ENGINEERING JOURNAL OF GEOSPATIAL INFORMATION TECHNOLOGY
Year:2017 | Volume:4 | Issue:4|Papers Count:8

The Zagros mountain forests in Iran, constitutes approximately 40 percent of the country’s forests expanding in eleven provinces, provides important functions as soil and water preservation. The forestes sustained severe oak decline in places over the last decade, triggered by chain factors such as drought, pathogens and Borer beetles. Determining the extent of the declined regions is the first step to address manage and address the risk posed by such environmental hazards. In this research, we focus on Malekshahi city in Ilam province and use Landsat satellite images in years between 2000 and 2015 for determining spatial pattern of oak decline in this region. Slope of temporal variation of an appropriate vegetation index and a water index, are extracted and analyzed from Landsat imageries. The oak forests are classified in three categories: Healthy forests, lowseverity declined forests, and high-severity declined forests, based on EVI and NDWI. According to the results, approximately 16%, 58% and 26% of the region belongs to healthy regions, low and high level of disease, respectively. Finally, the overall accuracy of the oak decline map, is evaluated based on available ground truth data. About %83 overall accuracy, shows high performance of the proposed method in detecting declined regions against healthy ones. But it has less ability in classifying different levels of decline, since overall acccuracy is about %54 for this purpose.

Measurement of pressure profiles at limited number of synoptic stations are performed by the Radiosondes on a routine basis where this usually do not meet the need for numerical weather forecasting and there is need for more input data. Producing pressure values at different geopotential heights in the atmosphere is very important especially in the study of atmospheric circulation and weather forecasting. The data used in this research are: Radiosonde data, MODIS satellite images and surface pressure collected at synoptic stations. The method used is based on the hydrostatic hypothesis that is based on the assumption of small vertical movements in the air. The pressure profile is extracted from hydrostatic equation. This research consists of two parts, in the first part hydrostatic model has been evaluated for the stability index based on Radiosonde data, In the second part, pressure profile was calculated at different geopotential height using MODIS products of temperautre, moisture profiles and MODIS surface pressure. The average RMSE between Radiosonde measured profiles and MODIS data was 0.4 and 1 milibar, respectively. The results calculated through Hydrostatic models have a logical conformity with the one from the radiosonde measurements in both stable and unstable atmospheric conditions. The results show that by having surface pressure and temperature and moisture profile, one can calculate atmospheric pressure precisely in different altitudes using Hydrostatic model. The amount of uncertainties of the results of this method has been evaluated and is presented a seperate table.

In this paper high-resolution SAR, panchromatic and multispectral images are fused for building detection purposes. This fusion is aimed to compensate the defects and shortcomings of these individual data sets. For this reason at first these three data sets are considered individually where some proposed input features are used for building detection. Then these features are fused in different combinations and the results are compared. In all experiments neural networks are applied and their performances are evaluated over different cover types of building roofs. It was discovered that the optimum fusion solution improves the building detection for more then 10% kappa coefficient. Also the proposed fusion strategy caused at least 8 times betters homogeneity of detection results over different roof types. The proposed method enjoying overall accuracy, kappa coefficient and building detection accuracy of% 87.11, % 67.99 and %89.08 respectively confirms the ability to detect buildings of multi-resource radar and optical data.

Large amount of users’ trajectories, is an emerging source of inexpensive data that can be used to provide an opportunity to present route recommendation service to the unfamiliar users within the area. In this study, with the aim of finding the optimal route, we first extract both local users and local road segments data sets by ranking them via HITS algorithm. In this model, a hub is a user who many time has crossed many road segments of a region, and an authority is a road segment that has been crossed by many users. Therefore, users’ travel experiences (hub scores) and the interests of road segments (authority scores) have a mutual reinforcement relation. We also propose a novel approach in which the basic unit of routing is separate road segment instead of GPS trajectory segment. Moreover, to provide the approximate routing, we create a local graph. The center of the local road segments are considered as nodes and are based on local streets sequence arrange the pieces obtained from the trajectory of the user as edges of local graph. According to this graph, two steps of routing are used to obtain the optimal path. Then using Dijkstra's algorithm on the main road network and obtained an approximate route, shortest route between two local road segments based on this graph is used to obtain the optimal route. To implement and test, used data, from the trajectories of moving users in Tehran, has been gathered for 3 months on daily basis. To evaluate performance of the two-step routing, we experimentally compared the travel time in proposed routeto Dijkstra’s shortest path for different lengths and users with different levels of regional knowledge. The travel time in the proposed method was decreased 60 percent compare to shortest route.

In this study, in order to eliminate the stripping error from GRACE gravity observations and localization of the signals of this satellite, wavelet analysis instead of Gaussian isotropic filtering approach is used. For this purpose, the scaling functions and wavelets, generated by a so-called cubic polynomial (CuP), are considered and gravity variations for two major earthquakes-Sumatra earthquake and Maule earthquake- are obtained. For the case of Sumatra earthquake- Indonesia, various scale function of CuP are tested and the most precise results of gravity variations with maximum 30 Micro-Gal is acquired in scale 4 which was similar to other studies. This result didn’t change with increasing scale function even higher than 4. Moreover, for the case of Maule earthquake- Chile, the gravity variations before and after of using wavelet is attained which shows many disparity. The maximum gravity variations before applying wavelet is acquired 20 Micro-Gal and after applying that, the maximum of these variations is computed 10 Micro-Gal which was similar to other researches.

Daily growth of unmanned aerial systems (UAS) technology in areas related to geospatial sciences and location-based services makes it easy to employ them in digital photogrammetry, environment monitoring, infrastructures, sensitive constructions and medical support and aid delivery tasks. In this area, fast and efficient development in UAS path planning can enhance the productivity, efficiency and quality of these missions. In this research, an efficient UAS path planning strategy is proposed based on the imperialist competitive optimization algorithm, which can improve the productivity and autonomy of different missions in new challenges such as medical support and aid delivery scenarios. For this purpose, first, with respect to the objectives and restrictions of the scenario, a single objective constrained optimization model is designed. Then, to intensify the exploration and exploitation capabilities of imperialist competitive algorithm, the assimilation step is integrated with gravity physics. In simulation phase, the results obtained by proposed method has been compared to the results of the other variants of this method with respect to the quality, standard deviation, running time, success rate and quality of the computed paths. The assessment in multiple simulations verifies the efficiency and robustness of the proposed strategy and quality of the obtained paths in studied scenario.

Buildings are one of the most important urban structures that are used for various applications and urban mapping. In recent years, with the development of the high resolution data acquisition technologies, many different approaches and algorithms have been presented to extract the accurate and timely updated 3D models of buildings as a key element of city structures for numerous applications in urban mapping. In this paper, a novel and model-based approach is proposed for automatic recognition of buildings’ roof models such as flat, gable, hip, and pyramid hip roof models based on deep structures for hierarchical learning of features that are extracted from both LiDAR and aerial orthophotos. The main steps of this approach include building segmentation, feature extraction and learning, and finally building roof labelling in a supervised pre-trained Convolutional Neural Network (CNN) framework to have an automatic recognition system for various types of buildings over an urban area. In this framework, the height information provides invariant geometric features for CNN network to localize the boundary of each individual roofs. CNN is a kind of feed-forward neural network with the multilayer perceptron concept that consists of a number of convolutional and sub-sampling layers in an adaptable structure which is widely used in pattern recognition and object detection applications. Since the training dataset is a small library of labelled models for different shapes of roofs, via using the pretrained models, the computation time of learning can decrease significantly. The experimental results highlight the effectiveness of the deep learning approach to detect and extract the pattern of buildings’ roofs automatically considering the complementary nature of height and RGB information. Based on the training results, the top 1 error and accuracy of training are about 0.05 and 95 %, respectively. Moreover, the average of correctness and completeness rates are about 97% and 69%, respectively.

In a multi-modal multi-objective route planning problem, the main purpose is finding an optimal route between the origin and destination, which is a combination of multi-transportation modes, pairs by considering multifitness function. Most of multi-objective problems are solved by assigning a weight to each objective function and using a linear averaging of the objectives as a distinct objective function. These methods have some weaknesses such as inability in searching the problem space and a need to normalize the objective functions. Therefore, in this paper, a non-dominated sorting genetic algorithm (NSGA-II) has been used to solve the multi-modal multi-objective routing problem. This algorithm proposes a set of non-dominated routes that has no absolute superiority to each other. Finally, the optimal route was determined using TOPSIS method from this set. The intended objective functions in this research are the lowest number of changes in transportation means, fare and time during the path. Moreover, five transportation modes including subway, taxi, bus, BRT, and walking transportation modes have been considered as means of transportation inside the mentioned network. This algorithm was implemented in a part of Tehran transportation network and results showed that the proposed NSGA-II algorithm proposed a better route in 89% and 87% of the routing cases than those of the genetic and the simulated annealing algorithms respectively.