Roghayeh Adabi; Rahim Ali Abbaspour; Alireza Chehreghan
Abstract
Extended AbstractIntroductionIn recent years, data has become the life-giving force of developing innovations in smart cities all around the world. The up-to-date, availability, and freeness of this data are the deciding factors in their frequent use in smart city projects. Today, different sources of ...
Read More
Extended AbstractIntroductionIn recent years, data has become the life-giving force of developing innovations in smart cities all around the world. The up-to-date, availability, and freeness of this data are the deciding factors in their frequent use in smart city projects. Today, different sources of information on city-related issues are available. They are crucial for driving towards “Smart Cities”. Among these sources is the Open Street Map (OSM) project, which is a free and open-source information repository used in many urban and non-urban-related applications. At present, OSM is used for a wide range of applications, for example, navigation, location-based services, construction of 3D city models, and traffic simulation. In the meantime, building blocks are among the OSM data that plays a key role in urban-related studies. These studies include constructing 3D building models, modeling urban energy systems, and land-use management in smart cities. Regarding the importance of completeness in the quality of spatial data, this study will assess the historical course of building blocks data completeness in OSM. Materials and methodsThe 20 districts of the Tehran metropolis have been selected as the study area. This city, with an area of 730 square kilometers and a population of around 8 million people covers the center of Tehran. The main purpose of this study is to present an analysis of the completeness of building block data in the OSM for the Tehran metropolis in 10 years (between 2011 and 2020). To reach this aim, an object-based approach based on object matching was used to assess the completeness parameter. Results and DiscussionThe findings of this study demonstrate that during the recent two years, OSM building block data in Tehran increased in terms of the number of features and the completeness of geometric information considerably. The number of data increased from 300 features in 2011 to 40.138 features in 2020, as well as the number of features edited and added to the OSM dataset increased from 38 and 194 in 2011 to 28680 and 10705 in the end of 2020, respectively. The completeness of OSM building block data in Tehran has increased from 0.18% in 2011 to 2.7% in 2020. Moreover, the evaluation of the completeness of OSM data in different regions of Tehran shows that the completeness of all regions of Tehran was less than 1% from 2011 to 2014, and in the last two years, for 12 of 20 regions of Tehran, the completeness is still less than 1%, but for the other eight regions (i.e., the regions no. 1, 2, 4, 5, 11, 15, and 20), which are mostly located in the northern part of Tehran, the completeness has increased. However, the data have many weaknesses in terms of the attribute information completeness. ConclusionThis study has provided a clear view of OSM building block status in Tehran. In addition, it has provided a better view of OSM data in different regions of Tehran. The insights gained from this study can lead toward creating the awareness required to use of these data in various fields of application. It can also assist local and national managers and related organizations to support active regions and encourage inactive regions. This paper represents a potential starting point for many possible future research directions in smart cities, especially in Tehran. Smart cities can conduct similar studies to understand the state of OSM data in their regions, make plans based on the findings, and manage their space more efficiently. To conduct future research, we evaluate the factors affecting the growth and development of OSM data and the efficiency of the OSM data in some smart city applications.
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.