To develop a deep learning model for real-time traffic sign recognition to aid autonomous and self-driving cars in safely navigating roads.
To evaluate the performance of the developed model in terms of accuracy, speed, and robustness in varying weather and lighting conditions.
Conduct a literature review on existing approaches and algorithms for traffic sign recognition in the context of autonomous vehicles.
Collect and preprocess a dataset of traffic sign images from public sources or through image capture using a camera mounted on a vehicle.
Design and implement a convolutional neural network (CNN) architecture for traffic sign recognition, considering factors such as model complexity, training time, and inference speed.
Train the model on the collected dataset and fine-tune hyperparameters to optimize performance.
Evaluate the model using metrics such as precision, recall, and F1 score, and compare it with state-of-the-art methods.
Conduct experiments to assess the model's performance under challenging conditions, such as low-light environments and occluded signs.
