A Method for Road Extraction Using Masked Image Modeling and Contrastive Learning

Authors

Jiangjiang Wu, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Zhenghong Li, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Zhichao Sha, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Hao Chen, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Shuang Peng, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Chun Du, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Jun Li, College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China

Abstract

Abstract: Aiming at the occlusion problem of road extraction from remote sensing images, a road extraction method combining MIM and CL is proposed, the model training process includes a masked pretraining stage and a contrast training stage. The masked pre-training stage mainly carries out mask image reconstruction, and trains the model to recover the whole image from some areas that are randomly occluded. The comparison training stage is mainly for the prediction error and low confidence regions to learn the comparison, to narrow the distance between the features of the same category and increase the distance between the features of different categories. The experimental results verify the effectiveness and usability of this method.

Recommended Citation

Wu, Jiangjiang; Li, Zhenghong; Sha, Zhichao; Chen, Hao; Peng, Shuang; Du, Chun; and Li, Jun (2025) "A Method for Road Extraction Using Masked Image Modeling and Contrastive Learning," Journal of System Simulation: Vol. 37: Iss. 4, Article 8.
DOI: 10.16182/j.issn1004731x.joss.24-1083
Available at: https://dc-china-simulation.researchcommons.org/journal/vol37/iss4/8

First Page

922

Last Page

932

CLC

TP751.1

Recommended Citation

Wu Jiangjiang, Li Zhenghong, Sha Zhichao, et al. A Method for Road Extraction Using Masked Image Modeling and Contrastive Learning[J]. Journal of System Simulation, 2025, 37(4): 922-932.

Corresponding Author

Li Zhenghong

DOI

10.16182/j.issn1004731x.joss.24-1083