Detekce a rozpoznání dopravních značek na křižovatkách

Abstract

The goal of the thesis is to create an application, which can detect intersection road traffic signs, and get information out of additional road sign about shape of intersection. To create this detector we will use convolutional neural networks, which is recognized as state-of-the-art method for detecting objects in images. The Implementation itself was written in Tensorflow framework, using Object detection API. Then a dataset for training and testing of the neural network was created. In first part, we will describe basic principles of convolutional neural networks. Next, we will describe model used for detection. In last part, we will go through our implementation and testing in real-time.