Abstract
Road extraction is important for road network renewal, intelligent transportation systems and smart cities. This paper proposes an effective method to improve road extraction accuracy and reconstruct the broken road lines caused by ground occlusion. Firstly, an attention mechanism-based convolution neural network is established to enhance feature extraction capability. By highlighting key areas and restraining interference features, the road extraction accuracy is improved. Secondly, for the common broken road problem in the extraction results, a heuristic method based on connected domain analysis is proposed to reconstruct the road. An experiment is carried out on a benchmark dataset to prove the effectiveness of this method, and the result is compared with that of several famous deep learning models including FCN8s, SegNet, U-Net and D-Linknet. The comparison shows that this model increases the IOU value and the F1 score by 3.35–12.8% and 2.41–9.8%, respectively. Additionally, the result proves the proposed method is effective at extracting roads from occluded areas.
Highlights
Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China; Abstract: Road extraction is important for road network renewal, intelligent transportation systems and smart cities
In the feature fusion stage, this paper designs a method incorporating the attention mechanism, and connects the feature maps based on their correlation, which will further improve the attention given to key areas
Aiming at the low accuracy in road extraction caused by the limitations of neural networks, this paper proposes a convolutional neural network model based on an enhanced attention mechanism
Summary
Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China; Abstract: Road extraction is important for road network renewal, intelligent transportation systems and smart cities. With the increase of the number and resolution of remote sensing images, the automatic extraction of road information by computers has become a hot research topic [6,7,8]. The object-based method performs better in suppressing noise [26] It segments the images into multiple objects, each composed of pixels with similar spectral features, and filters the road objects [27,28,29,30,31], but this method is only effective for Academic Editor: Saeid Homayouni
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 callDisclaimer: 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.
