MLAE: A Pretraining Method for Automatic Identification of Urban Public Space

doi:10.1109/LGRS.2023.3315687

	MLAE: A Pretraining Method for Automatic Identification of Urban Public Space
	Cheng, Siyuan 1; Chen, Huan 1; Yao, Ping 1; Song, Liuyi 2
	2023
发表期刊	IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
ISSN	1545-598X
卷号	20 页码:5
摘要	This letter proposes a deep-learning-based remote sensing image segmentation method for estimating the proportion of urban public space, which is an important urban planning problem. Remote sensing images contain diverse landforms and different scales of objects, making image segmentation a challenging task. Most current image segmentation methods use convolutional neural networks, which are deep neural networks that can automatically learn image features and perform classification or regression. However, existing convolutional neural networks are usually pretrained on natural image datasets such as ImageNet, which are very different from remote sensing images, resulting in pretrained models that cannot fully exploit the characteristics of remote sensing images. To address this issue, this letter proposes a MixLabel Autoencoder (MLAE) to further pretrain remote sensing images by image reconstruction. Unlike natural images, remote sensing images are complex and difficult to reconstruct; therefore, we use partial labels to guide the reconstruction process. Our method involves replacing random patches of the input image with corresponding labels and reconstructing the patches using an encoder-decoder architecture. Experimental results show that our method achieves higher segmentation accuracy and better visual effects in downstream tasks. Our method provides valuable guidance for urban planning and construction by identifying the proportion of pixels within each type of area in an image.
关键词	Image reconstruction Task analysis Remote sensing Feature extraction Computational modeling Training Decoding MixLabel antoencoder remote sensing semantic segmentation urban public space
DOI	10.1109/LGRS.2023.3315687
收录类别	SCI
语种	英语
资助项目	National DefenseScience and Technology Key Laboratory Fund Research Project[6142113210302]
WOS研究方向	Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology
WOS类目	Geochemistry & Geophysics ; Engineering, Electrical & Electronic ; Remote Sensing ; Imaging Science & Photographic Technology
WOS记录号	WOS:001080604700012
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：6[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21142
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.Univ Chinese Acad Sci, Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Chinese Univ Hong Kong, Inst Space & Earth Informat Sci, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Siyuan,Chen, Huan,Yao, Ping,et al. MLAE: A Pretraining Method for Automatic Identification of Urban Public Space[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2023,20:5.
APA	Cheng, Siyuan,Chen, Huan,Yao, Ping,&Song, Liuyi.(2023).MLAE: A Pretraining Method for Automatic Identification of Urban Public Space.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,20,5.
MLA	Cheng, Siyuan,et al."MLAE: A Pretraining Method for Automatic Identification of Urban Public Space".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 20(2023):5.