Understanding Road Sceses using Deep Neural Networks
Abstract: Understanding road lcenes is crucial for autonomous cars. This requires segmenting road scenes into semantical9y meaningful regions and recognizing objects in a scene. While objects such as cars and pedestrians has to be segmented accurately, it might not be necessary to detect and locate these objects in a scene. iowever, detecting aid classifying objects such as traffic signs is essential for conforming to road rules.
In this thesis, we first propose a method for classifying traffic signs using visual attrHbutes and Bayesian networks. Then, we propose two neural network for this purpose and develop a new method for creating an ensemble of models. Next, we study sensitivity of neural networks against advernarial samples and propose two denoising networks that are attached to the classification networks to increase their stability against noise. In the second part of the thesis, we first propose a network to detect traffic signs in high-resolution images in real-time and show how to implement the scanning window technique withnn our network using dilated convolutions. Then, we formulate the detection problem as a segmentation problem>and propose a fully convolutional network for detecting traffic signs. Finally, we propose a new fully convolutional network composed of fire modules, bypass connections and consecutive dilated convolutions in the last part of the thesis for segmenting road scenes into semantically meaningful regions and show that it is more accurate and computationally more efficient compared to similar networks.