LAUSR.org creates dashboard-style pages of related content for over 1.5 million academic articles. Sign Up to like articles & get recommendations!

Edge-Reinforced Convolutional Neural Network for Road Detection in Very-High-Resolution Remote Sensing Imagery

Photo from wikipedia

Road detection in very-high-resolution remote sensing imagery is a hot research topic. However, the high resolution results in highly complex data distributions, which lead to much noise for road detection—for… Click to show full abstract

Road detection in very-high-resolution remote sensing imagery is a hot research topic. However, the high resolution results in highly complex data distributions, which lead to much noise for road detection—for example, shadows and occlusions caused by disturbance on the roadside make it difficult to accurately recognize road. In this article, a novel edge-reinforced convolutional neural network, combined with multiscale feature extraction and edge reinforcement, is proposed to alleviate this problem. First, multiscale feature extraction is used in the center part of the proposed network to extract multiscale context information. Then edge reinforcement, applying a simplified U-Net to learn additional edge information, is used to restore the road information. The two operations can be used with different convolutional neural networks. Finally, two public road data sets are adopted to verify the effectiveness of the proposed approach, with experimental results demonstrating its superiority.

Keywords: high resolution; road; edge; remote sensing; convolutional neural; road detection

Journal Title: Photogrammetric Engineering and Remote Sensing
Year Published: 2020

Link to full text (if available)


Share on Social Media:                               Sign Up to like & get
recommendations!

Related content

More Information              News              Social Media              Video              Recommended



                Click one of the above tabs to view related content.