Browsing by Author "Zeybek, Mustafa"

Now showing 1 - 3 of 3

Citation - WoS: 10
Citation - Scopus: 13
Investigation of Landslide Detection Using Radial Basis Functions: a Case Study of the Takent Landslide, Turkey
(SPRINGER, 2020) Zeybek, Mustafa; Şanlıoğlu, İsmail
This paper investigates landslide detection over flat and steep-slope areas with large forest cover using different radial basis function interpolation methods, which can affect the quality of a digital elevation model. Unmanned aerial vehicles have been widely used in landslide detection studies. The generation of image-based point clouds is achievable with various matching algorithms from computer vision systems. Point cloud-based analysis was performed by generating multi-temporal digital elevation models to detect landslide displacement. Interpolation methodology has a crucial task to fill the gaps in insufficient areas that result from filtered areas or sensors that do not generate spatial information. Radial basis function interpolations are the most commonly used technique for estimating the unknown values in survey areas. However, the quality of the radial basis function interpolation methods for landslide studies has not been thoroughly investigated in previous studies. In this study, radial basis function interpolation methods are investigated and compared with the global navigational satellite systems, which provide high accuracy for geodetic measurement systems. The main purpose of this study was to investigate the various radial basis function models to detect landslides using a point cloud-based digital elevation model and determine the quality of detection with global navigational satellite systems. As a result of this study, each of the radial basis function-generated digital elevation models was found to be statistically compatible with global navigational satellite systems, resulting in displacements from the ground truth data.
Citation - WoS: 123
Citation - Scopus: 144
Point Cloud Filtering on Uav Based Point Cloud
(ELSEVIER SCI LTD, 2019) Zeybek, Mustafa; Şanlıoğlu, İsmail
Nowadays, Unmanned Aerial Vehicles (UAVs) have been attracted wide attentions such as a new measurement equipment and mapping, which are capable of the high-resolution point cloud data collection. In addition, a massive point cloud data has brought about the data filtering and irregular data organization for the generation of digital terrain models. Filtering of point clouds contains vegetations and artificial objects play a crucial role for bare earth terrain modelling. Topographical maps rely on the data structures which are built on bare ground terrain points. The bare earth surface extraction is not the only crucial to the topographical maps but also decision-making processes such as natural hazards management, deformation analysis and interpretation. In order to filter a UAV-based 3D raw point cloud data, in this paper, filtering performance of four different algorithms using open source and commercial software's have been investigated, (1) curvature based (Multiscale Curvature Classification-MCC), (2) surface-based filtering (FUSION), (3) progressive TIN based (LasTool-LasGround module-commercial) and (4) physical simulation processing (Cloth Simulation Filtering-CSF). The applied filtering results were validated with the reference data set classified by operator. Although different filtering methodologies implemented on point clouds, these methods demonstrated similar results to extract ground on distinctive terrain feature such as dense vegetated, flat surface, rough and complex landscapes. The filtering algorithms' results revealed that UAV-generated data suitable for extraction of bare earth surface feature on the different type of a terrain. Accuracy of the filtered point cloud reached the 93% true classification on flat surfaces from CSF filtering method. (C) 2018 Elsevier Ltd. All rights reserved.
Topoğrafik Yüzey Değişimlerinin Görüntü İşleme Teknikleriyle Belirlenmesi Üzerine Bir Araştırma
(2019) Zeybek, Mustafa; Şanlıoğlu, İsmail
Bu çalışma, topoğrafik yüzeylerde meydana gelen hareketlerin izlenmesinde İnsansız Hava Aracı (İHA) kullanımını sunmaktadır. Çalışmada farklı zamanlarda elde edilen görüntülerde komşuluk ve korelasyon ilişkileriyle yüzey hareketlerinin ortaya çıkarılması amaçlanmaktadır. Son yılların en yeni ve etkili ölçme teknolojisi hiç şüphesiz İHA’dır. İHA görüntüleri, santimetre hassasiyette çözüm üretebilen Küresel Konumlandırma Uydu Sistemleri (GNSS) ile birlikte kullanılarak yüzey hareketlerinin tespit edilmesi için değerlendirilmiştir. Bu çalışma kapsamında belirli zaman aralığında elde edilen verilerdeki özel detaylar otomatik çıkarılarak görüntülerdeki topoğrafik yüzeyin farklı sebeplerle oluşan değişimleri gözlemlenmiştir. Aynı koordinat sistemine sahip farklı zamanlarda elde edilen ortomozaikler arasındaki benzerlik ve farklılıklardan yararlanarak görüntüler üzerindeki topoğrafik yüzey özellikleri incelenebilmektedir. Çalışma bölgesi olarak heyelan vakalarının yoğun olarak görüldüğü Taşkent (Konya) ilçesi seçilmiştir. İHA görüntülerinden elde edilen ortomozaik ve sayısal arazi modeli verileri, yüzey hareketlerinin yatay ve düşey yönde tespit edilmesinde kullanılmıştır. Planimetrik olarak 0.005 m/gün hızda yer değiştirmeler, düşeyde ise ortalama 0.004m/gün hareketler tespit edilmiştir.