干旱区生态环境知识资源中心(Arid): Capturing Small Objects and Edges Information for Cross-Sensor and Cross-Region Land Cover Semantic Segmentation in Arid Areas

Arid

DOI	10.1109/JSTARS.2022.3232409
	Capturing Small Objects and Edges Information for Cross-Sensor and Cross-Region Land Cover Semantic Segmentation in Arid Areas
	Yuan, Panli; Zhao, Qingzhan; Zheng, Yuchen; Wang, Xuewen; Hu, Bin
通讯作者	Zhao, QZ ; Zheng, YC
来源期刊	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
ISSN	1939-1404
EISSN	2151-1535
出版年	2023
卷号	16 页码:983-997
英文摘要	In the oasis area adjacent to the desert, there is more complex land cover information with rich details, multiscales of interest objects, and blur edge information, which poses some challenges to the semantic segmentation task in remote sensing images (RSIs). In traditional semantic segmentation methods, detailed spatial information is more likely lost in feature extraction stage and the global context information is more effectively integrated into segmentation results. To overcome these land cover semantic segmentation model, FPN_PSA_DLV3+ network, is proposed in an encoder-decoder manner capturing more fine edge and small objects information in RSIs. In the encoder stage, the improved atrous spatial pyramid pooling module extracts the multiscale features, especially small-scale feature details; feature pyramid network (FPN) module realizes better integration of detailed information and semantic information; and the spatial context information at both global and local levels is enhanced by introducing polarized self-attention (PSA) module. For the decoder stage, the FPN_PSA_DLV3+ network further adds a feature fusion branch to concatenate more low-level features. We select Landsat5/7/8 satellite RSIs from the areas of north and south of Xinjiang. Then, three self-annotated time-series datasets with more small objects and fine edges information are constructed by data augmentation. The experimental results show that the proposed method improves the segmentation performance of small targets and edges, and the classification performance increases from 81.55% to 83.10% F1 score and from 72.65% to 74.82% mean intersection over union only using red-green-blue bands. Meanwhile, the FPN_PSA_DLV3+ network shows great generalization in cross region and cross sensor.
英文关键词	Convolutional neural networks (CNNs) fine edge remote sensing image (RSI) semantic segmentation small objects
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000912413700003
WOS类目	Engineering, Electrical & Electronic ; Geography, Physical ; Remote Sensing ; Imaging Science & Photographic Technology
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/396905
推荐引用方式 GB/T 7714	Yuan, Panli,Zhao, Qingzhan,Zheng, Yuchen,et al. Capturing Small Objects and Edges Information for Cross-Sensor and Cross-Region Land Cover Semantic Segmentation in Arid Areas[J],2023,16:983-997.
APA	Yuan, Panli,Zhao, Qingzhan,Zheng, Yuchen,Wang, Xuewen,&Hu, Bin.(2023).Capturing Small Objects and Edges Information for Cross-Sensor and Cross-Region Land Cover Semantic Segmentation in Arid Areas.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,16,983-997.
MLA	Yuan, Panli,et al."Capturing Small Objects and Edges Information for Cross-Sensor and Cross-Region Land Cover Semantic Segmentation in Arid Areas".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 16(2023):983-997.