Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets

Gülcan Yıldız; Bekir Dizdaroğlu; Doğan Yıldız

doi:10.29130/dubited.1732289

TR EN

Abstract

Trafik kazalarının büyük bir bölümü, sürücü kaynaklı hatalardan kaynaklanmakta ve bu kazalar çoğunlukla ciddi yaralanmalarla veya can kaybıyla sonuçlanmaktadır. Bu olumsuz durumun önüne geçebilmek amacıyla, özellikle son yıllarda akıllı ulaşım sistemlerine yönelik ilgi ve yatırımlar artış göstermektedir. Akıllı ulaşım teknolojilerinin kritik bileşenlerinden biri olan yol şerit tespiti, araçların kendi şeritleri içinde kalmalarını sağlayarak hem güvenli sürüşü desteklemekte hem de şerit ihlallerine bağlı kaza riskini azaltmaktadır. Bu çalışmada, görüntü işleme yöntemleri ile Destek Vektör Regresyonu (Support Vector Regression - SVR) tekniklerinin bütünleştirildiği yenilikçi bir yol şerit tespit modeli önerilmiştir. Geliştirilen modelde, araç içi kameralardan elde edilen yol görüntüleri üzerinde öncelikle perspektif dönüşümü gerçekleştirilmiş, ardından renk uzayı dönüşümü ile görsel ayrıştırma sağlanmış ve çeşitli morfolojik işlemler uygulanarak yol şerit çizgileri belirginleştirilmiştir. Şerit çizgileri tespit edildikten sonra, SVR tabanlı eğri uydurma algoritması ile şeritlerin eğimli yapısı modellenmiş ve bu sayede yol geometrisine uygun, tutarlı bir şerit yapısı oluşturulmuştur. Ayrıca, tespit edilen şeritler arasındaki alan renklendirilerek sürüş hattı daha anlaşılır hale getirilmiştir. Önerilen yaklaşım, iki farklı veri seti üzerinde test edilmiştir. İlki, Türkiye'de çeşitli yol koşullarında tarafımızca oluşturulan özgün bir veri setidir; diğeri ise otonom sürüş ve mobil robotik çalışmaları için sıklıkla kullanılan Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) veri setidir. Deneysel sonuçlar, her iki veri seti üzerinde de önerilen yöntemin yüksek doğrulukla şeritleri tespit edebildiğini ve çeşitli sürüş senaryolarında güvenilir sonuçlar sunduğunu göstermektedir. Bu bağlamda, geliştirilen modelin akıllı sürüş sistemlerinde gerçek zamanlı şerit takibi uygulamaları için etkili ve uygulanabilir bir çözüm sunduğu değerlendirilmektedir.

Keywords

Destek vektör regresyonu, Görüntü işleme, Yol şerit tespiti

Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets

Abstract

Traffic accidents are largely caused by human errors and often result in severe injuries or loss of life. To mitigate these risks, intelligent transportation systems have gained increasing attention in recent years. Lane detection is a fundamental component of such systems, as it supports safe driving by ensuring that vehicles remain within their designated lanes and by reducing accidents caused by lane violations. In this study, an effective lane detection model that integrates traditional image processing techniques with Support Vector Regression (SVR) is proposed. In the developed model, perspective transformation is first performed on the road images obtained from in-car cameras, then visual separation is provided with color space transformation, and various morphological operations are applied to highlight the lane lines. After the lane lines are detected, the curved structure of the lanes is modeled with the SVR-based curve fitting algorithm, and thus a consistent lane structure suitable for the road geometry is created. In addition, the area between the detected lanes is colored to make the driving line more understandable. The proposed method is evaluated on two different datasets: an original dataset created by us under various road conditions in Türkiye and the publicly available Karlsruhe Institute of Technology and Toyota Technological Institute (KITTI) dataset, which is widely used in autonomous driving research. For the Türkiye dataset, lane regions are manually labeled, and the system performance is quantitatively assessed using accuracy, precision, recall, specificity, F1-score, and Intersection-over-Union (IoU) metrics. In addition, the SVR-based curve fitting approach is compared with the classical Hough Transform under identical preprocessing conditions. The comparative results demonstrate that the proposed method achieves higher accuracy and reliability across multiple evaluation metrics. Overall, the experimental findings indicate that the proposed approach provides a robust and practical solution for lane detection and tracking in intelligent driving systems.

Keywords

Support vector regression, Image processing, Road lane detection

Supporting Institution

This research received no external funding.

Ethical Statement

This study does not involve human or animal participants. All procedures followed scientific and ethical principles, and all referenced studies are appropriately cited.

Thanks

The authors do not wish to acknowledge any individual or institution.

References

Ahmed, S. K., Mohammed, M. G., Abdulqadir, S. O., Abd El-Kader, R. G., El-Shall, N. A., Chandran, D., Ur Rehman, M. E., & Dhama, K. (2023). Road traffic accidental injuries and deaths: A neglected global health issue. Health Science Reports, 6(5), Article e1240. https://doi.org/10.1002/hsr2.1240
Baek, S.-W., Kim, M.-J., Suddamalla, U., Wong, A., Lee, B.-H., & Kim, J.-H. (2022). Real-time lane detection based on deep learning. Journal of Electrical Engineering & Technology, 17(1), 655–664. https://doi.org/10.1007/s42835-021-00902-6
Bar Hillel, A., Lerner, R., Levi, D., & Raz, G. (2014). Recent progress in road and lane detection: A survey. Machine Vision and Applications, 25(3), 727–745. https://doi.org/10.1007/s00138-011-0404-2
Bradski, G. (2000). The OpenCV library. Dr. Dobb's Journal: Software Tools for the Professional Programmer, 25(11), 120–123.
Charran, R. S., & Dubey, R. K. (2022). Two-wheeler vehicle traffic violations detection and automated ticketing for Indian road scenario. IEEE Transactions on Intelligent Transportation Systems, 23(11), 22002–22007. https://doi.org/10.1109/TITS.2022.3186679
Eid Kishawy, M. M., Abd El-Hafez, M. T., Yousri, R., & Darweesh, M. S. (2024). Federated learning system on autonomous vehicles for lane segmentation. Scientific Reports, 14(1), Article 25029. https://doi.org/10.1038/s41598-024-71187-8
Formosa, N., Quddus, M., Man, C. K., Singh, M. K., Morton, C., & Masera, C. B. (2024). Evaluating the impact of lane marking quality on the operation of autonomous vehicles. Journal of Transportation Engineering, Part A: Systems, 150(1), Article 04023126. https://doi.org/10.1061/JTEPBS.TEENG-7688
Fritsch, J., Kühnl, T., & Geiger, A. (2013). A new performance measure and evaluation benchmark for road detection algorithms. In 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) (pp. 1693–1700). IEEE. https://doi.org/10.1109/ITSC.2013.6728473
Gonzalez, R. C., & Woods, R. E. (2009). Digital image processing (3rd ed.). Pearson Education.
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv. https://doi.org/10.48550/arXiv.1704.04861

Kim, J., & Lee, M. (2014). Robust lane detection based on convolutional neural network and random sample consensus. In C. K. Loo, K. S. Yap, K. W. Wong, A. Teoh, & K. Huang (Eds.), Neural information processing (pp. 454–461). Springer. https://doi.org/10.1007/978-3-319-12637-1_57
Kumar, H., Mamoria, P., & Dewangan, D. K. (2025). Vision technologies in autonomous vehicles: Progress, methodologies, and key challenges. International Journal of System Assurance Engineering and Management, 16(12), 4035–4068. https://doi.org/10.1007/s13198-025-02912-3
Lee, D.-H., & Liu, J.-L. (2023). End-to-end deep learning of lane detection and path prediction for real-time autonomous driving. Signal, Image and Video Processing, 17(1), 199–205. https://doi.org/10.1007/s11760-022-02222-2
Li, J., Jiang, F., Yang, J., Kong, B., Gogate, M., Dashtipour, K., & Hussain, A. (2021). Lane-DeepLab: Lane semantic segmentation in automatic driving scenarios for high-definition maps. Neurocomputing, 465, 15–25. https://doi.org/10.1016/j.neucom.2021.08.105
Liu, B., Liu, H., & Yuan, J. (2019). Lane line detection based on Mask R-CNN. In Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019) (pp. 696–699). Atlantis Press. https://doi.org/10.2991/icmeit-19.2019.111
Mu, C., & Ma, X. (2014). Lane detection based on object segmentation and piecewise fitting. TELKOMNIKA Indonesian Journal of Electrical Engineering, 12(5), 3491–3500.
Parbat, D., & Chakraborty, M. (2020). A python based support vector regression model for prediction of COVID19 cases in India. Chaos, Solitons & Fractals, 138, Article 109942. https://doi.org/10.1016/j.chaos.2020.109942
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In N. Navab, J. Hornegger, W. M. Wells, & A. F. Frangi (Eds.), Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 (pp. 234–241). Springer. https://doi.org/10.1007/978-3-319-24574-4_28
Sapkal, A., Arti, Pawar, D., & Singh, P. (2023). Lane detection techniques for self-driving vehicle: Comprehensive review. Multimedia Tools and Applications, 82(22), 33983–34004. https://doi.org/10.1007/s11042-023-14446-6
Sayed, S. A., Abdel-Hamid, Y., & Hefny, H. A. (2023). Artificial intelligence-based traffic flow prediction: A comprehensive review. Journal of Electrical Systems and Information Technology, 10(1), Article 13. https://doi.org/10.1186/s43067-023-00081-6
Shilaskar, S., Patil, V., Pawar, S., Poke, A., Jambhulkar, R., & Bhatlawande, S. (2023). Driver safety system using microcontroller and image processing. In 2023 International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT) (pp. 340–344). IEEE. https://doi.org/10.1109/IDCIoT56793.2023.10053512
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14, 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
Soille, P. (1999). Morphological image analysis: Principles and applications. Springer. https://doi.org/10.1007/978-3-662-03939-7
Szeliski, R. (2022). Computer vision: Algorithms and applications (2nd ed.). Springer. https://doi.org/10.1007/978-3-030-34372-9
Undit, H. J. A., Hassan, M. F. A., & Zin, Z. M. (2021). Vision-based unmarked road detection with semantic segmentation using Mask R-CNN for lane departure warning system. In 2021 4th International Symposium on Agents, Multi-Agent Systems and Robotics (ISAMSR) (pp. 1–6). IEEE. https://doi.org/10.1109/ISAMSR53229.2021.9567892
Vapnik, V. N. (1995). The nature of statistical learning theory. Springer. https://doi.org/10.1007/978-1-4757-2440-0
Ye, Y. Y., Hao, X. L., & Chen, H. J. (2018). Lane detection method based on lane structural analysis and CNNs. IET Intelligent Transport Systems, 12(6), 513–520. https://doi.org/10.1049/iet-its.2017.0143
Yildiz, G., Ulu, A., Dizdaroglu, B., & Yildiz, D. (2023). Hybrid image improving and CNN (HIICNN) stacking ensemble method for traffic sign recognition. IEEE Access, 11, 69536–69552. https://doi.org/10.1109/ACCESS.2023.3292955
Yoo, J. H., Lee, S.-W., Park, S.-K., & Kim, D. H. (2017). A robust lane detection method based on vanishing point estimation using the relevance of line segments. IEEE Transactions on Intelligent Transportation Systems, 18(12), 3254–3266. https://doi.org/10.1109/TITS.2017.2679222
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018). ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 6848–6856). IEEE. https://doi.org/10.1109/CVPR.2018.00716
Zhuang, L., Jiang, T., Qiu, M., Wang, A., & Huang, Z. (2024). Transformer generates conditional convolution kernels for end-to-end lane detection. IEEE Sensors Journal, 24(17), 28383–28396. https://doi.org/10.1109/JSEN.2024.3430234
Zou, Q., Jiang, H., Dai, Q., Yue, Y., Chen, L., & Wang, Q. (2019). Robust lane detection from continuous driving scenes using deep neural networks. IEEE Transactions on Vehicular Technology, 69(1), 41–54. https://doi.org/10.1109/TVT.2019.2949603

Details

Primary Language

English

Subjects

Supervised Learning, Machine Learning Algorithms

Journal Section

Research Article

Authors

Gülcan Yıldız
0000-0001-8631-8383
Türkiye

Bekir Dizdaroğlu
0000-0002-2955-1776
Türkiye

Doğan Yıldız ^*
0000-0001-9670-4173
Türkiye

Publication Date

October 23, 2026

Submission Date

July 1, 2025

Acceptance Date

July 25, 2026

Published in Issue

Year 2026 Volume: 14 Number: 4

DOI

https://doi.org/10.29130/dubited.1732289

IZ

https://izlik.org/JA37SM33CG

APA

Yıldız, G., Dizdaroğlu, B., & Yıldız, D. (2026). Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets. Duzce University Journal of Science and Technology, 14(4), 1050-1062. https://doi.org/10.29130/dubited.1732289

AMA

1.Yıldız G, Dizdaroğlu B, Yıldız D. Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets. DUBİTED. 2026;14(4):1050-1062. doi:10.29130/dubited.1732289

Chicago

Yıldız, Gülcan, Bekir Dizdaroğlu, and Doğan Yıldız. 2026. “Road Lane Detection With SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets”. Duzce University Journal of Science and Technology 14 (4): 1050-62. https://doi.org/10.29130/dubited.1732289.

EndNote

Yıldız G, Dizdaroğlu B, Yıldız D (October 1, 2026) Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets. Duzce University Journal of Science and Technology 14 4 1050–1062.

IEEE

[1]G. Yıldız, B. Dizdaroğlu, and D. Yıldız, “Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets”, DUBİTED, vol. 14, no. 4, pp. 1050–1062, Oct. 2026, doi: 10.29130/dubited.1732289.

ISNAD

Yıldız, Gülcan - Dizdaroğlu, Bekir - Yıldız, Doğan. “Road Lane Detection With SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets”. Duzce University Journal of Science and Technology 14/4 (October 1, 2026): 1050-1062. https://doi.org/10.29130/dubited.1732289.

JAMA

1.Yıldız G, Dizdaroğlu B, Yıldız D. Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets. DUBİTED. 2026;14:1050–1062.

MLA

Yıldız, Gülcan, et al. “Road Lane Detection With SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets”. Duzce University Journal of Science and Technology, vol. 14, no. 4, Oct. 2026, pp. 1050-62, doi:10.29130/dubited.1732289.

Vancouver

1.Gülcan Yıldız, Bekir Dizdaroğlu, Doğan Yıldız. Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets. DUBİTED. 2026 Oct. 1;14(4):1050-62. doi:10.29130/dubited.1732289

Abstract

Keywords

Road Lane Detection with SVR Based Image Processing Methods: A Study on Türkiye and KITTI Datasets

Abstract

Keywords

Supporting Institution

Ethical Statement

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite