Abstract
Semantic segmentation using machine learning and computer vision techniques is one of the most popular topics in autonomous driving-related research. With the revolution of deep learning, the need for more efficient and accurate segmentation systems has increased. This paper presents a detailed review of deep learning-based frameworks used for semantic segmentation of road scenes, highlighting their architectures and tasks. It also discusses well-known standard datasets that evaluate semantic segmentation systems in addition to new datasets in the field. To overcome a lack of enough data required for the training process, data augmentation techniques and their experimental results are reviewed. Moreover, domain adaptation methods that have been deployed to transfer knowledge between different domains in order to reduce the domain gap are presented. Finally, this paper provides quantitative analysis and performance evaluation and discusses the results of different frameworks on the reviewed datasets and highlights future research directions in the field of semantic segmentation using deep learning.