Advanced lane and object detection systems are critical for improving the safety and efficiency of autonomous vehicles. This research leverages state-of-the-art deep learning techniques to accurately detect road elements, enabling enhanced navigation and decision-making. Models such as CLRNet (ResNet FasterRCNN), and SCNN (SSD VGG16) are utilized for lane marking detection, while YOLO variants (v5, v5x6, v8, and v9) are integrated for object detection. Among these, YOLOv9 demonstrated superior performance with a mean Average Precision (mAP) of 94.7%. The methodology includes dataset preprocessing, image visualization, model development, and training to achieve optimal detection accuracy. The best-performing model is deployed for real-time detection tasks, supported by a Flask-based frontend with user authentication for secure interaction and feedback collection. These advancements contribute to robust solutions for lane and object detection, aiming to enhance road safety and autonomous navigation.