Open Access iconOpen Access

ARTICLE

crossmark

Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images

Supeng Yu1, Fen Huang1,*, Chengcheng Fan2,3,4,*

1 College of Artificial Intelligence, Nanjing Agricultural University, Nanjing, 210095, China
2 Innovation Academy for Microsatellites of CAS, Shanghai, 201210, China
3 Shanghai Engineering Center for Microsatellites, Shanghai, 201210, China
4 Key Laboratory of Satellite Digital Technology, Shanghai, 201210, China

* Corresponding Authors: Fen Huang. Email: email; Chengcheng Fan. Email: email

Computers, Materials & Continua 2024, 79(1), 549-562. https://doi.org/10.32604/cmc.2024.048608

Abstract

Significant advancements have been achieved in road surface extraction based on high-resolution remote sensing image processing. Most current methods rely on fully supervised learning, which necessitates enormous human effort to label the image. Within this field, other research endeavors utilize weakly supervised methods. These approaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such as scribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised and edge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equipped with a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generating edge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise the model’s training by employing scribble labels and spreading scribble information throughout the image. To address the historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blend prediction results dynamically and continually update new pseudo-labels to steer network training. Our solution demonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-label support. The studies are conducted on three separate road datasets, which consist primarily of high-resolution remote-sensing satellite photos and drone images. The experimental findings suggest that our methodology performs better than advanced scribble-supervised approaches and specific traditional fully supervised methods.

Keywords


Cite This Article

APA Style
Yu, S., Huang, F., Fan, C. (2024). Weakly supervised network with scribble-supervised and edge-mask for road extraction from high-resolution remote sensing images. Computers, Materials & Continua, 79(1), 549-562. https://doi.org/10.32604/cmc.2024.048608
Vancouver Style
Yu S, Huang F, Fan C. Weakly supervised network with scribble-supervised and edge-mask for road extraction from high-resolution remote sensing images. Comput Mater Contin. 2024;79(1):549-562 https://doi.org/10.32604/cmc.2024.048608
IEEE Style
S. Yu, F. Huang, and C. Fan "Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images," Comput. Mater. Contin., vol. 79, no. 1, pp. 549-562. 2024. https://doi.org/10.32604/cmc.2024.048608



cc This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
  • 235

    View

  • 179

    Download

  • 0

    Like

Share Link