부산대학교 도서관

Deep learning techniques provide solutions to various real-world problems and have given rise to many innovations. One such innovation is autonomous vehicles; the key parameter of autonomous vehicles is providing the correct path which is nothing but detecting the road lanes. We primarily focused on detecting the path using an image dataset. The dataset consists of images of roads taken during morning, night and in various weather conditions. The dataset contains around 5000+ images. The deep learning algorithm that we used is a convolution neural network. Convolution neural network mimics the human brain and it is the most used algorithm for image processing. We built a CNN model that takes an image as input and processes it through different layers and extracts the necessary features. The features extracted are used for identifying the path from the testing images with utmost accuracy. The deep learning model that can effectively detect the path is built using google colab.