Sürdürülebilir Kalkınma Amaçları

• 2
• 2
• 1

• MakaleYalnız künye2026/r/gumushane/13612
  A Dense and Sparse Attention in Vision Transformer for Remote Sensing Image Classification

  Celik, Kemal

  Satellite imagery plays a crucial role in various applications, such as environmental monitoring, urban planning, and disaster response. Previously, Convolutional neural networks have played a crucial role in improving remote sensing scene classification by effectively capturing spatial features. However, they often struggle with long-range dependencies and complex spectral patterns in satellite images. Recently, transformer-based architectures, initially designed for natural language processing, have been adopted in computer vision to leverage self-attention mechanisms for capturing long-range dependencies. To effectively extract the long-range dependencies and complex patterns, this paper proposes a novel method combining dense and sparse attention mechanisms to enhance remote sensing scene classification in different scales. The dense attention mechanisms capture comprehensive connections within satellite images, followed by sparse attention mechanisms applied at both tile and patch scale levels. This multi-scale attention strategy allows the model to efficiently focus on important spatial and spectral features while managing computational complexity. Extensive experimental evaluations on three benchmark datasets, such as Merced, AID, and Optimal-31, demonstrate significant improvements in classification accuracy, achieving 98.9, 97.5, and 97.8, respectively. Experimental results show that the proposed framework outperforms CNN and Transformer baselines, enhancing the accuracy and robustness of remote sensing scene classification for geospatial analysis.

  • 
  İncele
• MakaleYalnız künye2024/r/gumushane/12639
  A New Approach for Ground Filtering of Airborne Laser Scanning Data Using PointNet++

  Akbulut, Zeynep; Karsli, Fevzi; Dihkan, Mustafa

  Ground filtering is an essential process that separates ground and non-ground points for generating digital elevation models (DEMs) from airborne laser scanning (ALS) point cloud data. Traditionally, ground filtering was carried out using rule-based approaches, but with the advancements in deep learning networks, ground filtering can now be performed using these methods. Deep neural networks (DNNs) require large amounts of training samples to reveal key information within the dataset. OpenGF is a new ultra-large-scale dataset which has nearly half a billion points from nine different scenes ranging from highly dense urban areas to steep vegetation covered mountains for ground filtering task. In this study, PointNet++ architecture was employed for ground filtering on the OpenGF dataset. Firstly, we slightly modified PointNet++ architecture’s sampling strategy to decrease the number of duplicate points in the batching process. We proposed a new adaptive tiling strategy based on input point cloud density to cope with highly varying point sampling of the OpenGF dataset. Modified PointNet++ architecture was trained with both adaptive tiling strategy and original OpenGF tiles to investigate the advantages and drawbacks of the proposed strategy on the ground filtering task. To evaluate the performance of the proposed strategy, the results for different test areas were compared with those obtained using the original PointNet++ and rule-based cloth simulation filtering (CSF) algorithms. Despite using fewer epochs, the proposed data collection strategy achieved up to 13% higher accuracy on test scenes with the modified PointNet++ architecture compared to the network trained with original OpenGF tiles.

  İncele
• MakaleYayıncıda açık erişim2022/r/gumushane/12787
  Analyzing and Predicting Spatiotemporal Urban Sprawl in Eskişehir Using Remote Sensing Data

  Küçük Matcı, Dilek; Çömert, Resul; Avdan, Uğur

  Urban areas of major cities in developing countries are expanding rapidly due to rapid population growth and industrialization. Determining the reasons for rapid urbanization and the amount of urban area that will be needed in the future is important for the planned growth of these cities. In this study, the LU/LC change of Eskisehir city center that has a rapid rate of urbanization and industrialization in Turkey between 1984 and 2020 was determined. Then, the area needed for urban and industrial areas in 2030 was investigated using the Cullullar Automata–Markov Chain (CA–MC) hybrid model simulation. Each year's LU/LC map was produced with over 80% kappa accuracies performing the pixel-based Random Forest (RF) algorithm for change analysis. In the change analysis made between 1984 and 2020, it was determined that there was a change of 117% in the urban area and 977% in the industrial area. The prediction was made for the validation of the CA–MC model from the period 2000–2010 to 2020. When compared with the 2020 LU/LC map, the model success was obtained as 0.84, 0.87, and 0.87 in the Kstandard, Klocation, and Kno Kappa metrics, respectively. By using the 2010–2020 periods in the estimation of 2030, it has been observed that the urban and industrial area will increase by 22.95%; therefore, there will be decreases in agriculture and other natural areas as in previous years.

  • 
  • 
  İncele
• MakaleYalnız künye2018/r/gumushane/13831
  An Extended Approach of Particle Swarm Optimization for Shoreline Extraction from RASAT Imagery

  Catal Reis, Hatice; Bayram, Bülent; Bozkurt, Salih; Ince, Abdulkadir; Demir, Nusret; Seker, Dursun Zafer

  This study presents an extended shoreline detection approach from pansharpened images of Turkish RASAT satellite which covers red, green and blue bands of the optical spectrum with 15 m ground resolution and panchromatic band with 7.5 m spatial resolution. The Lake Ercek of Turkey has been selected as the study area, which is a tectonic lake and home to a variety of water birds. The satellite images of the lake taken in 2013 and 2014 were considered for analysis. The proposed shoreline extraction system consists of a sequence of image processing steps in which simple linear clustering (SLIC) and particle swarm optimization (PSO) are the main components. SLIC was used to create superpixels that form basis for object-based image analysis while PSO was employed for classifying objects into corresponding classes. The resulting images still contained unwanted artefacts; therefore, a post-processing step was performed to improve the accuracy of segmentation by applying thresholding, morphological processing, and manual editing for noise removal. The proposed framework was applied on two temporal RASAT images to test the variations of defined parameter settings. The success of the proposed system was to obtain shorelines with satisfying accuracy without using NIR band. Finally, the extracted shorelines were vectorised and compared with manually digitized shorelines from pansharpened satellite images for accuracy assessment.

  İncele
• MakaleYalnız künye2018/r/gumushane/13377
  Automatic Building Extraction from Image and LiDAR Data with Active Contour Segmentation

  Akbulut, Zeynep; Özdemir, Samed; Acar, Hayrettin; Karsli, Fevzi

  Automatic building extraction is an important topic for many applications such as urban planning, disaster management, 3D building modeling and updating GIS databases. Its approaches mainly depend on two data sources: light detection and ranging (LiDAR) point cloud and aerial imagery both of which have advantages and disadvantages of their own. In this study, in order to benefit from the advantages of each data sources, LiDAR and image data combined together. And then, the building boundaries were extracted with the automated active contour algorithm implemented in MATLAB. Active contour algorithm uses initial contour positions to segment an object in the image. Initial contour positions were detected without user interaction by a series of image enhancements, band ratio and morphological operations. Four test areas with varying building and background levels of detail were selected from ISPRS’s benchmark Vaihingen and Istanbul datasets. Vegetation and shadows were removed from all the datasets by band ratio to improve segmentation quality. Subsequently, LiDAR point cloud data was converted to raster format and added to the aerial imagery as an extra band. Resulting merged image and initial contour positions were given to the active contour algorithm to extract building boundaries. In order to compare the contribution of LiDAR to the proposed method, the boundaries of the buildings were extracted from the input image before and after adding LiDAR data to the image as a layer. Finally extracted building boundaries were smoothed by the Awrangjeb (Int J Remote Sen 37(3): 551–579. https://doi.org/10.1080/01431161.2015.1131868, 2016) boundary regularization algorithm. Correctness (Corr), completeness (Comp) and accuracy (Q) metrics were used to assess accuracy of segmented building boundaries by comparing extracted building boundaries with manually digitized building boundaries. Proposed approach shows the promising results with over 93% correctness, 92% completeness and 89% quality.

  • 
  İncele
• MakaleYalnız künye2015/r/gumushane/12028
  Determination to Results of Forest Management Planning Applications with Land Use Changes from 1971 to 2008 in Yalova-Turkey

  Çakir, Günay; Özdemir, Mehmet

  The forest conservation organizations in Turkey have recommended changing the classical forest management systems to protect forest biodiversity since 2006. This study discusses the spatio-temporal analysis of forest management activities and land use changes in Yalova Forest Ecosystems, Turkey. We focused on the Yalova City because (a) it is located in a highly urbanized area, northwestern Turkey, (b) forest is a governmental ownership and producing of many non-wood forest product and wildlife species, (c) governmental organizations are encouraged to be decreased clear-cuts to protect forest ecosystems; (d) GIS databases are available in Yalova; (e) Yalova Forestry Administration has a membership of the Mediterranean Model Forest Network in 2011, and (f) many new forest policies will be developed in Turkey after the membership of the model forest. This study used forest management plans of Yalova Forest during 1971–2008 periods and analyzed data in geographic information system (GIS). Results showed that the rate of forest area in the Yalova steadily increased from 53.4 % in 1971 to 61.2 % to 62.5 % between 1994 and 2008 respectively.

  • 
  İncele