An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery

doi:10.1109/JSTARS.2025.3584546

	An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery
	Wei, Wentao 1,2; Chen, Huan 1,2; Jiang, Yu 1,2; Fu, Li 1,2; Yao, Ping 1,2
	2025
发表期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
卷号	18 页码:16929-16941
摘要	Monitoring urban public spaces is a vital component of scientific urban planning. This article proposes an improved masked autoencoder (MAE)-based pretraining method for automatic monitoring of urban public spaces with semantic segmentation of optical satellite remote sensing imagery. Different from most existing image encoders of vision transformer pretrained with MAE method on natural images, which have difficulty in transferring to small-scale remote sensing dataset because of its large domain gap relative to natural images and limit the fine-tuning performance on downstream tasks, our method performs pretraining directly on target remote sensing imagery to better capture its feature distribution. Specifically, label information is filled into masked regions to enhance the model's image reconstruction capabilities. In addition, we design a momentum branch to ensure the stability and consistency of feature updates and adopt the dynamic masking strategy to reduce reconstruction difficulty during the initial stages of pretraining. This ensures a smooth transition to later stages, significantly improving the accuracy and efficiency of image generation. Experimental results demonstrate that the proposed method significantly outperforms competing MAE-based vision transformer approaches as well as state-of-the-art CNN-based methods on the test dataset. Furthermore, an analysis of the per capita public space in Haikou city validates the effectiveness of the proposed method for monitoring urban public spaces.
关键词	Masked autoencoder (MAE) remote sensing semantic segmentation semantic segmentation urban public space urban public space urban public space
DOI	10.1109/JSTARS.2025.3584546
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA19020400]
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:001531874800004
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42091
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yao, Ping
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China
推荐引用方式 GB/T 7714	Wei, Wentao,Chen, Huan,Jiang, Yu,et al. An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2025,18:16929-16941.
APA	Wei, Wentao,Chen, Huan,Jiang, Yu,Fu, Li,&Yao, Ping.(2025).An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,18,16929-16941.
MLA	Wei, Wentao,et al."An Improved MAE-Based Pretraining Method for Urban Public Space Monitoring With Optical Remote Sensing Imagery".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 18(2025):16929-16941.