Creative Commons License

Bülbül H. İ., Dikbayır S.

Tübav Bilim Dergisi, vol.13, no.3, pp.1-14, 2020 (ESCI)

  • Publication Type: Article / Article
  • Volume: 13 Issue: 3
  • Publication Date: 2020
  • Journal Name: Tübav Bilim Dergisi
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Other Indexes
  • Page Numbers: pp.1-14
  • Gazi University Affiliated: Yes


Thanks to unmanned aerial vehicles’ mobility and high altitude; it has an increasing use in many areas such as area detection, traffic monitoring and traffic control in today. Real time vehicle detection and vehicle count are the one of the important works to be done by using unmanned aerial vehicles. For this purpose, deep learning, machine learning and many image processing techniques come to the fore. Within the scope of this study, a vehicle detection application has been developed by using the convolutional neural networks structure from deep learning architectures and with the help of real-time object detection algorithm, YOLO. YOLO algorithm performance is tried to be increased with the help of convolutional neural network structure. As a result of the study, the success of YOLO has been increased by %4,3 in the tests performed using different data sets and it has been observed that the input values of 400x400 can reach 60 fps transaction value. The structure that can be used for vehicle detection in real time applications has been introduced.