Abstract
Recent advances in deep-learning methods have shown extraordinary performance in road extraction from high resolution satellite imagery. However, most existing deep-learning network models yield discontinuous and incomplete results because of shadows and occlusions. To address this problem, a dual-attention road extraction network (DA-RoadNet) with a certain semantic reasoning ability is proposed. First, DA-RoadNet is designed based on a shallow encoder-to-decoder network with densely connected blocks, which can minimize the loss of road structure information caused by multiple down-sampling operations. Moreover, by constructing a novel attention mechanism module, the proposed network is able to explore and integrate the invisible correlations among road features with their global dependency in spatial and channel dimension respectively. Finally, considering that the proportion of road samples is small in the satellite imagery, a hybrid loss function is appended to handle class imbalance, which enables the network model to train stablely and avoid local optimum. The validation experiments using two open road datasets demonstrate that the proposed DA-RoadNet can effectively solve discontinuous problems and preserve integrity of the extracted roads, thus resulting in a higher accuracy of road extraction compared with other developed state-of-the-arts. The considerable performance on the two challenging benchmarks also proves the powerful generation ability of our method.
Highlights
H IGH-PRECISION and timely updated road network information play a critical role in many real world applications, Manuscript received February 4, 2021; revised April 28, 2021; accepted May 18, 2021
4) We propose a DA-RoadNet for road extraction from high resolution satellite imagery and carry out extensive experiments on two challenging benchmark datasets, the experimental results demonstrate the effectiveness and powerful generalization ability of the proposed method
The skip-connection can offset part of structural information loss caused by pooling operations in a way by connecting low-level feature maps to high-low feature maps, but plenty of background information is introduced in the meantime, the nonroad information will affect the recovery of road features in the decoder and cause false segmentation results
Summary
H IGH-PRECISION and timely updated road network information play a critical role in many real world applications, Manuscript received February 4, 2021; revised April 28, 2021; accepted May 18, 2021. Since it is expensive and laborious to update road network by the way of visual interpretation [4], there has been a promising way to extract road network from high resolution satellite imagery quickly and accurately [5]. Automatic road extraction [6]–[8] based on high resolution satellite imagery has been the key and difficult point in the field of remote sensing in the recent years. The road is a relatively open area, the trees or buildings on roadsides and the vehicles on the road may lead to the existence of shadows and occlusions in high resolution satellite imagery. It is still challenging to extract road at high quality from high resolution satellite imagery
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
