EHLM: Empirical Design of Novel Road Curve and Lane Identification Scheme using Effective Hybrid Learning Methodology

In this study, we present a novel Road Curve and Lane Identification Scheme that harnesses the power of an Effective Hybrid Learning Methodology (EHLM). This advanced approach combines Convolutional Neural Networks (CNN), Mask R-CNN, and ResNet, creating a formidable framework for road curve detection and lane identification in complex driving scenarios. The EHLM framework offers a versatile solution that excels in detecting road curves and accurately identifying lanes, crucial components of autonomous driving systems and advanced driver assistance. It leverages the strengths of each architecture, from CNN's feature extraction capabilities to Mask R-CNN's precise instance segmentation and ResNet's deep learning prowess. This study provides a comprehensive overview of the EHLM approach, showcasing its efficacy in real-world road scenarios. Through extensive experimentation and evaluation, we demonstrate the superiority of our methodology, achieving precise road curve detection and lane identification. Our research contributes to the development of safer and more efficient autonomous vehicles, ultimately enhancing road safety and transportation systems.In our evaluation, we have considered several models, including CNN, DCNN, MRCNN, CNN-LSTM, ANN, and our Proposed Model. Among these contenders, the Proposed Model stands out prominently in terms of accuracy, achieving an impressive 97.23%. This indicates its remarkable ability to correctly classify and recognize the target elements within the dataset.