In recent years, object detection, image segmentation, and autonomous driving have undergone rapid development due to major advances in deep learning and computer vision. In particular, modern object detection frameworks such as YOLO (You Only Look Once), SSD (Single Shot MultiBox Detector), and Faster R-CNN (Region-based Convolutional Neural Networks) have significantly improved detection accuracy while enabling faster and more efficient inference. Semantic and instance segmentation have been perfected with the help of models such as U-Net, Mask R-CNN and DeepLab resulting in more accurate and localized image analysis. These developments play a crucial role in autonomous driving where strong perception systems play a central role in navigation, avoidance of obstacles and making decisions in real-time. These innovative methods are used by autonomous vehicles to communicate with the surrounding environment to make their operation safer and efficient. This study reviews recent advances in object detection and image segmentation, examines their applications in autonomous driving systems, and highlights key challenges and directions for future research in these rapidly evolving areas.