Automobiles that drive themselves are called "Autonomous Vehicles" or "Self-Driving Cars". This car has the ability to sense around the environment. Without a human driver, an autonomous vehicle functions similarly to a conventional vehicle. In order to carry out their automated functions, autonomous vehicles depend on sensors, actuators, machine learning algorithms and software. Safety is an important aspect while driving, and ensuring safety and reducing accidents on the road is the primary concern for autonomous vehicles. Accidents takes place due to lack of response time to instant traffic events on the road. So, real-time monitoring and guidance to traffic is crucial for reducing accidents caused by delayed responses to sudden traffic events. This involves the use of Traffic Sign recognition and Road Lane detection. This study proposes a machine learning algorithm. Python is utilized for both, using the OpenCV standard file and the Hough Transformation technique. VGGNet is used for image recognition. With these resources we can train the shape models using a supervised learning algorithm and conduct detection in a manner that support vehicles in identifying road lanes and traffic signs. The method used in this, divides the video into a series of frames and generates image-features for each of them which are used to recognize the lanes and traffic signs on the road.