Research Article
BibTex RIS Cite

Development of CNN-based GUI for detection of non-motorized vehicles

Year 2022, Volume: 4 Issue: 3, 208 - 215, 01.10.2022
https://doi.org/10.47933/ijeir.1178790

Abstract

Today, various solutions are offered for traffic density. One of these suggestions is to popularize the use of bicycles in the category of non-motorized vehicles. For this, first of all, bicycle paths must be built. The use of bicycle lanes or the rate of bicycle use in normal traffic is an important data. Deep learning techniques, which have been popular in recent years, can be used to obtain this data. The aim of this study is to present a model that detects bicycles using various convolutional neural networks architectures. First of all, 962 open source bicycle images obtained from the internet are labeled. For this, trainings were conducted with YOLOv3, YOLOF, Faster R-CNN and Sparse R-CNN architectures. As a result of the trainings, a value of 0.92 mAP was reached with Faster R-CNN. At the end of the study, a software that detects bicycles in real time has been developed.

Project Number

1919B012102097

Thanks

This research was funded by the Scientific and Technology Research Council of Turkey (TUBITAK), under project name: TUBITAK 2209, 1919B012102097. The authors gratefully acknowledge the financial support provided by the TUBITAK.

References

  • Krizhevsky A, Sutskever I, Hinton GE Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 2012. pp 1097-1105 Tzelepi, M., & Tefas, A. (2017). Human crowd detection for drone flight safety using convolutional neural networks. In 2017 25th European Signal Processing Conference (EUSIPCO) (pp. 743-747). IEEE. https://doi.org/ 10.23919/EUSIPCO.2017.8081306

Motorsuz araçları tespiti için CNN tabanlı GUI geliştirilmesi

Year 2022, Volume: 4 Issue: 3, 208 - 215, 01.10.2022
https://doi.org/10.47933/ijeir.1178790

Abstract

Günümüzde trafik yoğunluğuna çeşitli çözüm önerileri sunulmaktadır. Bu önerilerden birisi de motorsuz araçlar sınıfında yer alan bisiklet kullanımının yaygınlaştırılmasıdır. Bunun için öncelikle bisiklet yollarının yapılması gerekmektedir. Bisklet yollarının kullanımı ya da normal trafikteki bisiklet kullanım oranı önemli bir veridir. Bu verinin elde edilmesi için son yıllarda popüler olan derin öğrenme tekniklerinden yararlanılabilir. Bu çalışmanın amacı çeşitli convolutional neural networks mimarileri kullanılarak bisiklet tespit eden bir model ortaya koymaktır. Öncelikle internet ortamından elde edilen 962 adet bisiklet görüntüsü etiketlenmiştir. Bunun için YOLOv3, YOLOF, Faster R-CNN ve Sparse R-CNN mimarileri ile eğitimler gerçekleştirilmiştir. Eğitimler sonucunda Faster R-CNN ile 0.92 mAP değerine ulaşılmıştır. Çalışma sonunda bir GUI tasarlanarak gerçek zamanlı olarak bisiklet tespiti yapan bir yazılım ortaya koyulmuştur.

Project Number

1919B012102097

References

  • Krizhevsky A, Sutskever I, Hinton GE Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, 2012. pp 1097-1105 Tzelepi, M., & Tefas, A. (2017). Human crowd detection for drone flight safety using convolutional neural networks. In 2017 25th European Signal Processing Conference (EUSIPCO) (pp. 743-747). IEEE. https://doi.org/ 10.23919/EUSIPCO.2017.8081306
There are 1 citations in total.

Details

Primary Language English
Subjects Engineering
Journal Section Research Articles
Authors

Sinan Uğuz 0000-0003-4397-6196

Oğulcan Çiftçi This is me 0000-0003-1069-6366

Project Number 1919B012102097
Early Pub Date October 1, 2022
Publication Date October 1, 2022
Acceptance Date September 30, 2022
Published in Issue Year 2022 Volume: 4 Issue: 3

Cite

APA Uğuz, S., & Çiftçi, O. (2022). Development of CNN-based GUI for detection of non-motorized vehicles. International Journal of Engineering and Innovative Research, 4(3), 208-215. https://doi.org/10.47933/ijeir.1178790

88x31.png

This work is licensed under a Creative Commons Attribution 4.0 International License