LEE- Geomatik Mühendisliği-Doktora
Bu koleksiyon için kalıcı URI
Gözat
Son Başvurular
1 - 5 / 37
-
ÖgeTürkiye'de imar hakkı transferi yönteminin tarihi yapıların korunmasında kullanılması(Lisansüstü Eğitim Enstitüsü, 2022-08-01)İmar hakkı veya diğer adıyla yapılaşma hakkı, taşınmaz mülkiyetinin en önemli unsurlarından birisidir. Mevcut hukuk düzenimizde bir arazinin mülkiyetine sahip olmak, doğal olarak üzerindeki imar hakkına da sahip olmayı beraberinde getirir. Hem evrensel hukuk prensipleri hem de ülkemizdeki mevzuata göre, mülkiyet hakkı ancak kanunlarla, kamu yararına ve rayiç değeri ödenmek şartıyla kısıtlanabilir. Ancak, özel mülkiyette bulunmasına rağmen "tarihi ve kültürel varlık" olarak tescil edilmek suretiyle koruma altına alınan tarihi yapılara getirilen imar yasağı ile, bu taşınmazların sahiplerine imar haklarını kullanmalarına engel olunmakta, daha da önemlisi bunun karşılığında hiçbir tazminat ödenmemektedir. Yani, muvafakatleri alınmadan ilan edilen koruma kararlarıyla tüm imar hakları dondurulan taşınmaz sahiplerine, neden olunan bu hak kısıtlamasının karşılığı olarak hiçbir tazminat seçeneği sunulmamaktadır. Bu durumun ortaya çıkmasının sebeplerinden en başta geleni, kamu maliyesinin kamulaştırma yaparak böyle bir yükünün üstesinden gelmesinin pek mümkün olmamasıdır. Özetle, yaşam alanlarımızda kamu otoritesi tarafından mutlaka korunması gereken kıymetli tarihi ve kültürel yapılar vardır, ancak bunun için hak sahiplerine ödenmesi gereken kaynak kısıtlıdır. Bu tez çalışmasında sorunun çözümü için İmar Hakkı Transferi (İHT) yöntemi önerilmektedir. Tez çalışması kapsamında öncelikle İHT konusunda geniş bir literatür taraması yapılmış ve diğer ülkelerde bu konuda ne tür çalışmalar yapıldığı hakkında bilgiler derlenmiştir. İmar Hakkı Transferi yönteminin yalnızca koruma altına alınmış tarihi yapılar üzerinde kullanılmadığı, bunun dışında doğal ve kültürel sit alanları, tarım arazilerinin korunması ve hatta kentsel dönüşüm uygulamalarında da kullanılabildiğinin altı çizilmiştir. Ardından ülkemizde İHT konusundaki mevcut durum, bu konuda daha önceden çıkarılmış kanun ve yönetmelikler de özetlenerek ilgili başlık altında irdelenmiştir. Bu bilgiler ışığında, Türkiye'deki yasal, kurumsal ve geleneksel özellikler göz önünde bulundurularak, imar hakkı transferi için teknik bir uygulama yöntemi geliştirilmiş ve bu uygulamanın adım adım nasıl yürütüleceği tüm ayrıntılarıyla tanıtılmıştır. Sekiz adımdan oluşan bu yöntem, kısıtlanmış olan bir imar hakkının bir parselden alınıp bir başka parsel üzerine aktarılmasının hukuki ve teknik yol haritasını sunmaktadır. İmar hakkının bir noktadan alınıp başka bir noktaya transfer edilmesi, doğal olarak transferin yapıldığı parsel üzerindeki yapılaşmayı artırmaktadır. Söz konusu inşaat alanı artışı bir takım altyapısal, estetik ve etik kaygıları da beraberinde getirmektedir. Hem bu kaygıların tespit edilmesi hem de geliştirilen teknik uygulama adımlarının geçerliliğinin test edilmesi için, konuyla ilgili sektörlerden 18 kişiyle mülakatlar yapılmıştır. Mülakat katılımcılarının İHT'nin şehircilik üzerindeki etkileri konusunda sahip oldukları pozitif ve negatif fikirleri kayıt altına alınarak analiz edilmiştir. Bununla birlikte, bu çalışma kapsamında geliştirilen teknik uygulama adımları ise mülakat katılımcılarının tamamı tarafından mantıklı ve uygulanabilir bulunmuştur. Sonuç olarak, başarılı bir İHT uygulamasının, imar kısıtlamalarından ötürü ekonomik olarak zarara uğrayan taşınmaz sahiplerinin haklarının iade edilmesini sağlayacağı; herhangi bir tazminat ödenmesine gerek kalmadan Devlet açısından neredeyse sıfır maliyetle koruma kararlarının uygulanabileceği; transfer işlemlerinin şeffaf bir şekilde kamu denetimine açık olarak yapılmasını sağlayacağı; bunun yanında mülakat katılımcılarının fikir ve yorumlarının bundan sonra yapılacak akademik çalışmalar için, üzerinde çalışılması gereken hususlar olarak yol gösterici olacağı düşünülmektedir.
-
ÖgeInvestigating olive trees by monitoring phenological stages using multi-modal satellite sensor data(Graduate School, 2024-02-09)Olive tree is crucial due to its social, cultural and economical values to the Mediterranean society. The demand for olive oil and other products produced from olives is constantly increasing with the global trend of healthy lifestyle. To meet this demand, olive trees are grown in different regions as long as climatic conditions allow. However, global warming and the environmental disasters adversely affect olive trees. As a result, during the past 20 years, several studies on olive trees have been carried out utilising a variety of remote sensing techniques and platforms for diverse agronomic aims, including tree identification, fertilisation, irrigation etc. However, researches on olive trees in Türkiye is limited and to the best knowledge, no studies on olive trees have been performed using remote sensing techniques on regional scale in Türkiye. Therefore, the aim of this research is to map olive trees of Izmir Province, one of the main olive growing regions, for the first time using Sentinel-1 and Sentinel-2 data. The phenology and productivity of olive trees of Izmir are investigated as well, using CLMS HR-VPP products on a regional scale for the first time. The effectiveness of multitemporal Sentinel-1 and -2 data for olive tree classification is evaluated in Chapter 2. Datasets consist of May and October composites of each year between 2017 and 2021 are used in order to capture the different phenological stages of olive trees. Random forest classfier is implemented to datasets. Classification map of Izmir province is produced and number of classes are reduced to two classes "olive" and "non-olive" to create binary olive tree map. Results are validated using both K-fold cross validation and confusion matrix methods. The results show that Sentinel-1 data can map olive trees with up to 70%, while Sentinel-2 data succed up to 90%. However, the combined usage of Sentinel-1 and Sentinel-2 datasets show the best classification accuracy for olive trees. This is a clear example of the advantage of mapping tree crops using radar and optical data fusion. In addition, this is the first olive tree distribution map of Izmir Province, and it's essential for creating a successful management plan. Using data from Sentinel-1 and Sentinel-2, this research assessed the possibilities of mapping olive trees regionally. The phenology and productivity of olive trees of Izmir Province are investigated in Chapter 3. Copernicus Land Monitoring Sevices's High-Resolution Vegetation Phenology and Productivity (HR-VPP) metrics are used. Interannual variability of phenology metrics (SOSD, EOSD) of olive trees are evaluated and the effects of climatic conditions such as precipitation and surface soil mositure as well as elevation to the productivity of olive trees are investigated. Results demonstrate that precipitation have a significant effect on EOSD. Additionally, a strong correlation between total productivity and elevation and climatic conditions, such as precipitation and surface soil moisture, is observed. The strong corrrelation between productivity of olive trees and TUIK crop yield data (R2 = 0.77) verifies the efficiency of CLMS HR-VPP metrics to be used on a regional and global scale. This is one of the first attempts to utilise the power and potential of WEkEO and GEE cloud infrastructures using Sentinel-1 and Sentinel-2 data as well as CLMS HR-VPP products. Moreover, this is the first regional satellite-based phenology and productivity research on olive trees in Türkiye. Field trips to the districts of Bergama and Bayındır are explained in Chapter 4, to look into the reasons of the overestimation and underestimation issues that are discussed in the Chapter 2 and Chapter 3. As olive forests in hillsides are mixed with different types of trees and the other background vegetation around olive trees, olive trees are more likely to be misclassified in hilly regions. In conclusion, this research encourages the use of the cloud infrastructure capabilities of GEE in order to develop a scalable methodology for studies on tree crops at regional to global scales. If this method is expanded to other parts of Türkiye, it will allow for the first country-scale research on olive trees.
-
ÖgeWeb tabanlı açık kaynak kodlu bir platform geliştirilerek jeodezik çalışmalarla kabuk deformasyonlarının statik modelle belirlenmesinin incelenmesi(Lisansüstü Eğitim Enstitüsü, 2024-01-29)Deformasyon analizi, jeodezinin temel araştırma alanlarından biridir ve insan güvenliği için büyük bir öneme sahiptir. Yerkabuğu, çeşitli etmenlerin etkisi altında sürekli bir deformasyona uğrar. Bu etmenler arasında tektonik levha hareketleri, levha içi deformasyonlar, heyelanlar, depremler, volkanik patlamalar, karasal gel-git, yeryuvarının dönmesi ve kutup gezinmesi gibi faktörler bulunmaktadır. Yerkabuğundaki deformasyonlar, depremlere ve heyelanlara neden olabilir; ayrıca büyük mühendislik yapılarında, örneğin köprülerde, barajlarda, yollarda, binalarda, limanlarda ve bu yapıların çevresinde ciddi zararlara yol açabilir. Bu durum aynı zamanda çevrede önemli değişikliklere ve topoğrafyada derin izlere neden olabilir. Yerkabuğu hareketlerinin neden olduğu yatay ve düşey konum değişimleri ile deformasyonların tespiti, olası felaketlere karşı önleyici tedbirlerin alınması açısından son derece kritiktir. Kabuk deformasyon çalışmalarının belirlenmesi, bilim insanları için karşılaştıkları en önemli problemlerden biri olarak kabul edilir. Bu zorlukla başa çıkmak için bilim insanları büyük çaba harcamak zorunda kalırlar. Bununla birlikte, son yıllarda yerkabuğu hareketlerine olan ilginin artması ve teknolojideki hızlı gelişmeler, deformasyon analizi için yeni yazılımların kullanılmasını zorunlu kılmıştır. Bu analizler genellikle kolayca erişilemeyen akademik programlar veya maliyetli ticari yazılımlar kullanılarak gerçekleştirilmektedir. Bu çalışmada jeodezik GNSS (Global Navigation Satellite System) ağlarındaki deformasyonların hızlı ve kolay tespitine yönelik alternatif bir çözüm oluşturmak ve bu sayede deformasyonların ve hareketlerin izlenmesi, belirlenmesi ve analiz edilmesine ilgi duyan uzman mühendislerin analizlerini daha kolay gerçekleştirmeleri için statik deformasyon analizi odaklı açık kaynak kodlu yazılımlar kullanılarak geliştirilmiş bir web tabanlı açık kaynaklı "Web-NDefA platformu ('Web'-based 'N'etwork 'Def'ormation 'A'nalysis)" oluşturulmuştur." Web-NDefA, univaryant jeodezik ağlardaki önemli yer değiştirmeleri incelemek için S-Dönüşüm tekniğini kullanarak 3 boyutlu istatistiksel analiz gerçekleştiren bir deformasyon analiz platformudur. Bu platform sayesinde, 3 boyutlu deformasyon analizi üzerine çalışmalar yürüten her kişi veya kurum jeodezik verilerini değerlendirecek ve buradan elde edilecek sonuçlara eksiksiz, doğru ve hızlı bir şekilde ulaşacaktır. Bu platform istemci taraflı programlama dillerinden olan JavaScript ile geliştirilmiştir. Platformunun oluşturulması için öncelikle HTML ve CSS uygulamaları gerçekleştirilmiştir. Platformu kullanmak için önce deformasyon çalışması için izlenen bir bölgede gerçekleştirilen GPS (Global Positioning System) kampanyasındaki veriler bir GNSS veri işleme yazılımına aktarılır ve değerlendirilir. Buradan baz vektörlerinin çözümlerini içeren ASCII veya Metin dosyası elde edilir ve akabinde Web-NDefA platformuna aktarılır. Burada karşılaştırılacak periyotlar seçilir ve 3 boyutlu statik deformasyon analizi gerçekleştirilir. Bu çalışmanın sonucunda, geliştirilen web uygulamasının teknik altyapısı detaylı bir şekilde açıklanacak ve uygulamalar üzerinde gerçekleştirilen analizler sunulacaktır. Bu sayede, deformasyon analizi alanındaki platformlara yeni bir boyut eklenmiş olacak ve kullanıcılar, ihtiyaç duyabilecekleri statik deformasyon analizi sonuçlarına görsel olarak erişebileceklerdir.
-
ÖgeRoad geometry extraction with fusion of low resolution satellite imagery and GPS trajectory using deep learning methods(Graduate School, 2024-06-03)Road extraction is an important process which plays a crucial role in different applications such as improving navigation systems, facilitating urban planning and providing accurate road mapping in the deployment of autonomous vehicles, which are highly dependent on precise and reliable road information. This study examines the integration of Global Positioning System (GPS) trajectory data with low-resolution satellite imagery to enhance road detection techniques. The study focuses on the use of advanced convolutional neural network models, U-Net, ResUnet D-Linknet, which are tailored for semantic segmentation tasks in satellite images and novel fusion strategies to combine both satellite imagery and GPS trajectory data. Series of experiments conducted to evaluate the impact of different data fusion techniques and loss functions on the performance of the models. The study explores three main types of data fusion: early fusion, and three loss functions: Binary Cross-Entropy (BCE), Mean Squared Error (MSE) and Focal loss (FL). The results reveal that incorporating GPS data enhances road detection capabilities significantly, with late fusion providing the most substantial improvements. Among the tested models, ResUnet emerges as the most effective, particularly when employing a concatenation method for data fusion and utilizing MSE as the loss function. The study introduces the application of a new evaluation metric in the road detection domain, mBoundary-IoU (Mean Boundary Intersection Over Union), which provides a detailed assessment of extraction accuracy, particularly effective in accurately delineating the precise boundaries of road networks within urban landscapes. This metric is designed to complement the traditional Intersection over Union (IoU) by offering a more nuanced evaluation of the road outlines. A key part of the study involves the creation of a benchmark dataset that combines low-resolution satellite imagery with corresponding GPS data. This dataset covers Istanbul and Montreal. It is the first dataset of its kind in Turkey made available for public use and aims to facilitate comparative studies with satellite imagery and GPS trajectory and encourage further research into the integration of these two types of data. The research also investigates the variability in model performance across different geographic areas: Istanbul and Montreal. It is noted that the models exhibit better performance on the Montreal dataset, which features simpler and less congested road layouts compared to the complex and densely packed roads of Istanbul. This variability highlights the challenges and considerations needed when applying these models to different urban environments. In conclusion, the study demonstrates that the integration of GPS trajectory data with satellite imagery can significantly improve the precision and reliability of road detection systems. While the current findings are promising, the study suggests that further improvements could be achieved by exploring additional fusion techniques and by further customizing the deep learning models to accommodate the unique characteristics of different geographic areas.
-
ÖgeAssessing the impact of super-resolution on enhancing the spatial quality of historical aerial photographs(Graduate School, 2024-06-10)The level of distinguishability of details in an image is called resolution. In current studies, high-resolution (HR) images are generally preferred. However, not all available images may have resolution sufficient to fulfill their intended purpose. Due to hardware and cost constraints, it's not always feasible to obtain and prodecure HR images, hence low-resolution (LR) images need to be enhanced. This process is possible through techniques known as super-resolution (SR). SR is defined as obtaining an HR image from an LR one. It's accepted that an LR image is a degraded version of its HR counterpart. When detrimental effects are applied to an HR image, some information will be lost. Consequently, a lower-quality image will be obtained, which is referred to as LR. However, the image in need of enhancement is LR, while the unavailable image is HR. Therefore, transitioning from LR to HR is an inverse problem. To solve this problem, the lost information must be identified and restored to the LR image. In current SR studies, deep learning (DL) based models are now being utilized. Various network designs are employed to enhance model performance and achieve better image quality. These designs primarily include linear learning, residual learning, recursive learning, multi-scale learning, dense connections, generative adversarial networks, and attention mechanisms. DL-based SR studies initially began with the use of linear learning in the Super-Resolution Convolutional Neural Network (SRCNN) model. After linear learning, models utilizing residual learning with deeper networks and higher performance perspectives gained prominence. Due to the practical challenges posed by the increased number of parameters in deeper networks, recursive learning has been introduced in image processing studies. Recursive learning, based on the principle of parameter sharing to control the total number of parameters, allowed models to run much faster but introduced the vanishing gradient problem. In this context, dense- connected models incorporating both residual learning and recursive learning were proposed. Subsequently, visually high-quality images were obtained using generative adversarial network structures. Nowadays, there is a focus on attention mechanisms in SR studies. In summary, to improve model performance, learning strategies were altered, various loss functions were tested, and network architectures were modified with various hyperparameters. However, all efforts have been solely algorithm-based, and satisfactory results have actually been achieved, especially with attention mechanisms. One aspect that has not yet been fully addressed in SR studies is the impracticality of using deeper and more complex structures in real-time applications and the inability of models built on common datasets to deliver the expected performance in enhancing images for solving real-engineering problems. For the former, the performance rates of lightweight network architectures should be increased. For the latter, specific approaches tailored to solving the problem should be introduced. The remotely sensed (RS) images that have been scarcely evaluated in SR studies are historical aerial photographs (HAP). Besides the negative effects harbored during the enhancement of RS images, HAPs have additional constraints. Information losses during the conversion of printed copies to digital copies, data acquisition hardware used depending on the technological possibilities of the era, lack of spectral bands, and color information are the main negative constraints. Since HAPs play a crucial role in solving problems the present which is related to the past, they also need to be improved with SR techniques. In this thesis study, it is aimed to enhance the spatial quality of grayscale HAPs with DL-based SR model. In this context, approaches have been brought regarding the content and structure of the dataset. Orthophotos obtained from the General Directorate of Mapping of different years with different resolutions have been used as the primary data source. The acquired orthophotos belong to the years 1954 with a resolution of 30 cm, 1968 with resolutions of 40 cm and 70 cm, and 1982 with a resolution of 10 cm, and 1993 with a resolution of 40 cm. In the approach to dataset content, images of residential areas, farmland areas, forested areas, and bare land classes were extracted separately from orthophotos to create datasets. DL-based SR models cannot be directly used on HAPs because they are built on multi-spectral images. To overcome this limitation, artificial 3-band images were created by duplicating the same band twice. Although the single-band image is numerically converted to a three-band image, there is no change in content. To minimize this limitation, images of different resolutions from different years covering the same regions were used. This approach, which can be called imitating the multi-spectral image, did not include images containing only three different spectral bands in the training, but it seemed as if different spectral bands of the same image were included separately in the training. Another limitation is the lack of color information, which is due to the grayscale nature of the HAPs. The lack of color information for grayscale HAPs was minimized by using images with a wide range of intensities. Since different intensity values provide different grayscale tones, maximum use has been made of intensity values that provide differences for objects that are similar to each other both within the same category and across different categories. Another limitation for HAPs is that LR-HR image pairs are insufficient in content, which has been overcome by using larger size images. Depending on the years from which the data were obtained, there are a limited number of classes. During the convolution process, filters have been ensured to gather information on images containing more diversity in larger image sizes. The proposed approach for the dataset structure is based on the hierarchy of photo interpretation elements. The hierarchy of photo interpretation elements is expressed with different levels. The first level involves color and tone information, which are more pronounced in bare land and forest areas found in orthophotos. The second level includes size, shape, and texture. Residential areas represent the group that reflects these elements the most. The third level includes patterns, with farmland areas being the group that best reflects this element. Within this framework, the dataset is structured as the 1st level consisting of bare land and forest areas, the 2nd level consisting of residential areas, and the 3rd level consisting of farmland areas. The 1993 image was also used in the approach to the data set structure. Each of the three datasets were trained separately by means of SRCNN model. Two different methodologies were used to obtain the final image from separately trained data sets. The final image was created with the average of 3 different images improved in the first methodology. In the second methodology, each improved image was divided into pieces of equal size. A reference-free image quality metric was calculated for each part obtained. The final image was created by concatenating identical parts for which the quality metric gave better results. Approaches to both dataset content and dataset structure were evaluated with reference-based image quality metrics as well as visual interpretation. In the content-based approach, pixel-based metrics and structural similarity based metrics demonstrated positive progress. Evaluations made through visual interpretation also yielded consistent results with image quality metrics. This approach was also effective in reducing the softening effect on the output image. In the structural-based approach, creating the final image based on the reference-free image quality metric gave better results. However, the selectability of better image parts requires more advanced image processing techniques.