MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 光电信息技术研究室

	MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images
	Zhang, Qingchun 1; Ren, Mengcheng 1; Yang, Jingchao 3; Li Y(李勇)1,4; Jiang, Yanmei 2,3; Wang ED(王恩德)4
刊名	APPLIED SCIENCES-BASEL
	2019
卷号	9 期号:19 页码:1-18
关键词	Semantic segmentation remote sensing images feature fusion cost-sensitive
ISSN号	2076-3417
产权排序	1
英文摘要	Semantic segmentation of remote sensing images is an important technique for spatial analysis and geocomputation. It has important applications in the fields of military reconnaissance, urban planning, resource utilization and environmental monitoring. In order to accurately perform semantic segmentation of remote sensing images, we proposed a novel multi-scale deep features fusion and cost-sensitive loss function based segmentation network, named MFCSNet. To acquire the information of different levels in remote sensing images, we design a multi-scale feature encoding and decoding structure, which can fuse the low-level and high-level semantic information. Then a max-pooling indices up-sampling structure is designed to improve the recognition rate of the object edge and location information in the remote sensing image. In addition, the cost-sensitive loss function is designed to improve the classification accuracy of objects with fewer samples. The penalty coefficient of misclassification is designed to improve the robustness of the network model, and the batch normalization layer is also added to make the network converge faster. The experimental results show that the classification performance of MFCSNet outperforms U-Net and SegNet in classification accuracy, object details and prediction consistency.
语种	英语
WOS记录号	WOS:000496258100101
资助机构	Natural Science Young Foundation of Hebei Provincial Department of Education [QN2017324]
内容类型	期刊论文
源URL	[http://ir.sia.cn/handle/173321/25888]
专题	沈阳自动化研究所_光电信息技术研究室
作者单位	1.College of Information Science and Engineering, Northeastern University, Shenyang 110819, China 2.State Key Laboratory of Reliability and Intelligence of Electrical Equipment, Hebei University of Technology, Tianjin 300130, China 3.Department of Electrical and Information Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang 050000, China 4.Key Laboratory of Optical Electrical Image Processing, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
推荐引用方式 GB/T 7714	Zhang, Qingchun,Ren, Mengcheng,Yang, Jingchao,et al. MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images[J]. APPLIED SCIENCES-BASEL,2019,9(19):1-18.
APA	Zhang, Qingchun,Ren, Mengcheng,Yang, Jingchao,Li Y,Jiang, Yanmei,&Wang ED.(2019).MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images.APPLIED SCIENCES-BASEL,9(19),1-18.
MLA	Zhang, Qingchun,et al."MFCSNet: Multi-Scale Deep Features Fusion and Cost-Sensitive Loss Function Based Segmentation Network for Remote Sensing Images".APPLIED SCIENCES-BASEL 9.19(2019):1-18.