نشریه علوم و فنون نقشه برداری
سال نهم شماره 1 (پیاپی 33، تابستان 1398)

Because in Iran, flood phenomenon has the highest financial losses and death tolls among the natural disasters, thus reducing the damage caused by it has been considered for a long time and it is regarded essential. The most urgent action to deal with this natural disaster is to make preparations and take measures to reduce its harmful effects. One of the basic measures in this regard is the recognition of flood-stricken areas and the zoning of these areas in terms of the risk of flooding or runoff production. As a result, it is possible to decide on the use of land and various applications, such as agriculture, urban, industrial, etc., and minimize flood damages. In this study, first the factors affecting flood formation such as geology, precipitation, drainage density, distance from the waterway, concentration time, slope, aspect, soil material and land use were identified. Then, using the GIS capabilities and the fuzzy hierarchical analytical method, the zoning map of flood gas potential of the Tajan basin was prepared in five classes of very low, low, moderate, high and very high floodwater potential. Accordingly, 0.51% of the basin areas have very high runoff potential, 5.48% of the regions are with low runoff potential, 29.09% are with medium run runoff potential, 52.4% are with high runoff potential and 12.52% are with very high runoff production potential. Also, the range of Sari city is in the range from medium to high runoff potential, and 87 of the 441 villages in the studied area have very high runoff potential and are in the danger zone. In general, the situation of the roads in the basin is not suitable for the runoff production potential, and the main parts of the roads in the catchment area, including the main roads such as the parts of the Sari-Semnan axis, have very high run runoff production potential. Flood Damage alleviation both by structural or Non-Structural measures firstly requires accurate identification of study area in terms of flood risk or runoff production potential. This is more important due to financial limitations and the lack of an integrated management perspective. The presence of a zoning map of runoff production potential in Tajan basin is more important as it is located in border of Mazandaran and Semnan provinces and since some of the flood-prone areas are located in Shirin Rood tributaries at Chashm district of Semnan province and its floods impose substantial damage to downstream areas in Mazandaran province. Hence, this zonation map and its results, i.e. identifying runoff prone areas, assist us to define, complete and develop watershed project at   upstream of flood-prone areas with high runoff potential with holistic view as well as proper prioritization in management decisions. Also through management of the financial and human resources, roads prone to flooding can be secured and it helps to prevent the establishment of industries and population centers and the implementation of civil constructions and projects in the high risk areas. At the same time   in credit and budget allocation for flood and education areas with high runoff generation potential are prioritized. It is also possible to consider the zoning map of runoff production potential in the selection of plowing and furrow methods, tillage and flood protection and flood control measures.

Auto-navigating of unmanned aerial vehicles (UAV) in the outdoor environment is performed by using the Global positioning system (GPS) receiver. The power of the GPS signal on the earth surface is very low. This can affect the performance of GPS receivers in the environments contaminated with the other source of radio frequency interference (RFI). GPS jamming and spoofing are the most serious and intentional RFI attacks. Due to the jamming attacks, the positioning accuracy of UAV will be degraded. This positioning error can be reached to tens of kilometers off the true location as was reported in some research articles. The detection of GPS jamming is the first step to mitigate this attack. Most of jamming detection methods are based on GPS signals processing. If a jamming detection system just relies on GPS signal processing to detect and confront RFI threats, it will be capable of failure in the use of the more advanced hardware and sophisticated methods by invaders intentional. The camera is a common sensor almost in all of UAVs which is a passive sensor and resistant to the jamming signals. Here, the use of image-based navigation methods for GPS jamming detection will be helpful due to the insensitivity of camera sensors to jamming signals. GPS jamming attacks can be detected in UAV navigation, independently of the signal processing methods, using a comparison of two flight trajectories assigned for a UAV, determined from visual navigation and GPS positioning data. For this purpose, the trajectory descriptor of the Normalized Distance of the Consecutive Points (NDCP) and trajectory descriptor of the Consecutive Directions Angles (CDA) is used. These descriptors are independent of the coordinate system of the trajectory but are not independent of the number of trajectory points. As a result of the jamming attacks, the GPS receiver may not be able to receive the signal and the positioning cannot be performed. Therefore, two trajectories of UAV from GPS and visual navigation may have a different number of points. So, the NDCP and CDA cannot be used for these trajectories in all the time. The trajectory descriptor of Histogram of the Oriented Displacements (HOD) is independent of the number of trajectory points, but it is not independent of the coordinate system of the trajectory. In this paper, a method is developed to allow the use of the HOD trajectory descriptor to detect the occurrence of the GPS jamming attacks. For this purpose, first, the coordinate system of the UAV trajectory from GPS data is transformed to the coordinate system of the UAV trajectory from visual navigation. Here, a sliding window-based approach is used for determining of the jamming location. The performance of the HOD trajectory descriptor in detecting jamming attacks versus the NDCP and CDA trajectory descriptors were compared. The results show that the HOD trajectory descriptor has a significant advantage in detecting the jamming attacks concerning NDCP and CDA trajectory descriptors, especially in the positioning errors of more than ten meters due to jamming attacks, which can be more reliable. This descriptor can be used to detect the occurrence of the jamming attacks. The ability of the HOD trajectory descriptor is significant in detecting positioning errors greater than five meters, compared to the other two trajectory descriptors.

With the increasing popularity of sharing media on social networks and facilitating access to location technologies, such as Global Positioning System (GPS), people are more interested to share their own photos and videos. The world wide web users are no longer the sole consumer but they are producers of information also, hence a wealth of information are available on web 2.0 applications. The shared media usually contain geo-tagged locations, time stamp, hashtags, and comments. As such, mining social networks can yield extensive knowledge about human dynamics and mobility behaviors within urban context So web users are no longer just users but also producers of information This wealth of information can be leveraged for location-based services. If the locations visited by users are collected and sorted according to the timestamps, the sequence that the user has visited can be determined; exploring of which can be used in tourism planning. Recently, there is an increasing tendency to adopt the information from these geo-tagged photos for learning to recommend tourist locations. For a tourist, before traveling to an unfamiliar city, the most important preparation is planning the trip. without any prior knowledge, tourist must either rely on travel books, personal travel blogs or combination of online resources and services. It is difficult and time consuming and painstaking to find out the locations worth to visit and figure out the order in which they are to be visited. Hence, the purpose of the present study is to provide a framework for recommending locations and travel sequences to tourists by using geo-tagged photos in social networks. Most existing methods for tourist recommendation do not consider context constraints, or at best, address a few dimensions of contexts. The present work aims to develop a context-aware recommender system that recommends interesting locations and the travel sequence. The proposed method is designed such that it can use the collective wisdom of people from collection of geo-tagged photos in order to provide a set of tourism locations and interesting trip sequences that matches the user's current context given a city that is unfamiliar to that user.  first Due to the low accuracy of positioning with GPS embedded in mobile phones to find a unique pair of geographic coordinates for a tourist place the geo-tagged photos were clustered. For this reason OPTICS clustering method exploit to group geo-tagged photos by their locations. It then uses the combined method, to annotate all of the clusters that are created in the previous step with semantics. Then, we create a profile for clusters by using historical context (time stamps and weather). After that, we generated a travel sequences database and rated the sequences in the database according to their context. Finally In order to evaluate the performance of the proposed method, Panoromia site dataset of one region in Tehran was used and Experimental results showed that 64.5% of the results obtained by our proposed strategy are identical with the user preferences, which illustrate rationality of the recommendation from analyzing the geo-tagged photos.

In recent years, developments in unmanned aerial vehicles, lightweight on-board computers, and low-cost thermal imaging sensors offer a new opportunity for wildlife monitoring. In contrast with traditional methods now surveying endangered species to obtain population and location has become more cost-effective and least time-consuming. In this paper, a low-cost UAV-based remote sensing platform is introduced. It is a small, low-cost, flexible remote sensing platform, which was accomplished object detection, classification, and measures the accurate GPS coordinates of animals in wild or agriculture areas.
The paper describes both hardware and software architecture of a UAV such as thermal image sensor, an RGB camera, on-board computer, object detection, and recognition algorithms. While flying the onboard computer run a developed program to achieve real-time detection and path planning. The proposed system proved to be capable of detecting 83% of animals with a spatial accuracy of 2.17 meters.

Rice is considered as one of the most strategic plants in Iran. The production of rice has been confronted with new challenges since the year of 2000, so the necessity of supporting policies implemented by all relevant authorities has been revealed more and more. Average rainfall records in Gilan province, a rice-favored tropical region, often show a range of 800 ml – 2000 ml with the latter number knowns as the desirable quantity for rice farming. Generally, rice farming needs humidity of 70-80 per cent and Gilan province is well-known for its tropical climate that formulates the necessities for successful productive rice farming industry in this specified district. Long tedious hours of work roughly reach out to 1050-1400 hours for each hectare of rice farm so that all three stages of the rice farming process could be completed respectively. This long hours of work commands stretched hours of pay for the staff that may leave the business overdrawn in the long run. With population overgrowth and lack of unlimited resources, a need for research and development in terms of optimized rice productivity, is inevitably on the rise. Each advanced plan that guarantees higher product yield with better quality boosts the country one step closer to economical and political independence. A comprehensive knowledge over rainfall locations and its seasonal changes enhances the farming productivity and plays key role in the agricultural risk management and its crops insurance. Considering rice dominance in Iran’s farming, use of old fashioned methods in evaluation of the damages imposed by different hazards; such as heavy rainfalls, seems defectively inefficient due to the fact that the surveys are conducted in a very short period of time with a great deal of cost. 
Recent developments in the field of Remote Sensing (RS) have popularized the technique; as it offers unique vast insight, high levels of data transition speed, and availability of field-specialized software/hardware. In this research, TRMM_3B42 data which is known as TRMM data (version 07), is utilized for measuring precipitation.
In an attempt to evaluate the efficiency of TRMM in reporting the damages occurred to Gilan’s province rice farms, Pearson correlation coefficient, was compared among processed data and the gathered observational results separately across the larger states where rice farms cover the area of 15 hectares and less than that, also few villages in Rasht district so that the results indicate the promising use of method in Gilan’s province ultimately since Pearson correlation coefficient between calculations and observations equals to 0.945, so it is meaningful in the statistical level of 1%, although in the occasion of smaller villages its efficiency was graded as poor.

In recent years, Iran has faced serious water scarcity and excessive use of water resources. Therefore, exploring the pattern of urban water consumption and the relationships between geographic and demographic parameters and water usage is an important requirement for effective management of water resources. In this study, association rule mining has been used to analyze the data of municipal water consumption in Esfahan urban areas. Association rules mining have been used to discover the connections between geographic and demographic parameters including the number of family members, the number of apartment units, residential building types, areal coverage of the house and green spaces, distance from river and central of city, spatial location, distance from main road, population density and percentage of young population with water consumption patterns. A version of Appriori algorithm with less computational volume that can processes large amounts of data has been used for association rule mining. Each of the extracted rules that satisfy minimum support equal 30 and minimum confidence equal 60 reflects the relationship of each spatial and demographic parameters with the consumption water. Then, the obtained rules have been evaluated and water consumption hot spots were extracted. Results shows that distance from the main road, areal coverage of the residential and green spaces have direct relationship with the household water consumption. On the other hand, number of residential units, population density, distance from river, X and Y value and percentage of young population are inversely related to household water consumption. Also, if the distance from the city center increases, household water consumption decreases. Moreover, the southern areas of the city by minimum distance from the river have the highest water consumption and specified as hot spots. In these neighborhoods, building types are villa and have a lower population density with higher area of green space and yard than others.

Infant's head circumference measurement and and its growth monitoring plays a crucial role in diagnosis the diseases which cause a deformation in the infant's head. Due to the fact that the contact measurement, which is performed using a tape measure and a caliper, has problems such as transmitting disease, infecting, not comfortable and disruption relaxing the baby, going to non-contact measurements is unavoidable. The purpose of this study is to provide a non-contact image based method for measuring the infant's head circumference. In this study, an algorithm was developed that calculates the infant's head circumference using an image taken above the infant's head and the scale index next to the head. The first step in calculating the head circumference is detecting and segmenting the baby's head in the image. In this regard, two the state of the art deep learning algorithms, MaskR-CNN and CRF-RNN, were compared in this study for accurately segmenting the infant's head. Subsequently, the head circumference pixels were detected by a fusion of the Canny edge detection and morphology algorithms. In the next step, the ground sample distance at suitable level was calculated using the scale tag in the image. Finally, the head circumference was calculated using the ground sample distance value and the number of pixels forming the head circumference. The evaluations show that the MaskR_CNN method with a total accuracy of 98.8% is a more appropriate method than the CRF-RNN method for detection and segmentation of the head in the image. Also by comparing the results of the proposed algorithm with the actual values obtained by strip meter on 10 images, it was found that the error of the proposed method is about 1 to 3%.

The industry development and the life standards increment have caused the human feels more easement, but it also has caused an increase of energy consumption, environmental pollution and the large volume of greenhouse gases emission.
Those changes make the researchers to find out the alternative energy sources such as renewable energies. The most prominent and the oldest source of clean and renewable energies is hydropower.
There is no international consensus on the definition of small scale hydropower. In Canada 'small scale' can refer to upper limit capacities of between 20 and 25 MW, in the United States 'small scale' can mean 30 MW, however, a value of up to 10 MW total capacity is becoming generally accepted. Small scale hydropower can be further subdivided into mini hydro (usually defined as <500kW) and micro hydro (<100kW). No matter how you define it one thing remains the same, small scale hydropower is one of the most environmentally benign forms of energy generation available to us today.
 
Small scale hydropower systems capture the energy in flowing water and convert it to usable energy. Although the potential for small hydro-electric systems depends on the availability of suitable water flow, where the resource exists it can provide cheap clean reliable electricity. A well designed small hydropower system can blend with its surroundings and have minimal negative environmental impacts. Moreover, small hydropower has a huge, as yet untapped potential in most areas of the world and can make a significant contribution to future energy needs. It depends largely on already proven and developed technology, yet there is considerable scope for development and optimization of this technology. In other, more rugged regions of the country, it is possible to develop relatively higher heads without elaborate or expensive civil engineering works so that relatively smaller flows are required to develop the desired power. In these cases, it may be possible to construct a relatively simple diversion structure and obtain the highest drop by diverting flows at the top of a waterfall or steeply falling watercourse.
Small hydropower plants are a precursor for economic growth and social development. They guarantee a local, stable power supply. Small hydropower plants are often the only way to create environmentally-friendly power for electric lighting, for preparing and cooling food and for stimulating economic growth in remote regions. In developing countries, they are a good substitute for diesel-powered generators. Even in industrialized nations, small hydropower plants are in demand, as they provide a useful contribution on the whole and effectively support energy change.
In this study, has been tried to evaluate the existence and assessment the resources of this clean source of energy in Kurdistan- the northwestern province of Iran and the calculate the extraction amount of energy from this resource of energy due to the high potentials of the province.
In the evaluated small-scale hydroelectric power in this study, after full identification river and its catchment areas in terms of flow and head and after extraction of relevant maps, by using ArcGIS software, and after apply appropriate environmental, geographical and technical- economic criteria, the hydropower potential of the province from its rivers was estimated.
 The results show that Kurdistan province capable of producing around 500 megawatts of renewable power from that small-scale hydropower that it has.
As a result, 3455 small-scale hydropower plant with the average capacity of 160 kW could be located in the suggested suitable locations in the Kurdistan province. These proposed areas are selected by considering the appropriate environmental, geographical and technical- economic criteria.

Precise estimation of the forest structural parameters supports decision makers for sustainable management of the forests. Moreover, timber volume estimation and consequently the economic value of a forest can be derived based on the structural parameter quantization. Mean age and height of the trees are two important parameters for estimating the productivity of the plantations. This research aims to estimate mean height and age of a Pinus radiata plantation using SPOT-5 textural and spectral data derived from multi-spectral and panchromatic images, respectively. The study site for this research consisted of a 5000 ha Pinus radiata plantation from 35◦ 23/ 35// S to 35◦ 29/ 58// latitude, and 147◦ 58/ 48// E to 148◦ 04/ 02// E longitude, near the town of Batlow in the Hume Forestry Region, NSW Australia. Tree age classes ranged from 10-20 years, 21-30 years and more than 30 years. A total of 63 plots with radii varied from 7 m to 20 m to ensure there were a minimum of 15 trees per plot in variable stocking classes, were randomly surveyed in June and July 2008 by the New South Wales Department of Industry and Investment (IINSW) and Forests New South Wales (FNSW). The effects of forest boundaries, road edges and the other irrelevant features on the estimations were eliminated through buffering prior to locating the plot centres. Tree heights and DBH were measured for 978 trees. Tree heights were measured twice using Vertex hypsometer to increase the accuracy of the measurement. After calculating mean height of the plots, a regression equation was derived based on the relationship between tree age and mean height of the plots. Using this equation and available age of each segment, the mean height was calculated for 278 segments of this plantation. Spectral data includes band reflectance, vegetation indices, and principal component analysis were derived using multispectral image for each segment. Gray level co-occurrence matrix was calculated in four different angles and window sizes to extract the textural data from panchromatic image. Prior to modeling, random forest feature selection method was applied on the spectral and textural data, individually and together to determine the most important features for estimating mean height and age at segment level. Multiple-linear regression (MLR) was applied to model mean height and age using textural and spectral data. Also, spectral and textural attributes were fused at feature level using two approaches. In the first approach, the spectral and textural attributes were used together as inputs for MLR. In the second approach, ratio of spectral and textural attributes were calculated for feeding MLR. The results indicated that there is not significant difference between the models derived from spectral attributes of multispectral data and those derived from textural attributes of panchromatic data. Moreover, it was shown that the models derived from the ratio of the spectral and textural data with age estimation error of 17% and height estimation error of 13% performed better than the other models.

With the growing dominance of complex and multi-level urban structures, current cadastral systems, which are often developed based on 2D representations, are not capable of providing unambiguous spatial information about urban properties. Therefore, the concept of 3D cadastre is proposed to support 3D digital representation of land and properties and facilitate the communication of legal ownership rights associated with them. On the other hand, Building Information Modeling (BIM) provides a common data environment for integrated management of 3D building lifecycle data in the construction industry. Harnessing BIM for 3D cadastre will provide the ability to capture and manage the ownership and legal status of properties in modern cities, providing an efficient approach to access legal information about urban properties. However, querying the meaning of property information inside BIM models has not been addressed. There are studies which investigated the adoption of the semantic web techniques for a better understanding of concepts of the building lifecycle in BIM; however, these investigations do not provide a semantic approach to query and retrieve property information encoded in the BIM environment.
Therefore, this study aims to adopt a linked data methodology to develop a BIM-based spatial ontology for managing 3D property information. In addition, SPARQL query language will be used to retrieve 3D property information. The appropriate entities for modelling properties the in the open BIM data model were deciphered and the spatial ontology was developed in accordance with the BIM open data model structure. To assess the feasibility of the developed spatial ontology, BIM models of multi-story buildings with different levels of complexity and detail were implemented. These models were transformed into the RDF (Resource Description Framework) structure, and 3D semantic queries related to 3D property information have been done in semantic BIM models. These queries retrieve boundaries and spatial arrangements of properties. The query results were displayed using a WebGL viewer, and retrieval time of each query was measured. The findings of this study indicate semantic querying of 3D property information is faster than spatial queries relying on the geometry of 3D property objects.

Road health information is an important indicator for assessing the status of the road in management systems. Identifying the abandonment of surfaces is an important process in maintaining roads and traffic safety, which is traditionally conducted on the basis of field surveys. Today, remote sensing methods, especially photogrammetric imaging, are presented. In this article, based on by UAVs images, the road surface cracks are extracted. The proposed method consists of six stages of acquisition of images, separating the road from the background, identifying and eliminating disturbing objects, preprocessing, combining morphological filters with complication features, applying SVM classifications, generation of crack map .The results of the proposed method show the success rate of 98% in the extraction of the cracks.

Measuring the 3D displacement fields provide essential information regarding the Earth crust interaction and the mantle rheology. The interferometric synthetic aperture radar (InSAR) has an appropriate capability in revealing the displacements of the Earth’s crust. Although, it measures the real 3D displacements in the line of sight (LOS) direction. The 3D displacement vectors can be retrieved through multiple InSAR measurements acquired from at least three independent imaging geometries in a theoretical manner. However, this is a physically ill-posed inverse problem and consequently, the retrieving process of the components in 3D displacements become sensitive to observation errors, especially in the northern component due to the near-polar orbiting of SAR missions. Combining different datasets regarding this issue requires proper treatment of the weight of observations, which otherwise will have a negative effect on both the precision and accuracy of the estimated 3D displacement field. In retrieving the 3D displacement fields through InSAR technique, we deal with two major issues, integration of inhomogeneous precision of observations and instability of the estimation problem. These facts constitute the motivations to address the Tikhonov regularization (TR) and least squares variance component estimation (LS-VCE). In this article, to overcome these drawbacks, the regularized least squares variance component estimation (RLS-VCE) is proposed for retrieving the 3D displacement vectors. Usually, the number of InSAR observations in relation to the three unknowns of 3D displacements for each pixel is not enough to apply VCE. Therefore, observations of some neighborhood cells are taken into account to increase the redundancy of stochastic model. In this context, a moving frame including a window of 3 × 3 pixels is considered to increase the number of observations and consequently, the degree of freedom of stochastic model. To assess the efficiency of the proposed method, the RADAR dataset of the Envisat and ALOS missions for the 17 June 2007 eruption of Kilauea volcano on Hawaiian island are applied. To validate the results of the proposed method, co-event displacement vectors of 19 GNSS stations around the Kilauea volcano are used. Furthermore, the 3D displacements of GNSS stations are applied for detrending the displacements of InSAR from systematic or random disturbing effects (e.g. orbit errors, curvature and topography of the Earth, atmosphere, etc.) through fitting a two variates linear or quadratic polynomial. Comparing the co-event retrieved 3D displacement vectors through RLS-VCE method and GNSS measurements indicates that the componential RMSE of northern displacements decreases drastically to 2.2 cm from 11.7 cm (for range displacements and primary weights). This is approximately equivalent to 80% improvement in the accuracy of estimating the northern component of displacement. The overall RMSE of retrieving 3D displacement vectors decrease from 7.8 cm to 2.6 cm, which is equal to 66% improvement. Achieving to this overall accuracy and for northern component is of major interest for all disciplines of geoscience dealing with 3D surface deformation analysis. Results indicate that retrieving the 3D displacement vectors through applying the RLS-VCE method has a meaningful improvement on the precision and accuracy of the results, the northern-southern component in special.

Soil moisture content (SMC) is one of the most significant variables in drought assessment and climate change. Near-real time and accurate monitoring of this quantity by means of remote sensing (RS) is a useful strategy at regional scales. So far, various methods for the SMC estimation using a RS data have been developed. The use of spectral information based on a small range of electromagnetic spectrum in the form of a single index cannot be a suitable way to estimate the moisture content in the optical and thermal RS. Single use of each index has its own limitations. These limitations can include the effect of atmospheric conditions, solar illumination geometry, topographic conditions and soil characteristics. Therefore, the use of all potential of the electromagnetic spectrum (visible to short-wave infrared bands) in the form of regression combinations of spectral indices might be useful in improving the accuracy of SMC estimation. In this study, at first, the correlation of 20 indices commonly used in soil moisture estimation studies with in situ soil moisture measurements were evaluated. In the next step, based on the correlation results, the indices gradually were added into the soil moisture linear regression and the accuracy of each stage was evaluated. The best SMC estimation model was included the linear regression made of LST, VSDI, NDWI and SASI indices. This ended up with and improvement accuracy (RMSE = 0.048). Soil texture is one of the most important factors in the estimation of SMC by means of RS data especially in optical and thermal regions of spectrum. On the other hand, due to the fact that the soils have different levels of porosities, it seems that the SMC modelling should be based on soil texture. Therefore, the SMC model was evaluated for three dataset, medium textured, moderately coarse texture and coarse texture soils. The results showed that the medium texture soils have a profound relationship with in situ measured compared to coarse texture soils (RRMSE=29%…, RRMSE=0.032). On the other words, the SMC model is not generalizable for all soil types. The results showed an inverse relationship between the accuracy in the SMC estimation and the soil particle size. In other words, the accuracy of the SMC model decreased by the increase in soil particle size. In the case of medium texture soils, better response to the SMC estimation have been seen in optical bands. Coarse texture soils such as sandy soil, because of porosity, water penetrates rapidly and freely inside the soil due to the force of gravity and show a lower water content capacity. On the contrary, medium texture soils have the ability to retain more water in their textures and the length of capillary rise in these soils is greater than those of coarse texture soils. Thus, moisture variations in this type of soils have a greater effect on the soil spectral responses compared to the coarse texture soils where the results of the SMC modelling for loamy medium texture soils approves this.

Image matching is a critical process in various photogrammetry, computer vision and remote sensing applications such as image registration, 3D model reconstruction, change detection, image fusion, pattern recognition, autonomous navigation, and digital elevation model (DEM) generation and orientation. The primary goal of the image matching process is to establish the correspondence between two images of the same scene (i.e., the reference and input images). Image matching methods are generally classified as feature-based matching and template matching.
Feature-based methods extract image features (points, lines, regions) and attempt to establish the correspondence between these features. Template matching methods, also known as area-based methods, are generally defined as the process of finding a template in an image, based on a similarity measure such as cross-correlation and mutual information. Identical image windows of predefined size are applied for the computation of correspondence. Similarity measures play an essential role in the quality of template matching in photogrammetry, remote sensing, and computer vision. Various similarity measures have been proposed in the literature. Each similarity measure has its strengths and weaknesses.
In this paper, the capability of some well-known similarity measures for matching of various close range and satellite images with diverse geometric and radiometric differences are evaluated. Also, to increase the template matching stability against geometric and radiometric variations, a novel weighting approach for computing of similarity measures has been introduced. The proposed approach is based on three weight factor that are computed using gradient and Gaussian functions. By applying this weighting approach for cross correlation similarity measure, a novel measure named Weighted Cross-Correlation (WCC) has been presented.
Ten algorithms, including SSD (Sum of Squared Differences), LSSSD (Locally Scaled Sum of Squared Differences), NSSD (Normalized Sum of Squared Differences), JF (Jeffrey Divergence), Tanimoto, ISD (Incremental Sign Distance), IRV (Intensity-Ratio Variance), CC (Cross-Correlation), MI (Mutual Information) and WCC are considered for evaluation.
To evaluate the capability of various similarity measures, a number of template-matching experiments were applied. Several synthetic and real images for different geometric and radiometric variations including, scale, rotation, viewpoint, blur, and illumination changes are used as data set. The similarity measures are evaluated using three evaluation criteria, including success rate, positional accuracy, and computation time. The experimental results indicate that the proposed WCC method outperforms the other similarity measures for all images and all types of transformations. Based on the evaluation results, the WCC method can be applied to the reliable template matching for a variety of photogrammetric and remote sensing applications. Generally, after the WCC, better results, on average, were obtained by the NSSD, LSSSD, and CC measures in most cases. For illumination variations, MI and ISD methods provide the best results. The fastest method is the IRV and the slowest method is MI. Evaluation of the performance of the various similarity measures for other applications such as dense matching process is suggested as future work.

With the development of digital sensors, an increasing number of high-resolution images are available. Interpretation of these images is not possible manually, which necessitates seeking for practical, fast and automatic solutions to solve the environmental and location-based management problems. The land cover classification using high-resolution imagery is a difficult process because of the complexity of the landscapes, and the spatial and spectral resolution of images. The predecessor studies of land cover classification were done using statistical methods such as maximum likelihood classification. However, the newer studies apply the artificial intelligence techniques such as artificial neural networks and support vector machines as a substitute for classification applications. A major problem with using these models is that the user cannot easily understand the final rules. In this paper, a hybrid algorithm is proposed in order to obtain the needed data by the knowledge-based system from the input data set. The proposed algorithm is designed to get better training data and improvement of the learning system in semi-urban areas by classes covered by different material and colors.
Classification of the remote sensing images refers to separation of the similar spectral sets and division of the units with the same spectral behavior. In remote sensing, due to the large size of data, the processing procedure is costly. On the other hand, to achieve better results, it has been recommended to use various features in the training procedure, which will consequently incrementally increase the volume of processing. Accordingly, the use of object-based process can increase velocity and homogeneity of the final interpreted image by reducing the computational base units. In the field of feature generation, a hybrid feature including both region-based (by kernels) and object-based (by segments) strategy, has been employed in this study. In order to produce the training data, needless of determining that by the user, utilize the capacity of integration of the multi-source data by KBS based system. For this purpose, the ontology concept that applying by the knowledge-based rules was used. Then to improve the obtained training samples and compensate its defects in the expression of the target class properties, the correction step is done. In the other words, the automatic Knowledge-based method was performed to apply the ontological relationships in order to train and control the object-based support vector machine system.
In order to evaluate the proposed method, a set of test images from two different geographic regions were used for validation of the method. In each geographic region, it was attempted to select different test images (various scene features). On this basis, in the first group, three test images belong to a region in northern Iran and Bandar Anzali city, and the second group includes two images in Germany. The GSD (Ground Sampling Distance) of all the 5 test images is equal to 9 cm. Finally, the proposed method has achieved an average accuracy of 82/80% in all test images. The evaluation of the results showed that the proposed technique could be desirable as an automatic and semi-supervised method for interpreting high-resolution images of the semi-urban regions.