İnsansız Hava Araçları Kullanılarak Deforme Olmuş Karayolu Çizgilerinin Tespitinde Yapay Zekâ Yöntemlerinin Kullanılması

Abstract

Teknolojinin hızla ilerlemesiyle birlikte yapay zekanın (AI) eğitim, sağlık, güvenlik ve savunma gibi çeşitli sektörlerde kullanımı giderek artıyor. Yapay zekanın kritik bir uygulaması, özellikle otonom araçların yükselişiyle birlikte otoyol yönetimidir. Bu çalışmanın odak noktası, otonom araçlar için zorluklar oluşturan ve trafik güvenliğini etkileyen otoyol işaretleme çizgilerindeki deformasyonlar sorununu ele almaktır. Araştırma, otoyol hatlarının orijinal bir görüntü veri kümesini oluşturmak için insansız hava aracının (İHA) kullanılmasını içeriyor. Bu veri seti, görüntü iyileştirme teknikleri ve derin öğrenme modelleriyle işlenecektir. İlk aşama, görüntülerin yabancı maddelerden temizlenmesini içerir. Daha sonra derin öğrenme modelleri potansiyel hat deformasyonlarını belirleyecektir. Bu modeller, çeşitli performans ölçümleri kullanılarak optimum doğruluk için geliştirilecek ve eğitilecektir. Nihai hedef, İHA'yı yerdeki bilgisayar sistemiyle birleştirerek otoyol hatlarındaki farklılıkları doğru bir şekilde tespit etmek ve raporlamak için gerçek zamanlı bir sistem uygulamaktır. Bu, yetkililere zamanında bildirim yapılmasını sağlayacak ve hat deformasyonlarıyla ilgili trafik güvenliği sorunlarının önlenmesine yardımcı olacaktır. Bu yaklaşım, yapay zekanın yol güvenliğini ve otonom araç navigasyonunu iyileştirmedeki pratik uygulamalarını gösteriyor.

Keywords

• Derin öğrenme
• İnsansız hava aracı
• Görüntü işleme

Using Artificial Intelligence Methods in Detecting Deformed Highway Lines Using Unmanned Aerial Vehicles

Abstract

With the rapid advancement of technology, artificial intelligence (AI) is increasingly used in various sectors like education, health, security, and defense. A critical application of AI is in highway management, especially with the rise of autonomous vehicles. The focus of this study is to address the issue of deformations in highway marking lines, which pose challenges for autonomous vehicles and impact traffic safety. The research involves using an unmanned aerial vehicle (UAV) to create an original image dataset of highway lines. This dataset will undergo processing with image enhancement techniques and deep learning models. The initial phase involves cleaning the images of impurities. Subsequently, deep learning models will identify potential line deformations. These models will be refined and trained for optimal accuracy using various performance metrics. The final goal is to implement a real-time system, combining the UAV with a ground computer system, to accurately detect and report any discrepancies in highway lines. This will ensure timely notification to authorities, helping prevent traffic safety issues related to line deformations. This approach demonstrates the practical applications of AI in enhancing road safety and autonomous vehicle navigation.

Keywords

• Deep Learing
• Unmanned aerial vehicle
• Image processing

References

1. [1] S. Thrun, M. Montemerlo, H. Dahlkamp, D. Stavens, A. Aron, J. Diebel, P. Fong, J. Gale, M. Halpenny, G. Hoffmann, K. Lau, C. Oakley, M. Palatucci, V. Pratt, P. Stang, S. Strohband, C. Dupont, L. E. Jendrossek, C. Koelen, C. Markey, C. Rummel, J. van Niekerk, E. Jensen, P. Alessandrini, G. Bradski, B. Davies, S. Ettinger, A. Kaehler, A. Nefian and P. Mahoney, “Stanley: the robot that won the darpa grand challenge,” J. Field Robotics, vol. 23, pp. 661-692, 2006. doi:10.1002/rob.20147
2. [2] C. Urmson, J. Anhalt, D. Bagnell, C. Baker, R. Bittner, M. N. Clark, J. Dolan, D. Duggins, T. Galatali, C. Geyer, M. Gittleman, S. Harbaugh, M. Hebert, T. M. Howard, S. Kolski, A. Kelly, M. Likhachev, M. McNaughton, N. Miller, K. Peterson, B. Pilnick, R. Rajkumar, P. Rybski, B. Salesky, Y. W. Seo, S. Singh, J. Snider, A. Stentz, W. Whittaker, Z. Wolkowicki, J. Ziglar, H. Bae, T. Brown, D. Demitrish, B. Litkouhi, J. Nickolaou, Va. Sadekar, W. Zhang, J. Struble, M. Taylor, M. Darms and D. Ferguson, “Autonomous driving in urban environments: boss and the urban challenge,” J. Field Robotics, vol 25, pp. 425-466, 2008. doi:10.1002/rob.20255
3. [3] Waymo, "Waymo's journey," http://www.waymo.com, [Online]. Available: http://www.waymo.com [Accessed September 2023].
4. [4] D. J. Fagnant and K. Kockelman, “Preparing a nation for autonomous vehicles: opportunities, barriers and policy recommendations,” Transportation Research Part A: Policy and Practice, vol. 77, pp. 167-181, 2015 doi:10.1016/j.tra.2015.04.003.
5. [5] R. Merkert and J. Bushell, “Managing the drone revolution: A systematic literature review into the current use of airborne drones and future strategic directions for their effective control,” Journal of air transport management, vol. 89, pp. 101929, 2020. doi:10.1016/j.jairtraman.2020.101929.
6. [6] F. Ahmed, J. C. Mohanta, A. Keshari, and P. S. Yadav, “Recent advances in unmanned aerial vehicles: a review,” Arabian Journal for Science and Engineering, vol. 47, pp. 7963-7984, 2022. doi:10.1007/s13369-022-06738-0
7. [7] G. Macrina, L. D. P. Pugliese, F. Guerriero and G. Laporte, “Drone-aided routing: a literature review,” Transportation Research Part C: Emerging Technologies, vol. 120, pp. 102762, 2020. doi:10.1016/j.trc.2020.102762.
8. [8] H. Wang, T. Fu, Y. Du, W. Gao, K. Huang, Z. Liu, P. Chandak, S. Liu, P. Van Katwyk, A. Deac, A. Anandkumar, K. Bergen, C. P. Gomes, S. Ho, P. Kohli, J. Lasenby, J. Leskovec, Y. Liu, A. Manrai, D. Marks, B. Ramsundar, L. Song, J. Sun, J. Tang, P. Veličković, M. Welling, L. Zhang, C. W. Coley, Y. Bengio and M. Zitnik, “Scientific discovery in the age of artificial intelligence,” Nature, vol. 620, pp. 47-60, 2023. doi:10.1038/s41586-023-06221-2.

9. [9] S. J. Russell and P. Norvig, “Artificial intelligence a modern approach,” London: Pearson, 2021 [10] Y. LeCun, Y. Bengio and G. Hinton. “Deep learning”, nature, vol. 521, pp. 436-444, 2015. doi:10.1038/nature14539.
10. [11] L. Breiman, “Random forests,” Machine learning, vol. 45, pp. 5-32, 2001. doi:10.1023/A:1010933404324.
11. [12] K. M. Na, K. Lee, S. K. Shin and H. Kim, “Detecting deformation on pantograph contact strip of railway vehicle on image processing and deep learning,” Applied Sciences, vol. 10, pp. 8509, 2020. doi:10.3390/app10238509.
12. [13] J. Cao, C. Song, S. Song, F. Xiao and S. Peng ,“Lane detection algorithm for intelligent vehicles in complex road conditions and dynamic environments,” Sensors, vol. 19, pp. 3166, 2019. doi:10.3390/s19143166.
13. [14] T. Liu, Z. Chen, Y. Yang and H. Li “Lane detection in low-light conditions using an efficient data enhancement: Light conditions style transfer,” In 2020 IEEE intelligent vehicles symposium (IV), 2020, Las Vegas, NV, USA, 2020. pp. 1394-1399. IEEE. doi:10.1109/IV47402.2020.9304613.
14. [15] A.Punagin and S.Punagin, “Analysis of lane detection techniques on structured roads using OpenCV, ” International Journal for Research in Applied Science and Engineering Technology, vol.8, pp. 2994-3003. doi:10.22214/ijraset.2020.5502.
15. [16] S.Joy , B. S. Mamta , T. B. Mukesh, M. M. Ahmed, and U. Kiran, “Real time road lane detection using computer vision techniques in python, ” In 2022 International Conference on Automation, Computing and Renewable Systems (ICACRS), December 2022, Pudukkottai, India, 2022, pp. 1228-1232. doi: 10.1109/ICACRS55517.2022.10029238.
16. [17] Z. M. Chng, J. M. H. Lew and J. A. Lee, "RONELD: Robust Neural Network Output Enhancement for Active Lane Detection," 25th International Conference on Pattern Recognition (ICPR), 2020, Milan, Italy, 2021, pp. 6842-6849, doi: 10.1109/ICPR48806.2021.9412572.
17. [18] R. Bibi, Y. Saeed, A. Zeb, T. M. Ghazal, T. Rahman, R. A. Said, S. Abbas, M. Ahmad and M. A. Khan, “Edge ai-based automated detection and classification of road anomalies in VANET using deep learning, " Computational intelligence and neuroscience, 2021, pp. 1-16. doi:10.1155/2021/6262194.
18. [19] D. Luo, J. Lu and G. Guo, "Road Anomaly Detection Through Deep Learning Approaches," in IEEE Access, vol. 8, pp. 117390-117404, 2020, doi: 10.1109/ACCESS.2020.3004590.
19. [20] A. Howard, M. Sandler, G. Chu, L. C. Chen, B. Chen, M. Tan, W. Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le and H. Adam; "CCNet: criss-cross attention for semantic segmentation," Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Oct 27-Nov. 2, 2019, Seoul, Korea (South), 2019, pp. 1314-1324
20. [21] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, "Mobilenetv2: Inverted residuals and linear bottlenecks," In Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, Salt Lake City, USA, 2018. pp. 4510-4520. IEEE.
21. [22] F. Chollet, "Xception: Deep learning with depthwise separable convolutions. "In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, Honolulu, Hawai, 2017. pp. 1251-1258. IEEE.
22. [23] B. Zoph, V. Vasudevan, J. Shlens, and Q. V. Le, "Learning transferable architectures for scalable image recognition." In Proceedings of the IEEE conference on computer vision and pattern recognition, 18-23 June, 2018, Salt Lake City, USA, 2018. pp. 8697-8710.
23. [24] M. Tan, and Q. Le, "Efficientnet: Rethinking model scaling for convolutional neural networks."In International conference on machine learning, 10-15 June, Long Beach, USA, 2019, pp. 6105-6114.
24. [25] W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed , C.Y. Fu, and A.C. Berg, "Single shot multibox detector. " In Computer Vision–ECCV 2016: 14th European Conference, 11-14 Oct., 2016, Amsterdam, Netherlands, 2016, pp. 21-37.
25. [26] A. Canziani, A. Paszke, and E. Culurciello, “An analysis of deep neural network models for practical applications”, arxiv.org, 2016. [Online]. Avaible https://arxiv.org/abs/1605.07678 [Accessed September 2023].
26. [27] G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, Honolulu, HI, USA, 2017, pp. 2261-2269. doi: 10.1109/CVPR.2017.243.
27. [28] K. He, X. Zhang, S. Ren, and J. Sun, "Identity mappings in deep residual networks. " In Computer Vision–ECCV 2016: 14th European Conference, 11-14 Oct., 2016, Amsterdam, Netherlands, 2016, pp. 630-645..
28. [29] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems, vol. 25, pp. 1-9, 2012.
29. [30] G. Litjens, T. Kooi, B. E. Bejnordi, A. A. A. Setio, F. Ciompi, M. Ghafoorian, J.A.W.M. van der Laak, B. van Ginneken and C.I. Sánchez, "A survey on deep learning in medical image analysis." Medical image analysis, vol. 42, pp. 60-88, 2017. doi:10.1016/j.media.2017.07.005
30. [31] D. E. Rumelhart, G. E. Hinton and R. J. Williams, "Learning representations by back-propagating errors. " nature, vol. 32, no.6088, pp. 533-536, 1986. doi:10.1038/323533a0
31. [32] I. Goodfellow, Y.Bengio and A. Courville, Deep learning, Cambridge, MA: MIT press. 2016.