Damla Tatlıcan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Damla Tatlıcan has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Orhan Yaman
Department of Digital Forensics Engineering, Firat University, 23119 Elazig, Turkey
2 shared publications - Abdulsamed Güneş
Firat Universitesi
1 shared publication - Mehmet Karakose
Computer Engineering Department, Firat University, 23119 Elazığ, Türkiye
1 shared publication - Nafiye Nur Apaydın
Firat University
1 shared publication - Yusuf Duran
Yildiz Teknik Üniversitesi
1 shared publication - Yüksel Yalçin
Yildiz Teknik Üniversitesi
1 shared publication
Latest Publications
- 15 September 2026
- Published by Gumushane University Journal of Science and Technology Institute in Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi
- Vol. 16 (4) , 1144-1159
Rooftop Photovoltaic Panel Segmentation in UAV Imagery Using Attention U-Net with a ResNet34 Encoder
Today, satellite image analysis and mapping systems play a significant role in urban planning, energy management, potential assessment, and sustainable development studies. In addition to the difficulty and high cost of fieldwork, the analysis of observations delays potential assessment and detection efforts. To overcome this delay and high cost, the use of satellite imagery is among the most important methods that facilitate these processes. In this study, a deep learning-based method is proposed to detect solar power plants from satellite imagery. This proposed method combines the U-Net architecture with an attention mechanism with the pre-trained ResNet34 encoder, enabling the efficient integration of both low-level and high-level features. The Albumentations library was used for data augmentation during the model training process, and the images were resized to 256x256. In the post-processing stage, the Dense Conditional Random Fields (CRF) method was applied to improve the accuracy of the segmentation masks generated by the model. For the test subset of the PV01 dataset, 95% IoU, 97% Dice, 99% Precision, 97% Recall, and 98% Accuracy were achieved. These results lead to lower costs and sharper results in determining energy potential.
- 15 September 2026
- Published by Gumushane University Journal of Science and Technology Institute in Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi
- Vol. 16 (4) , 1144-1159
Rooftop Photovoltaic Panel Segmentation in UAV Imagery Using Attention U-Net with a ResNet34 Encoder
Today, satellite image analysis and mapping systems play a significant role in urban planning, energy management, potential assessment, and sustainable development studies. In addition to the difficulty and high cost of fieldwork, the analysis of observations delays potential assessment and detection efforts. To overcome this delay and high cost, the use of satellite imagery is among the most important methods that facilitate these processes. In this study, a deep learning-based method is proposed to detect solar power plants from satellite imagery. This proposed method combines the U-Net architecture with an attention mechanism with the pre-trained ResNet34 encoder, enabling the efficient integration of both low-level and high-level features. The Albumentations library was used for data augmentation during the model training process, and the images were resized to 256x256. In the post-processing stage, the Dense Conditional Random Fields (CRF) method was applied to improve the accuracy of the segmentation masks generated by the model. For the test subset of the PV01 dataset, 95% IoU, 97% Dice, 99% Precision, 97% Recall, and 98% Accuracy were achieved. These results lead to lower costs and sharper results in determining energy potential.
- Open Access
- 30 April 2025
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 4 (2) , 66-75
Crowd Density Estimation via a VGG-16-Based CSRNet Model
Accurate crowd density estimation has become critical in applications ranging from intelligent urban planning and public safety monitoring to marketing analytics and emergency response. In recent developments, various methods have been used to enhance the precision of crowd analysis systems. In this study, a Convolutional Neural Network (CNN)-based approach was presented for crowd density detection, wherein the Congested Scene Recognition Network (CSRNet) architecture was employed with a Visual Geometry Group (VGG)-16 backbone. This method was applied to two benchmark datasets—Mall and Crowd-UIT—to assess its effectiveness in real-world crowd scenarios. Density maps were generated to visualize spatial distributions, and performance was quantitatively evaluated using Mean Squared Error (MSE) and Mean Absolute Error (MAE) metrics. For the Mall dataset, the model achieved an MSE of 0.08 and an MAE of 0.10, while for the Crowd-UIT dataset, an MSE of 0.05 and an MAE of 0.15 were obtained. These results suggest that the proposed VGG-16-based CSRNet model yields high accuracy in crowd estimation tasks across varied environments and crowd densities. Additionally, the model demonstrates robustness in generalizing across different dataset characteristics, indicating its potential applicability in both surveillance systems and public space management. The outcomes of this investigation offer a promising direction for future research in data-driven crowd analysis, particularly in enhancing predictive reliability and real-time deployment capabilities of deep learning models for population monitoring tasks.
- 30 April 2025
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 4 (2) , 66-75
Open AccessCrowd Density Estimation via a VGG-16-Based CSRNet Model
Accurate crowd density estimation has become critical in applications ranging from intelligent urban planning and public safety monitoring to marketing analytics and emergency response. In recent developments, various methods have been used to enhance the precision of crowd analysis systems. In this study, a Convolutional Neural Network (CNN)-based approach was presented for crowd density detection, wherein the Congested Scene Recognition Network (CSRNet) architecture was employed with a Visual Geometry Group (VGG)-16 backbone. This method was applied to two benchmark datasets—Mall and Crowd-UIT—to assess its effectiveness in real-world crowd scenarios. Density maps were generated to visualize spatial distributions, and performance was quantitatively evaluated using Mean Squared Error (MSE) and Mean Absolute Error (MAE) metrics. For the Mall dataset, the model achieved an MSE of 0.08 and an MAE of 0.10, while for the Crowd-UIT dataset, an MSE of 0.05 and an MAE of 0.15 were obtained. These results suggest that the proposed VGG-16-based CSRNet model yields high accuracy in crowd estimation tasks across varied environments and crowd densities. Additionally, the model demonstrates robustness in generalizing across different dataset characteristics, indicating its potential applicability in both surveillance systems and public space management. The outcomes of this investigation offer a promising direction for future research in data-driven crowd analysis, particularly in enhancing predictive reliability and real-time deployment capabilities of deep learning models for population monitoring tasks.