Bilgisayarla Görme Destekli Otonom Araç Prototipinin Tasarımı ve Uygulaması

Öz

Son yıllarda, otomotiv üreticileri, bilgi teknolojileri sağlayıcıları, ticari elektronik çip üreticileri otonom araçlar (OA) için bir yatırım yarışına girdiklerinden, OA birçok altyapıda kullanılmaya başlamıştır. OA seyir halindeyken, otomatik kontrol sistemlerini kullanarak sürücüye ihtiyaç duymadan yolu, trafik akışını ve çevreyi algılayarak kendi kendine gidebilen otomobillerdir. OA, radar, lidar, GPS, odyometri ve bilgisayarla görme gibi teknolojileri kullanarak etrafındaki nesneleri algılayabilir. Bu çalışmada, bilgisayarla görme tabanlı bir otonom araç prototipinin tasarımı ve uygulaması önerilmektedir. Geliştirilen prototip, kameradan elde edilen görüntüleri işleyerek şerit takibi ve trafik işareti kontrolü gerçekleştirebilmektedir ve mesafe sensörü ile etrafındaki nesneleri algılayabilmektedir. Geliştirilen OA prototipinde görüntüleri işlemek ve motorları kontrol etmek için Raspberry Pi 3B+ modülü ve trafik işaretlerini tanımak için kaskad sınıflandırıcı kullanılmıştır. Yapılan testlerde trafik işaretleri 7 farklı senaryoda tanınmış ve performansları karşılaştırılmıştır. Sonuçlara göre tek trafik işareti ile yapılan testlerde doğruluk oranı %94,8'dir. Sonuç olarak, bu çalışmada geliştirilen otonom araç prototipi, trafik işaretlerini başarıyla tanıyabilmektedir ve farklı senaryolarda belirlenen rotada hareket edebilmektedir.

Anahtar Kelimeler

• Otonom araçlar
• Bilgisayarla görme
• Raspberry Pi
• Kaskad sınıflandırıcı
• Trafik işareti tanıma
• Şerit takibi

Design and Implementation of Computer Vision Based Autonomous Vehicle Prototype

Öz

In recent years, since automotive makers, IT providers, commercial electronic chip manufacturers have entered a rapid investment race for autonomous vehicles (AVs), they have started to be used in many infrastructures. AVs are automobiles that can drive themselves using the automatic control systems while cruising by sensing the road, traffic flow and surroundings without the need for a driver. AVs can detect objects around them using technologies such as radar, lidar, GPS, audiometry and computer vision. In this study, the design and implementation of a computer vision-based autonomous vehicle prototype is proposed. The developed prototype can perform lane tracking and traffic sign control by processing images obtained from the camera, and can detect objects around it with the distance sensor. In the AV prototype, the Raspberry Pi 3B+ module is used to process the images and control the motors, and the cascade classifier is used to recognize the traffic signs. In the performed tests, traffic signs are recognized in 7 different scenarios and the performances are compared. According to the results, the accuracy rate is 94,8% in the tests performed with only one traffic sign. As a result, the autonomous vehicle prototype developed in this study can successfully recognize traffic signs and move on the determined route in different scenarios.

Anahtar Kelimeler

• Autonomous vehicles
• Computer vision
• Raspberry Pi
• Cascade classifier
• Traffic sign recognition
• Lane tracking

Kaynakça

1. Ahmadi A. Cascade Classifier GUI. 2021; Available online: https://amin-ahmadi.com/cascade-trainer-gui/. (Accessed on: 29.01.2021)
2. Anderson J.M., Nidhi K., Stanley K.D., Sorensen P., Samaras C., & Oluwatola O.A., Autonomous vehicle technology: A guide for policymakers. 2014: Rand Corporation.
3. Anthony S. Google’s self-driving car passes 700,000 accident-free miles, can now avoid cyclists, stop at railroad crossings. 2014; Available online: https://www.extremetech.com/extreme/181508-googles-self-driving-car-passes-700000-accident-free-miles-can-now-avoid-cyclists-stop-for-trains. (Accessed on: 20.10.2021)
4. Bechtel M.G., McEllhiney E., Kim M., & Yun H. Deeppicar: A low-cost deep neural network-based autonomous car. 2018 IEEE 24th international conference on embedded and real-time computing systems and applications (RTCSA) 2018. IEEE.
5. Burns L.D., A vision of our transport future. Nature 2013; 497(7448): 181-182.
6. Dandıl E. & Özkul İ., Futbol maçları için bilgisayarlı görü destekli gol karar sistemi (golkasis): Bir prototip çalışma. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji 2019; 7(1): 213-224.
7. Deac M.-A., Al-doori R.W.Y., Negru M., & Dǎnescu R. Miniature autonomous vehicle development on raspberry pi. 2018 IEEE 14th International Conference on Intelligent Computer Communication and Processing (ICCP) 2018. IEEE.
8. El-Tawab S., Sprague N., & Mufti A. Autonomous vehicles: Building a test-bed prototype at a controlled environment. 2020 IEEE 6th World Forum on Internet of Things (WF-IoT) 2020. IEEE.

9. Fagnant D.J. & Kockelman K., Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations. Transportation Research Part A: Policy and Practice 2015; 77: 167-181.
10. Gouda M., Chowdhury I., Weiß J., Epp A., & El-Basyouny K., Automated assessment of infrastructure preparedness for autonomous vehicles. Automation in construction 2021; 129: 103820.
11. Haboucha C.J., Ishaq R., & Shiftan Y., User preferences regarding autonomous vehicles. Transportation Research Part C: Emerging Technologies 2017; 78: 37-49.
12. Harper C.D., Hendrickson C.T., Mangones S., & Samaras C., Estimating potential increases in travel with autonomous vehicles for the non-driving, elderly and people with travel-restrictive medical conditions. Transportation Research Part C: Emerging Technologies 2016; 72: 1-9.
13. Hossai M.R.T., Shahjalal M.A., & Nuri N.F. Design of an IoT based autonomous vehicle with the aid of computer vision. 2017 International Conference on Electrical, Computer and Communication Engineering (ECCE) 2017. IEEE.
14. Hough P.V., Method and means for recognizing complex patterns, 1962; Google Patents.
15. KGM. Karayoları Genel Müdürlüğü (KGM) Trafik İşaretleri El Kitabı. 2015; Available online: https://www.kgm.gov.tr/SiteCollectionDocuments/KGMdocuments/Trafik/IsaretlerElKitabi/TrafikIsaretleriElKitabi2015.pdf. (Accessed on: 29.10.2020)
16. Meyer J., Becker H., Bösch P.M., & Axhausen K.W., Autonomous vehicles: The next jump in accessibilities? Research in transportation economics 2017; 62: 80-91.
17. Mukhopadhyay P. & Chaudhuri B.B., A survey of Hough Transform. Pattern recognition 2015; 48(3): 993-1010.
18. NHTSA. National Highway Traffic Safety Administration-Automated Vehicles for Safety. 2021; Available online: https://www.nhtsa.gov/technology-innovation/automated-vehicles-safety. (Accessed on: 20.10.2021)
19. NumPy. 2021; Available online: https://numpy.org/doc/stable/. (Accessed on: 04.04.2021)
20. OpenCV. 2021a; Available online: https://opencv.org/. (Accessed on: 29.01.2021)
21. OpenCV. Cascade Classifier Training. 2021b; Available online: https://docs.opencv.org/4.5.4/dc/d88/tutorial_traincascade.html. (Accessed on: 29.01.2020)
22. Python. 2021; Available online: https://www.python.org. (Accessed on: 29.01.2021)
23. Rossi A., Ahmed N., Salehin S., Choudhury T.H., & Sarowar G., Real-time Lane detection and Motion Planning in Raspberry Pi and Arduino for an Autonomous Vehicle Prototype. arXiv preprint arXiv:2009.09391 2020.
24. Van Brummelen J., O’Brien M., Gruyer D., & Najjaran H., Autonomous vehicle perception: The technology of today and tomorrow. Transportation Research Part C: Emerging Technologies 2018; 89: 384-406.
25. Viola P. & Jones M. Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001 2001. IEEE.
26. Wadud Z., Fully automated vehicles: A cost of ownership analysis to inform early adoption. Transportation Research Part A: Policy and Practice 2017; 101: 163-176.
27. Wiseman Y., Autonomous vehicles, Encyclopedia of Information Science and Technology, Fifth Edition 2021; IGI Global. 1-11.