Turkish Journal of Remote Sensing and GIS
|Journal Papers (6)||Details||Call for Paper||Manuscript submission||Publication Ethics||Contact||Authors' Guide Line|
Image Fusion with Metaheuristic Cuckoo Search Algorithm
Component substitution-based fusion methods are among the most widespread image fusion methods in the literature. Despite the fact that these methods are very successful in enhancing the spatial detail quality, they tend to deteriorate the spectral quality of the input multispectral images. The main reason for this is that they are not so successful in optimizing the intensity component produced from the input multispectral bands. In this study, an image fusion method which utilizes metaheuristic cuckoo search algorithm was proposed to optimize the intensity component used in fusion process. The proposed method was applied on the Gram-Schmidt (GS) method, one of the most widely-used component substitution-based image fusion methods. The colour preservation performance of the proposed method was qualitatively and quantitatively compared not only against that of the High-Pass Filtering (HPF) method, but also against those of popular component substitution-based methods Multiplicative (MCV), Brovey (BRV), Principal Component Analysis (PCA), Ehlers (EHL), Modified Intensity-Hue-Saturation (MIHS), Synthetic Variable Ratio (SVR) and original GS in two test sites. The results showed that the proposed method was successful in optimizing the intensity component and therefore preserved the colour content of the input multispectral image more successfully than other methods used.
Road Distress Measurements Using UAV
Mustafa Zeybek, Serkan Bicici
Maintenance and rehabilitation of the road are very serious actions. Therefore, road conditions should be inspected accurately before taking these actions. Manual and visual inspection in the field is the traditionally used method to monitor road conditions. However, it is time-consuming, labor-intense and costly. In addition, the traditional inspection method is unsafe directly for the inspectors and indirectly for primary users of the road, such as pedestrians and drivers. In this study, the unmanned aerial vehicle (UAV) was used to inspect the road condition. UAV technology is becoming a valuable tool for collecting data efficiently and accurately. The proposed method involved three steps. First, several images were acquired from a UAV flight. Then, these images were used to generate a three-dimensional (3D) point cloud, digital surface model and orthomosaic. Finally, road distresses were detected and measured from two-dimensional (2D) and 3D data. The measurements obtained from the proposed methodology were compared against the measurements obtained from the traditional inspection method. It was found that both measurements produced similar results. In conclusion, the use of the UAV measurement technique was found to be suitable for detecting road distress. Given the advantages of the proposed methodology, it can also be inferred that UAVs can be used instead of the traditional inspection method.
A Web Platform for the Generation of Labeled Data for Deep Learning
Compared to conventional RGB images, new problems arise in the use of satellite images for deep learning. The absence of labeled training data for remotely sensed images is one of these problems. One of the methods that can solve the problem of insufficient labelled data available for satellite images in a short time and accurately is crowdsourcing. This study introduces a web platform created to ensure that the labelled data for high-resolution satellite images can be collected by the masses. This platform has a dynamic structure and is designed to be used by different users simultaneously. In order to create tagged data, users can use Google Earth satellite images covering the entire Earth’s surface as well as new images added to the database. In this way, it will be possible to generate labelled data for all types of classes (buildings, roads, forests, streams, hazelnuts, tea, ships, planes, etc.) that can be extracted from images around the world. Help documents have been added to the web platform to identify training classes for users, enabling them to use the platform effectively. Users can use the polygon tool to create descriptive fields for the classes specified in the help document to create labels. Data verification module has also been added to the web platform in order to determine the correct and incorrect labels. In this module, users verify and score the labels created by other people using the help document. As a result, the correctly labelled data with the highest score are selected.
Ekrem Saralioglu, Oguz Gungor
Improving SVM Classification Accuracy with Image Fusion-Based Gabor Texture Features
Cigdem SERIFOGLU YILMAZ, Oguz GUNGOR
Image fusion is one of the most common techniques used to enhance the interpretability and functionality of remotely sensed data. The aim of this study was to improve the performance of the SVM (Support Vector Machines) classifier with the aid of texture features (TF) extracted from fused images. As a first step, the spatial resolution of the WorldView-2 MS (multispectral) imagery was increased by fusing it with a WorldView-2 PAN (panchromatic) image using the PCA (Principal Component Analysis), WSB (Wavelet Single Band), GS (Gram-Schmidt), BRV (Brovey), EHL (Ehlers), HCS (Hyperspherical Colour Space), HPF (High-Pass Filtering) and MCV (Multiplicative) algorithms. A PCA transform was then applied on all fused images. The first principal component obtained from each fused image was used to extract the Gabor TFs. As a final step, extracted Gabor TFs were combined with the original MS image. Resultant images were classified with the SVM algorithm to investigate to what degree the used methodology affect the classification accuracy. The results showed that the GS fusion-based Gabor TFs provided the greatest classification accuracy increase with 19.3%, whereas the PCA fusion-based Gabor TFs resulted in the second best classification accuracy increase with 18.7%.
The Use of Terrestrial Laser Scanning Technology in Architectural Documentation: A case study of Historical Seismology Building
Asli Sabuncu, Haluk Ozener
Terrestrial laser scanning, one of the main subjects of geomatics engineering, is an important technological development that is frequently used in many different studies including industrial design studies, mining and infrastructure studies, modeling and design of cities, architectural restoration and documentation studies etc. In this study, it is aimed to modelling and documenting the architectural Science History Collection (Historical Seismology Building) building located in the Kandilli Campus of Boğaziçi University by using a terrestrial laser scanning tool. For this purpose, before the study, a reconnaissance survey was performed around the building and the positions of the terrestrial laser scanner and the stations were homogeneously distributed in the study area to minimize the error that may arise when combining point clouds. The Historical Seismology Building was measured by terrestrial laser scanning device from 17 stations and a 3D model of the building was produced from the obtained point clouds. All scanned stations of the point clouds were adjusted and errors of 3.7 mm, 1.5 mm and 4.1 mm were found in horizontal direction, vertical direction and average length, respectively. This error was found to be within the error limits. This study is just a start for the university, and it is aimed to apply terrestrial technology in the studies of documenting different cultural assets within the campuses of the university, especially Kandilli Campus.
The Earth Surface Stability Observation by Satellite Radar Images
Remote sensing is the art of acquisition of information about any objects (such as the Earth) without making any physical/close contact. Remote sensing has many vital civilian and none-civilian applications. Interferometric Synthetic Aperture Radar (InSAR) is a radar technique used in geoscience and remote sensing to measure the Earth surface deformation from 800 km above the Earth. In particular, Permanent/persistent/point-like Scatterer Interferometry (PSI) is a powerful remote sensing technique, which is able to measure the deformation on the Earth’s surface over temporal baselines. This technique was developed to estimate the temporal characteristics of the Earth’s deformation rates from multiple radar images acquired over time (series). This paper reviews InSAR and PSI techniques, and explains the current state of the art and potentials of the available radar remote sensing techniques. One case study is examined, pertaining to well-known deformation problem in the Mexico City area.