Improving Road Semantic Segmentation Using Generative Adversarial Network

Abstract

Road network extraction from remotely sensed imagery has become a powerful tool for updating geospatial databases, owing to the success of convolutional neural network (CNN) based deep learning semantic segmentation techniques combined with the high-resolution imagery that modern remote sensing provides. However, most CNN approaches cannot obtain high precision segmentation maps with rich details when processing highresolution remote sensing imagery. In this study, we propose a generative adversarial network (GAN)-based deep learning approach for road segmentation from high-resolution aerial imagery. In the generative part of the presented GAN approach, we use a modified UNet model (MUNet) to obtain a high-resolution segmentation map of the road network. In combination with simple pre-processing comprising edge-preserving filtering, the proposed approach offers a significant improvement in road network segmentation compared with prior approaches. In experiments conducted on the Massachusetts road image dataset, the proposed approach achieves 91.54% precision and 92.92% recall, which correspond to a Mathews correlation coefficient (MCC) of 91.13%, a Mean intersection over union (MIOU) of 87.43% and a F1-score of 92.20%. Comparisons demonstrate that the proposed GAN framework outperforms prior CNN-based approaches and is particularly effective in preserving edge information.

A Residual Attention and Local Context-Aware Network for Road Extraction from High-Resolution Remote Sensing Imagery

“…Zhang et al [48] improved the U-net network by adding residual units, which simplified the training of the deep neural network and improved the generalization ability of the network model while reducing the number of parameters by adding multi-layer skip connections. Abdollahi et al [49] proposed a method to extract road information based on the generative adversarial network (GAN). In this method, the improved U-Net network was used to obtain road network feature maps, which retained edge information, for the most part, reduced the influence of occlusions from trees, and finally got ideal extraction results.…”

GAN-Based Satellite Imaging: A Survey on Techniques and Applications

“…To address this problem, Abdollahi et al [27] proposed a GAN-based deep learning approach for road segmentation from high-resolution aerial imagery with a modified U-Net model (MUNet) in the generative part of the presented GAN and edge-preserving filtering as the pre-processing phase. To alleviate the overfitting, Hu et al [3] proposed a diversitysensitive loss to force the generator to produce different synthetic images.…”

“…MUNet [79] is the modified version of U-Net used by Abdollahi et al [27] for road extraction. MUNet includes two cor-…”

Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI)

“…We used Python and the Keras with TensorFlow as a backend to apply the entire process of the suggested model for vegetation mapping from aerial data. Because of the lack of gradient vanishing impact, great computing efficiency, and sparsity property during back-propagation training, ReLU is a popular option of activation function in deep learning [47,48]. We utilized the Softmax function for the output layer L out to predict class possibilities after calculating a H for the last hidden layer.…”