Alireza Taheri Dehkordi; Seyyed Mohammad Milad Shahabi; Mohammad Javad Valadan Zouj; Mahmood Reza Sahebi; Alireza Safdarinejad
Abstract
Extended Abstract
Introduction
Over the past three decades, with the rapid development of spatial-based satellite imagery, remote sensing technology has found a special place in various applications of urban management. Production of status maps of urban structures, the study of energy loss status, ...
Read More
Extended Abstract
Introduction
Over the past three decades, with the rapid development of spatial-based satellite imagery, remote sensing technology has found a special place in various applications of urban management. Production of status maps of urban structures, the study of energy loss status, identification of thermal islands, monitoring of urban vegetation, and assessment of air pollution are just a few examples of areas related to urban management that remote sensing technology is the basis for indirect measurement of the related quantities. Maps of urban structures such as building blocks are commonly used in crisis management, urban design, and urban development studies.
Materials
In this study, the production of urban building block maps using Sentinel 1 and 2 satellite images has been conducted. Normalized Difference Vegetation Index (NDVI) and Normalized Difference Building Index ( NDBI ) for three consecutive months, the slope feature derived from the 30-meter Shuttle Radar Topographic Mission (SRTM)Digital Elevation Model of the study area, along with two Vertical – Vertical (VV) and Vertical - Horizontal ( VH ) polarization in both ascending and descending orbits, form the set of input features.
Methods
The proposed method of this paper relies on the use of a generalizable trained classifier. Initially, the classifier is trained in 2015 using training samples obtained from a new rigorous refining process using different remote sensing and spatial products. This rigorous refining process uses a reference urban map of 2015. In the first step, the corresponding areas related to the ways and roads are removed using the OpenStreetMap data layer. Areas suspected of vegetation with NDVI greater than 0.2 are then discarded. Also, due to the high backscattering of buildings in Synthetic Aperture Radar images, areas with a value less than the average backscattering coefficient of the remaining areas are eliminated. Finally, the residual map is refined using the Mahalanabis distance and the Otsu automatic thresholding method. The trained classifier is then used to generate a map of building blocks at similar time intervals for the three target years (2018, 2019, and 2020). Due to the diversity of texture and density of building blocks in the metropolis of Tehran, the proposed method has been evaluated in this area. Due to the concentration of political, welfare, and social facilities, Tehran has experienced more unplanned and irregular expansion and urbanization than other cities in Iran, which has lead to changes in buildings and constructions. Also, due to the availability of free satellite images and various online processing operations, the Google Earth Engine platform has been used in this study. The performance of three different classifiers including Random Forest (RF), Minimum Mahalanabis Distance (MD), and Support Vector Machines (SVM) are examined in this process. In order to evaluate the proposed method, reference samples obtained from visual interpretation of high-resolution satellite images (Google Earth) in all three target years have been used.
Results
The performance of the aforementioned classifiers has been investigated using 3 different criteria: overall accuracy, user accuracy, and F-score of building blocks. The RF method with an overall accuracy of over 93% in all three target years has shown the best performance. The SVM method ranks second with an accuracy of about 91% every three years. However, the MD method with an overall accuracy below 85% in all three target years has not performed well.
Discussion
The results show better performance of the RF method in all three target years with an overall accuracy of over 93%. It should be noted that the MD classifier with higher user accuracy than other methods, has shown better performance in detecting the class of building blocks. However, the RF method is the best classifier in terms of the user accuracy of the background class. The effect of using two VV and VH polarization and also the slope derived from the SRTM Model in the input feature set on the final accuracy of classification was also investigated. According to the results, the simultaneous use of these three features produces more accurate results in both target classes. However, the results show that the use of VV polarization increases the final classification accuracy compared to VH polarization. The presence of slope feature along with both polarizations has also increased the classification accuracy of each class, especially the background class. However, the exclusion of both VV and VH features from the input feature set has resulted in a more than 10% reduction in overall classification accuracy.
Conclusion
Based on calculated overall accuracies which are above 80% in the majority of investigated cases, two different results can be concluded. First, the trained classifier has shown good temporal generalization and has achieved acceptable accuracy in the target years. Second, due to the different collection processes of training and evaluation data, the proposed rigorous refining method for the preparation of training data has shown good performance. The effect of using two VV and VH polarization and also the slope derived from the SRTM Digital Elevation Model in the input feature set on the final accuracy of classification was also investigated. According to the results, the simultaneous use of these three features produces more accurate results in both target classes. However, the results show that the use of VV polarization increases the final classification accuracy compared to VH polarization. The presence of slope feature along with both polarizations has also increased the classification accuracy of each class, especially the background class. However, the exclusion of both VV and VH features from the input feature set has resulted in a tangible decreasein overall classification accuracy.
Alireza Safdarinezhad; Mahdi Mokhtarzadeh; Mohammadjavad Valadanzouj
Abstract
Abstract
3D point clouds obtained by Airborne Laser Scanner Systems provide a varied and unique geometric information of the physical terrain surfaces due to advantages such as relatively high geometric accuracy and high spatial density of the points. Classification ...
Read More
Abstract
3D point clouds obtained by Airborne Laser Scanner Systems provide a varied and unique geometric information of the physical terrain surfaces due to advantages such as relatively high geometric accuracy and high spatial density of the points. Classification and separation of cloud point data to environmental constructive terrains plays an important role in the process of 3D modeling of terrains. In this procedure, point cloud clustering is a fundamental step in the procedure of information extraction form LiDAR's data. In this paper, a novel method is proposed for supervised classification of LiDAR cloud of points based on contextual analysis of LiDAR points. The proposed method consists of three main steps. In the first step, a set of features based on contextual analyses are produced for each point in LiDAR data. In the second step, the optimum feature selection is done in the modified prototype space using a new strategy. The last step is conducted by a simple k-means clustering in the feature space spanned by optimum contextual clusters. An urban area with the residential texture has been used as the case study to evaluate the proposed method. The results indicate proper classification accuracies. The overall accuracies and kappa coefficients were 93.15% and 0.89 respectively.
Behnam Bigdeli; Mohammad Javad Valadan zoj; Yaser Maghsoudi Mehrani
Abstract
Collecting information on the areas under cultivation of wheat and the amount of its products provides the successful and sustainable management in the economic policy-makingfor this strategic product. Introduction of high spectral and special resolution satellite data has enabled the production of such ...
Read More
Collecting information on the areas under cultivation of wheat and the amount of its products provides the successful and sustainable management in the economic policy-makingfor this strategic product. Introduction of high spectral and special resolution satellite data has enabled the production of such information in a timely and accurate manner. Investigating the spectral reflection of plants using field spectrometry and forming a spectral library increases the possibility of differentiating various wheat cultivars and preparing their distribution map. For this purpose, the spectral behavior curves for 6 wheat cultivars named Bahar, Chamran, Pishtaz, Shiraz, Shiroodi and Yavaros, were measured at three stages of growth at the ‘Research Institute of Seed and plant improvement " of Karaj in Iran. Observations were obtained by the ASD FieldSpec®3 Field Spectrometerin the range of 350-2500 nm wavelength under natural light and natural conditions. In the pre-processing stage, three noisy ranges affected by water vapor were detected and eliminated to enhance the gathered data quality. Then,in order to qualitatively collect the data, wrong observations were excluded using statistical methods. This research was designed and implemented in two main steps. In the first step, the spectral response function of the OLI sensor installed on the Landsat 8 satellite was applied to the library's spectra. Then, using the spectral similarity criteria and the twenty seven important vegetation indices sensitive to chlorophyll concentration, photosynthesis intensity, nitrogen and water content in the crown of the plant, etc., the extreme final resolution of wheat cultivars under study, was estimated.In the second step, the classification of the identified farms was carried out by conducting a field survey of the studied area and obtaining satellite images of the target sensor using spectral library spectra. The results showed a significant separabilityof Yavarus wheat variety from other cultivars, both in field spectra and satellite images.
Hadi Babapour; Mahdi Mokhtarzadeh; Mohammad Javad Valadanzoj; Mahdi Modiri
Abstract
The importance of spatial-referenceddata in all developmental and research affairs is not overlooked. Among the methods for the preparation and production of spatial data, the photogrammetry method has a unique position due to speed, cost-effectiveness and above all, the lack of need to direct human ...
Read More
The importance of spatial-referenceddata in all developmental and research affairs is not overlooked. Among the methods for the preparation and production of spatial data, the photogrammetry method has a unique position due to speed, cost-effectiveness and above all, the lack of need to direct human presence on the site. In photogrammetric method, airborne cameras play a key role in the success and achievements of other stages, as the main means of providing input data and the first operational loop. Today, technological advances have led to the presentation of high quality digital cameras that promise the provision of the required spatial information by photogrammetric method with high accuracy, speed and efficiency. Given the emergence of new digital cameras and the variety of construction and technology used in these types of cameras, the need for their calibration is recognized as a primary requirement. Considering the high costs and executive problems with performing laboratory calibration, the use of self-calibration equations is considered as one of the most useful solutions in this field. For this purpose, in this paper, the use of Fourier equations with optimal terms derived from the genetic algorithm was proposed, and was evaluated and compared with previous models on the simulated data. Based on the results, this model is able to model multiple distortions with minimal dependency. The accuracy presented for modeling multiple distortions in simulated images of the Ultra Cam digital camerashows an about 30% improvement in modeling accuracy with the least dependency,compared with other additional parameters.
Mohammad Javad Valadan Zowj; Asghar Milan Lak; Mahdi Gholam Ali Majd Abadi
Volume 14, Issue 55 , November 2005, , Pages 9-12
Abstract
Dynamism of satellite images with linear arrangement has made it possible to use highly complex algorithms requiring information from the satellite's orbit to carry out geometric correction of these images with high precision. On the other hand, in new satellite imagery, sellers of these images are not ...
Read More
Dynamism of satellite images with linear arrangement has made it possible to use highly complex algorithms requiring information from the satellite's orbit to carry out geometric correction of these images with high precision. On the other hand, in new satellite imagery, sellers of these images are not interested in sending this information. For this reason, in order to perform the geometric correction of these images, we need new mathematical models to perform the geometric correction and meet the required precision without any need for satellite information. One of these models is the Rational Function Model, which is used for this purpose. The other is the modified DLT. In this paper, these models have been investigated for geometric correction of satellite images, for which purpose programs have been written in Visual C environment. To test these models, the results of these models’ implication on IRS, IKONOS and SPOT satellite images were surveyed. The results of this study showed that these models were able to perform the geometric correction of these images. Although they are less accurate than the models that use orbit parameters, the value of these models lies in their independence from satellite orbit parameters, their vast capacity of processing and also in the simplicity of these models.