefore, in the present study, we aimed to evaluate the mobility of sand dunes as part of the natural hazards active in the region. The research method is library, remote sensing and surveying. Data analysis is based on two main concepts,segmentation and classification. Initially, based on geological and topography maps and field survey, geomorphology maps were created. Then based on the prepared and adapted maps and field surveillance, sandy forms were limited. Then, in order to determine the working units, using the CCD technique with Sentinel-1 radar images, the active and inactive parts of the sand forms were detected. Two radar interfrograme (Master and slave) related to the two dates of 14/05/2017 and 22/03/2018 were used to extract the CCD (based on phase difference). Finally, with the identification of work units, automatic detection and extraction of sand dunes was targeted, and for this purpose, the bottom-up hierarchical Object-oriented method and top-down classification using the growing region technique was used. Also, by extracting sand dunes using Object-oriented classification, the values and direction of moving the dune were extracted using Guy, 1995 optimized model and the corresponding sand rose were drawn. Wind rose analysis and drawing related to wind statistics of Damghan synoptic station (the closest meteorological station to the study area) in the statistical period of 1384-96 was also performed with the aim of verifying the findings of the previous step. Result and discussionA: Extract sandy formsImage enhancement is the first step in preparing an image for the extraction of image elements (including sand dunes). Due to the importance of the dune slip face, in the process of identifying the displacement and sand dunes movement, and its lower compaction coefficient than other parts of a sand dune, in order to detection This enhance method, by using the most abundant discontinuity search, distinguishes brighter borders that forming sand dune steep slope from other parts of dune and around environments. The output of this filter is an image in which the sand dunes slip face, with different radiometric intense, is marked from the surrounding sand surfaces. B: Detecting and extracting sand dunesIn order to evaluate the displacement amount and direction, the Object-oriented classification paradigm was used to automatically detect the edges as dune front. Instead of just evaluating pixels, the spatial pattern of Objects and forms is also considered. Therefore, the initial segmentation was performed using a scale factor "100" that determined the maximum heterogeneity in the diagnosis of the forms. in addition to using radiometric values, classes can be formed based on geometry and related elements. The rules used are Brightness and Compactness. First, by analyzing the values of average brightness with a threshold of 165, the overall sand dune pattern as the first layer was created. Then, using the Compactness rule, the pixels that were recognized as the dune slip face by the spectral feature in the previous step were eliminated from the classes. C: calculation the sand dunes amount and direction displacement. Sand dunes displacement calculated by considering the end edge, as the progressive edge at successive times and measuring the distance between two consecutive lines in two consecutive years. To evaluate the dunes movement direction, the axis of symmetry of each hill was selected as the main axis and the initial and final point of this line on the downwind front of sand dunes in both the first and last years were considered. The azimuth line or the direction of movement relative to the north was drawn and this angle was calculated and its sand rose with an angle of 135 degrees was drawnConclusion This study, suggested a new approach to detect sand dynamics using radar InSAR techniques and Object-oriented classification using high resolution optical images. The results of InSAR processing, and CCD technique, was able to recognize active and inactive sand dunes dynamic, and display them in continuous numerical values (fully active to fully stabilized hills). The application of OBIA on Bird’, s eye and Geo eye images (2003-2016) results, indicates that the 22. 4 m movement of hills is mainly in the southwest direction in a period of 13 years and 1. 7 m for each year. The result of comparing wind rose (wind data analysis) and sand rose (sand movement data analysis) shows a significant relationship between 80% of northwest-southeast wind frequency in relation to 135 °,azimuth for 75% of sand dunes movement and 15% of north-south wind frequency in relation to 180°,azimuths of 25% of sand dunes movement.

Precipitation rate and amount measurements are among the flood warning methods which have been suggested by remote sensing in recent years. Cloud type identification and classification, as basic principles of precipitation estimation methods, are usually performed using visual interpretation of satellite images. In these studies only cloud brightness temperature and albedo are used for cloud classification, while texture and shape of clouds are effective properties in cloud type detection as well. Textures and shapes of clouds are ignored in pixel base classifications. So Object- oriented classification technique is a suitable approach. In this technique, in addition to cloud brightness temperature and albedo, textures and shapes are the major parameters. Object-orient classification method, despite its benefits, depends on segmentation accuracy. The accuracy of segmentation is scale dependent too. Therefore, optimum segmentation scale is resulting to higher accuracy of Object oriented classification. In this study two NOAA/AVHRR images in two consecutive cloudy days in August 2005 are used. In the first step, additional information included brightness temperature of band 3 and 4 and cloud height produced from NOAA/AVHRR images that used in image segmentation, and bi-spectral method has been employed for training region selection. Then the negative impacts of under-segmentation errors on the potential accuracy of Object-based classification were quantified by developing a new segmentation accuracy measure. In this step, scale evaluation was performed with quantifying overall effect relative to features and units in 31 scales of segmentation.The results based on a NOAA/AVHRR satellite images were the same and indicate that: (1): cloud segmentation accuracies decrease with increasing segmentation scales, and (2) the negative impacts of under-segmentation errors in cloud segmentation become significantly large at large scales. Hence, the finest scale for cloud segmentation has been defined 50 as in this scale the overall accuracy of classification was 90.5% in cloud Object oriented classification.

Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements that are essential for decision-makers. Therefore, the accuracy of maps obtained from the classification of satellite images is very effective in uncertainty for urban management. Due to the uniform quality of images in large areas at regular intervals, remote sensing images are essential for land use maps. The primary purpose of this study is to present a proposed method to create an accurate land cover map in urban areas using a combination of Sentinel-1 and Sentinel-2 data. For this purpose, the features of the backscattering coefficient VV and the two parameters obtained from the H-α decomposition method (entropy, alpha) of Sentinel-1 radar images and the features of the blue, green, red band, NDVI, NDWI, MNDWI, and SWI were extracted from Sentinel-2 Multispectral images and used as influential components to classify the urban area. To separate agricultural areas from other coatings, the SWI index was used. Elevation data have also been used to optimally distinguish complex classes with different topographies. We evaluated the extraction of effective indicators from these two datasets in an Object-oriented approach based on support vector machine algorithms and random forest for land use classification. The results showed that using properties extracted from radar and Multispectral images simultaneously in the Object-oriented classification method could altogether determinate the Object's properties in the study area. When optical and radar data were used simultaneously for both classification algorithms, the overall accuracy classification increased. For the stochastic forest method, which provided the highest accuracy, the overall accuracy for the radar and optics data combination approach increased by 13% and 5%, respectively, compared to the radar feature approach and the optics feature approach alone. There was also a significant difference in classification accuracy at all levels between the support vector machine classification algorithm and the random forest. The results showed that the random forest classification method's overall accuracy and support vector machines were 83.3 and 79.8%, respectively, and the kappa coefficient was 0.72 and 0.68%, respectively.

Background and Objectives: Locating in arid and semi-arid region, Iran is always affected by sloping instability and erosion, especially gully erosion. This erosion pattern has occurred in different parts of Iran continuously over many years, and during erosion process and transferring the high amount of sediment has caused the destruction of roads, infrastructures, pasturelands, hillslopes, etc. which makes it necessary to identify high-risk areas and to develop sensitivity maps. In recent years, the processing of satellite images as an advanced method with the aim of increasing the accuracy and saving time and cost has been widely used by researchers. The Object-oriented analysis of images is one of the most important methods for extracting information from satellite imagery, which is based on spectral, form and spatial characteristics and using expert knowledge to identify complications. Materials and Methods: In this research, the Lighwan watershed was studied as one of the most important sub-basins of Aji Chay in the East Azarbaijan Province. The images of Sentinel-2 (2016) with spatial resolution of 10, 20 and 60 meters were used for the processing and identification of gully erosion sites. The images were processed using the eCognition software and applied with different types of algorithms to design a semi-automatic model based on Object-oriented analysis. Finally, in order to evaluate the accuracy of the model, the identified gully affected area were mapped out and calculated using ArcGIS software to match the ground truth map and to calculate the error matrix, manufacturer accuracy, user accuracy and kappa coefficient for each of the algorithms. Results: The results showed that the density and compactness algorithms had the highest and lowest accuracy of the manufacturer (manufacturer accuracies were 88 and 78), respectively. While based on Kappa coefficient, the asymmetry algorithm had the highest accuracy compared to other methods (kappa = 0. 91). Then, the shape index and density algorithms with kappa coefficient of 0. 89 and 0. 85 provided acceptable accuracy for the classification and identification of the gully. Conclusion: In the present study, semi-automatic semi-automatic model for ditch identification was presented using spectral and geometric properties of Sentinel-2 satellite images and Object-oriented processing in eCognition software environment. The use of Object-oriented methods due to the increased accuracy of classifying and identifying surface effects and phenomena can be used as a suitable solution for future soil studies and natural phenomena.

Optimal natural resources management depended on reliable as well as up-to-dated data. For this mean, land use/ cover maps are considered as an important source of information on the natural resources management. Nowadays, remote sensing users could be able to derive different land use/cover maps from satellite images by using specific interpretation techniques. Some characteristics of Satellite images such as: digitally format, production up-to dated data, wide viewing angle (swath width), multispectral as well as multi temporal and revisiting time of data acquisition with high speed on data transformation make those be considered as valuable information on the natural resources management. In this research, land use/cover map of study area has been produced based on digital interpretation of SPOT5 satellite image (2005) by Object oriented method. Based on proposed methodology, some pre-Processing practices which involve geometric and radiometric correction were implemented by applying Pci Geomatica 9.1 software. Image processing was conducted on the next step based on Object oriented method by applying eCogenation software. Followed step related to classifying of SPOT image based on proposed classes (18 classes: irrigated agriculture, dry farming area, bare soil, apricot orchards. Apple gardens, vineyards…). Finally, accuracy of classified image was assessed by fulfilling of error matrix and calculating of overall accuracy as well as Kappa Coefficient. Result of overall accuracy assessment was calculated 93.43%. It was confirmed the reliability of classification results. Final step was proposed to implement geo database into GIS environment for both illustration of produced map and comparing with former which was derived by pixel method. Results of this research showed, by Object-oriented method one be capable to produce land use/cover maps simultaneously with high accuracy and more classes.

Planning and optimal use of resources and controlling and unprincipled changes in the future, requires studying the extent of change and destruction of resources. In fact, planners for principled decisions must have a full knowledge of land use, detection, prediction of land use change and land cover in order to better manage natural resources in the long time. The aim of this study was to evaluate the accuracy of different supervised classification algorithms of basic and Object-oriented pixels in land use extraction in Samalghan watershed in three periods of time 1987, 2002 and 2019. The results showed that the support vector machine algorithms for the images of 1987 and 2019 and the neural network for the 2002 image in the pixel-based classification method have the highest overall accuracy and kappa coefficient. Also, the most obvious change that can be seen by comparing the prepared user maps is the change in the level of land uses with the growth of residential areas, thus this expansion has been continuously associated with a decrease in rangeland land use. Thus, from the years of 1987 to 2019, the residential land use area increased by more than 9. 197 km2 and dryland lands during these years increased by 130. 89 km2, irrigated agricultural lands also increased from 44. 45 km2 and Rangeland use has also decreased by 272. 3 km2.

Introduction: classification is one of the important methods in extraction of information from digital satellite images. The traditional methods of classification are based on the value of individual pixels in the images which are reflected from territorial features. The ability of pixel based approach in the satellite image classification is limited, when Objects have similar spectral information. This circumstance reduces the classification accuracy. Then in this approach the image cannot be classified correctly. The classic pixel-based approach is based on “binary theory”. By this theory, one pixel will be labeled to a class or is not assigned or remains unknown or not classified. In the case of the pixels in the overlapping areas of the feature space, by binary theory, those pixels will be labeled into only one class but they show the affinity with more than one class. With binary theory the classification result will not be accurate.But Object oriented image analysis approach is the procedure in image analysis that combines spectral and spatial information. This approach segments the pixels into Objects according to the tone of the image and classifies image by treating each Object as a whole. Utilizing the texture and contexture information of the Object in addition to using spectral information, Object orient image analysis has more powerful image analysis ability. The basic theory of Object oriented approach is the fuzzy theory, in the case of the overlapping area in the feature space, pixels in the overlapping areas will not be classified only into one information class, which is not correct in the real world, but are given different membership to one (with the value 1) or more than one (with the value between 0 to 1) information classes. This approach of classification is soft classifier (for example fuzzy system), which uses a degree of membership to express an Object’s assignment to a class. The membership value usually lies between 1.0 and 0.0, where 1.0 expresses full membership (a complete assignment) to a class and 0.0 expresses absolutely non-membership. The degree of membership depends on the degree to which the Objects fulfill the class-describing conditions. The main advantage of this soft classifier lies in their possibility to express uncertainties about the classes’ descriptions. It makes it also possible to express each Object’s membership in more than just one class or the probability of belonging to other classes, but with different degrees of membership. This classification can be done by the algorithm of nearest neighbor. The nearest neighbor is applied to selected Objected features and is trained by sample image Objects. The fuzzy realization of the nearest neighbor approach which is used in eCognition software automatically generates multidimensional membership functions. They are suitable for covering relations in multi-dimensional feature space.  The nearest neighbor classifies image Objects in a given feature space and with given samples for the class of concern.Materials and methods: In this study the maximum likelihood classification (MLC) of pixels based and nearest neighborhood of Object oriented (O.O) for classifications of satellite images are compared. This comparison is done by extracting the land cover of west Azarbaijan province. To compare these methods we used satellite images of SPOT 5 to extract land use maps of the case study area. To do so, in pre-processing stage of images, geometric correction including georeferencing, orthorectification and atmospheric correction were implemented. In processing stage, images after enhancement were classification in two ways. Frits, pixel-based classification was done based on Maximum likelihood algorithm, then Object oriented classification was implemented by using the nearest neighbor algorithm in eCognition software.Results and discussion: After satellite images classified by two methods, to evaluate and compare the results, overall accuracy and Kappa coefficient of the frame were extracted for each algorithm and it was determined that in pixel-based classification algorithm , the maximum Likelihood approach with overall accuracy of 88.37% and Kappa coefficient of 0.87 has lower accuracy in comparison with nearest neighbor algorithm, because Kappa coefficient of classification in nearest neighbor algorithm in Object oriented method estimated about 0.94 while overall accuracy was about 95.10%. This means that “O.O” approach has almost 7% improvement in the overall accuracy and the Kappa indices. In another word, the Object oriented image analysis can be the best method in classification of satellite images compared to pixel-based algorithms.Conclusion: This research has been done to compare pixel-based algorithms and Object oriented image analysis in classification of digital satellite images. The results of this research showed classification based (O.O) method provides more precise results in satellite image processing. Also it will be better to consider geodatabase and calculating geometric characteristics of each land use class in the pos-processing stage. The outcome of the research has been applied in the land cover extraction of East Azarbaijan province and extracting the land use changes of Satarkhan dam basin for the period of 30 years.