Road Segmentation for Remote Sensing Images Using Adversarial Spatial Pyramid Networks

Road extraction in remote sensing images is of great importance for a wide range of applications. Because of the complex background, and high density, most of the existing methods fail to accurately extract a road network that appears correct and complete. Moreover, they suffer from either insufficient training data or high costs of manual annotation. To address these problems, we introduce a new model to apply structured domain adaption for synthetic image generation and road segmentation. We incorporate a feature pyramid (FP) network into generative adversarial networks to minimize the difference between the source and target domains. A generator is learned to produce quality synthetic images, and the discriminator attempts to distinguish them. We also propose a FP network that improves the performance of the proposed model by extracting effective features from all the layers of the network for describing different scales' objects. Indeed, a novel scale-wise architecture is introduced to learn from the multilevel feature maps and improve the semantics of the features. For optimization, the model is trained by a joint reconstruction loss function, which minimizes the difference between the fake images and the real ones. A wide range of experiments on three data sets prove the superior performance of the proposed approach in terms of accuracy and efficiency. In particular, our model achieves state-of-the-art 78.86 IOU on the Massachusetts data set with 14.89M parameters and 86.78B FLOPs, with 4× fewer FLOPs but higher accuracy (+3.47% IOU) than the top performer among state-of-the-art approaches used in the evaluation.

I. Introduction

Currently road segmentation in remote sensing (RS) images has become one of the crucial tasks in many urban applications such as traffic management, urban planning, and road monitoring. Meanwhile, it is tremendously time-consuming to manually label roads from the high-resolution images. Unsupervised models, which are based on the predefined features, achieved low accuracy and failed on heterogeneous regions. However, supervised deep learning models, have achieved high performance in most of computer vision tasks, such as object detection [1]–[3], semantic segmentation [4]–[6], and skeleton extraction [7]. With the improvement of convolution neural networks, road detection from RS images tends to be an efficient and effective process.