OTONOM ARAÇLAR İÇİN MİKRODENETLEYİCİ TABANLI ÇEVRESEL GÜVENLİK SİSTEMİ TASARIMI
Year 2022,
Volume: 6 Issue: 2, 39 - 47, 30.12.2022
Umutcan Tüzün
,
Merdan Özkahraman
,
Bekir Aksoy
Abstract
Günümüzde sağlık alanı, video işleme, robot görüşü, sürücüsüz araç gibi pek çok örnekte karşımızı çıkan görüntü işleme sürekli büyüyen bir daldır. Görüntü işleme uygulamaları, otonom araçlarda nesne algılama ve şerit takibinin yapılabilmesinde oldukça fayda sağlamaktadır. Bu tez çalışmasında trafik kazalarındaki artış ve sürücü hataları göz önünde bulundurularak sürücü hatası sebebiyle oluşan kazaları en aza indirgemek ve otonom araçlara olan güveni artırmak hedeflenerek bir otonom araç sistemi geliştirilmiştir. Görüntü işleme, Raspberry Pi’a OpenCv kütüphanesi kurularak gerçekleştirilmiştir. Bu sayede şerit takibi yapılmış ve hareketli nesneler algılanmıştır. Yol sınırları ve kenarların algılanması için Canny kenar algoritmasından yararlanılmıştır. Yazılımlar için Python programlama dili kullanılarak kodlar yazılmıştır. Çalışmanın trafikte güvenli sürüşe ve araçlardaki görüntü işleme uygulamalarının artırılmasını sağlamaya yardımcı olacağı düşünülmektedir.
Supporting Institution
TÜBİTAK
Project Number
1919B012102178
Thanks
Projeyi 2209-A Üniversite Öğrencileri Araştırma Projelerini Destekleme Programı kapsamında maddi olarak destekleyen TÜBİTAK'a teşekkür ederiz.
References
- Anonim (2017). OpenCV Dersleri (Ders:16) Canny Kenar Algılama. http://mavienginberk.blogspot.com/2017/06/opencv-dersleri-ders16-cannykenar.html (Son erişim tarihi: 30.05.2022)
- Assidiq, A. A. (2008). Vision-based road lane detection for autonomous vehicles (Master's thesis, Gombak: International Islamic University Malaysia, 2008).
- Bingöl, M. S., Kaymak, Ç., & Uçar, A. (2019). Derin öğrenme kullanarak otonom araçların insan sürüşünden öğrenmesi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1), 177-185.
- Bounini, F., Gingras, D., Lapointe, V., & Pollart, H. (2015, October). Autonomous vehicle and real time road lanes detection and tracking. In 2015 IEEE Vehicle Power and Propulsion Conference (VPPC) (pp. 1-6). IEEE.
- Day, C., McEachen, L., Khan, A., Sharma, S., & Masala, G. (2019, September). Pedestrian recognition and obstacle avoidance for autonomous vehicles using raspberry Pi. In Proceedings of SAI Intelligent Systems Conference (pp. 51- 69). Springer, Cham.
- Fernandes, S., Duseja, D., & Muthalagu, R. (2021). Application of Image Processing Techniques for Autonomous Cars. Proceedings of Engineering and Technology Innovation, 17, 1
- Gupta, A. (2021). Top Python Libraries For Image Processing In 2021. https://www.analyticsvidhya.com/blog/2021/04/top-python-libraries-forimage-processing-in-2021/ (Son erişim tarihi: 30.05.2022)
- Khandelwal, N. (2022). Image Processing in Python: Algorithms, Tools, and Methods You Should Know. https://neptune.ai/blog/image-processing-python (Son erişim tarihi: 30.05.2022)
- More, C. S., Debbarma, S., Kandpal, N., & Singh, V. (2019). Open CV Python Autonomous Car. People, 6(01).
- Nguyen, T.B. (2017). Evaluation of lane detection algorithms based on an embedded platform. (Master’s thesis, Chemnitz University of Technology, Chemnitz, Germany.)
- Panfilova, E., Shipitko, O. S., & Kunina, I. (2021, January). Fast Hough transformbased road markings detection for autonomous vehicle. In Thirteenth International Conference on Machine Vision (Vol. 11605, p. 116052B). International Society for Optics and Photonics.
- Rastogi, A. (2020). Computer Vision: Lane Finding Through Image Processing. https://medium.com/swlh/computer-vision-lane-finding-through-imageprocessing-516797e59714 (Son erişim tarihi: 30.05.2022)
- Rossi, A., Ahmed, N., Salehin, S., Choudhury, T. H., & Sarowar, G. (2020). Real-time lane detection and motion planning in Raspberry Pi and Arduino for an autonomous vehicle prototype. arXiv preprint arXiv:2009.09391.
- Schwarting, W., Alonso-Mora, J., & Rus, D. (2018). Planning and decision-making for autonomous vehicles. Annual Review of Control, Robotics, and Autonomous Systems, 1(1), 187-210.
- Seçkin, M. E. (2021). Derin öğrenme kullanılarak trafik koşullarına uygun otonom araç uygulaması (Doctoral dissertation, Bursa Uludag University (Turkey)).
- Tian, D. (2019). DeepPiCar-Part 1: How to Build a Deep Learning, Self Driving Robotic Car on a Shoestring Budget. https://towardsdatascience.com/deeppicar-part-1-102e03c83f2c (Son erişim tarihi: 17.05.2022)
- Ujjainiya, L., & Chakravarthi, M. K. (2015). Raspberry-Pi based cost effective vehicle collision avoidance system using image processing. ARPN J. Eng. Appl. Sci, 10(7).
MICROCONTROLLER BASED ENVIRONMENTAL SAFETY SYSTEM DESIGN FOR AUTONOMOUS VEHICLES
Year 2022,
Volume: 6 Issue: 2, 39 - 47, 30.12.2022
Umutcan Tüzün
,
Merdan Özkahraman
,
Bekir Aksoy
Abstract
Today, image processing is an ever-growing branch that we encounter in many examples such as healthcare, video processing, robot vision, and driverless vehicles. Image processing applications are very useful for object detection and lane tracking in autonomous vehicles. In this thesis, an autonomous vehicle system has been developed with the aim of minimizing the accidents caused by driver error and increasing the confidence in autonomous vehicles, taking into account the increase in traffic accidents and driver errors. Image processing was carried out by installing OpenCv library in Raspberry Pi. In this way, lane tracking was performed and moving objects were detected. Canny edge algorithm is used to detect road boundaries and edges. Codes were written for the software using the Python programming language. It is thought that the study will help safe driving in traffic and increase the image processing applications in vehicles.
Project Number
1919B012102178
References
- Anonim (2017). OpenCV Dersleri (Ders:16) Canny Kenar Algılama. http://mavienginberk.blogspot.com/2017/06/opencv-dersleri-ders16-cannykenar.html (Son erişim tarihi: 30.05.2022)
- Assidiq, A. A. (2008). Vision-based road lane detection for autonomous vehicles (Master's thesis, Gombak: International Islamic University Malaysia, 2008).
- Bingöl, M. S., Kaymak, Ç., & Uçar, A. (2019). Derin öğrenme kullanarak otonom araçların insan sürüşünden öğrenmesi. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1), 177-185.
- Bounini, F., Gingras, D., Lapointe, V., & Pollart, H. (2015, October). Autonomous vehicle and real time road lanes detection and tracking. In 2015 IEEE Vehicle Power and Propulsion Conference (VPPC) (pp. 1-6). IEEE.
- Day, C., McEachen, L., Khan, A., Sharma, S., & Masala, G. (2019, September). Pedestrian recognition and obstacle avoidance for autonomous vehicles using raspberry Pi. In Proceedings of SAI Intelligent Systems Conference (pp. 51- 69). Springer, Cham.
- Fernandes, S., Duseja, D., & Muthalagu, R. (2021). Application of Image Processing Techniques for Autonomous Cars. Proceedings of Engineering and Technology Innovation, 17, 1
- Gupta, A. (2021). Top Python Libraries For Image Processing In 2021. https://www.analyticsvidhya.com/blog/2021/04/top-python-libraries-forimage-processing-in-2021/ (Son erişim tarihi: 30.05.2022)
- Khandelwal, N. (2022). Image Processing in Python: Algorithms, Tools, and Methods You Should Know. https://neptune.ai/blog/image-processing-python (Son erişim tarihi: 30.05.2022)
- More, C. S., Debbarma, S., Kandpal, N., & Singh, V. (2019). Open CV Python Autonomous Car. People, 6(01).
- Nguyen, T.B. (2017). Evaluation of lane detection algorithms based on an embedded platform. (Master’s thesis, Chemnitz University of Technology, Chemnitz, Germany.)
- Panfilova, E., Shipitko, O. S., & Kunina, I. (2021, January). Fast Hough transformbased road markings detection for autonomous vehicle. In Thirteenth International Conference on Machine Vision (Vol. 11605, p. 116052B). International Society for Optics and Photonics.
- Rastogi, A. (2020). Computer Vision: Lane Finding Through Image Processing. https://medium.com/swlh/computer-vision-lane-finding-through-imageprocessing-516797e59714 (Son erişim tarihi: 30.05.2022)
- Rossi, A., Ahmed, N., Salehin, S., Choudhury, T. H., & Sarowar, G. (2020). Real-time lane detection and motion planning in Raspberry Pi and Arduino for an autonomous vehicle prototype. arXiv preprint arXiv:2009.09391.
- Schwarting, W., Alonso-Mora, J., & Rus, D. (2018). Planning and decision-making for autonomous vehicles. Annual Review of Control, Robotics, and Autonomous Systems, 1(1), 187-210.
- Seçkin, M. E. (2021). Derin öğrenme kullanılarak trafik koşullarına uygun otonom araç uygulaması (Doctoral dissertation, Bursa Uludag University (Turkey)).
- Tian, D. (2019). DeepPiCar-Part 1: How to Build a Deep Learning, Self Driving Robotic Car on a Shoestring Budget. https://towardsdatascience.com/deeppicar-part-1-102e03c83f2c (Son erişim tarihi: 17.05.2022)
- Ujjainiya, L., & Chakravarthi, M. K. (2015). Raspberry-Pi based cost effective vehicle collision avoidance system using image processing. ARPN J. Eng. Appl. Sci, 10(7).