This study investigates the performance effect of using recurrent neural networks (RNNs) for semantic segmentation of urban scene images, to generate a semantic output map with refined edges. We proposed three deep neural network architectures using recurrent neural networks and evaluated them on the Cityscapes dataset. All three proposed architectures outperformed the baseline and shown improvement in classifying edges. Additionally, we showed a new method for using RNN for any prior semantic segmentation network that makes use of skip connections. PyTorch was the selected framework for conducting this study.
https://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1494982&dswid=-5063
