Sürdürülebilir Kalkınma Amaçları

• 1
• 1

Yazarlar

• Doğan, Gürkan(2)
• Ergen, Burhan(2)
• Uyanık, Hakan(1)
• Şener, Abdullah(1)

• MakaleAçık Erişim2025Scopus SJRQ1/r/munzur/821
  A new lightweight convolutional neural network model for detecting drivable road regions

  Doğan, Gürkan; Uyanık, Hakan; Ergen, Burhan

  Nowadays, due to the rapid increase in the number of autonomous vehicles on the market, the safe navigation of these vehicles in drivable road areas has become extremely important. One of the most crucial factors in ensuring safe navigation is addressing the detection of drivable road areas as a task of semantic segmentation. Considering that autonomous vehicles are modular, the algorithm to perform this task must have the optimum trade-off in terms of lightweight, computational complexity, and segmentation accuracy. In this study, RoNet, a new model based on convolutional neural networks that provides an optimum trade-off for the detection of drivable road regions, was designed and proposed. The standard convolution types for the encoder and decoder bottleneck module of the RoNet model, as well as the spatial edge attention mechanism, have been optimized by developing asymmetric convolution types using asymmetric atrous convolution, asymmetric convolution types using Prewitt and Sobel kernels. Spatial edge attention mechanism is designed to reduce the loss of detailed information in small-resolution feature maps. In experimental tests performed with CamVid and FUVid datasets, RoNet achieved a better trade-off in terms of segmentation accuracy, number of parameters, and computational complexity compared to other state-of-the-art methods.

  • 
  • 
  AtıfScopus3·WoS3·OpenAlex6

  İncele
• MakaleAçık Erişim2024Scopus SJRQ2/r/munzur/1792
  A novel convolutional neural network model with hybrid attentional atrous convolution module for detecting the areas affected by the flood

  Şener, Abdullah; Doğan, Gürkan; Ergen, Burhan

  Natural disasters are sudden and unexpected events that occur as a result of natural processes and often have a significant impact on people, animals, and plants, often resulting in material and emotional losses. Two of the most devastating disasters are floods and tsunamis. After these disasters, search and rescue operations to identify flooded areas are very important to save the lives of affected people and to ensure the health and safety of rescue workers. In this study, a novel semantic segmentation model called Flood Area Segmentation Network (FASegNet) was proposed to guide search and rescue teams in disaster areas to speed up search and rescue operations after natural disasters such as floods, high tides, and tsunamis. The obtained results were compared with common image segmentation models used in various fields. It was found that the developed model achieved higher accuracy rates with fewer parameters. When tested with the "Flood Area" and "Water Body" datasets without pretraining and data augmentation, FASegNet achieved mIoU accuracy of 84.3% and 84.5% respectively.

  AtıfScopus23·WoS21·OpenAlex23

  İncele