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

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.