The road extraction from high resolution remote sensing image is of great importance in a variety of applications. Recently, the abundant deep convolutional neural networks are proposed for road extraction task. However, the existing approaches lack suitable strategy to utilize multiple views road features for road extraction, which fails to extract road with smooth appearance and accurate boundary under complex scenes. To address this problem, the authors propose a novel deep residual and pyramid pooling network (DRPPNet) for extracting road regions from high resolution remote sensing image. The DRPPNet consists of three parts: deep residual network (DResNet), pyramid pooling module (PPM) and deep decoder (DD). Specially, the DResNet uses several residual blocks to extract deep road features from input images, which can enhance learning ability of DRPPNet and avoid gradient vanish. Then, PPM is proposed to fuse road features from multiple views and it aims to address disadvantage of single view feature. Finally, the DD is used to recover size of feature maps to input size. Extensive experiments on two challenging road datasets demonstrate that proposed method outperforms the state-of-the-art methods greatly on performance of road extraction task.
INTRODUCTIONThe road is the backbone and essential infrastructure in many domains, such as urban planning, geographic information system updating and traffic navigation [1][2][3][4][5][6][7]. Recently, with the rapid development of satellites, high resolution remote sensing image can be easily accessed and contains road information in more detail, which provides a promising way to extract road. However, manually labeling roads in high resolution remote sensing image will cost a lot of time and effort [8,9]. To overcome this problem, many automatic methods, such as SVM [10,11] and CRF [12], have been proposed to extract road from high resolution remote sensing image. Compared with manual extraction method, automatic road extraction methods are more efficient and economical.With the development of deep learning, convolutional neural networks (CNNs) not only have been widely and successfully applied in semantic segmentation [13][14][15], but also play a key role in road extraction [16,17]. For example, [18][19][20] first used CNN to extract road from high resolution remote sensingThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.