RADANet: Road Augmented Deformable Attention Network for Road Extraction From Complex High-Resolution Remote-Sensing Images

Extracting roads from complex high-resolution remote sensing images to update road networks has become a recent research focus. How to apply the contextual spatial correlation and topological structure of the roads properly to improve the extraction accuracy becomes a challenge in the increasingly complex road environment. In this article, inspired by the prior knowledge of the road shape and the progress in deformable convolution, we proposed a road augmented deformable attention network (RADANet) to learn the long-range dependencies for specific road pixels. We developed a road augmentation module (RAM) to capture the semantic shape information of the road from four strip convolutions. Deformable attention module (DAM) combines the sparse sampling capability of deformable convolution with the spatial self-attention mechanism. The integration of RAM enables DAM to extract road features more specifically. Furthermore, RAM is placed behind the fourth stage of encoder, and DAM is placed between last four stages of encoder and decoder in RADANet to extract multiscale road semantic information. Comprehensive experiments on representative public datasets (DeepGlobe and CHN6-CUG road datasets) demonstrate that our RADANet achieves advanced results compared with the state-of-the-art methods.

I. Introduction

Road information plays the fundamental role in many applications, such as smart city construction, urban planning, vehicle navigation, and automatic drive [1], [2], [3]. To obtain up-to-date road information in large-scale areas, extracting road network from high-resolution remote-sensing images has become a promising method. High-resolution remote sensing imagery has become the main data source for extracting road regions and updating geospatial databases in real time [4]. Although road extraction from high-resolution satellite imagery recently gained considerable attention, this task remains challenging owing to irregular and complex road sections and structures [5]. Therefore, various methods for extracting roads from high-resolution satellite imagery have been proposed.