• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Wu, Xinhui (Wu, Xinhui.) [1] | Mao, Zhengyuan (Mao, Zhengyuan.) [2] (Scholars:毛政元) | Weng, Qian (Weng, Qian.) [3] (Scholars:翁谦) | Shi, Wenzao (Shi, Wenzao.) [4]

Indexed by:

EI PKU CSCD

Abstract:

Current mainstream deep learning network models have many problems such as inner cavity, discontinuity, missed periphery, and irregular boundaries when applied to building extraction from high spatial resolution remote sensing images. This paper proposed the RMAU-Net model by designing a new activation function (Activate Customized or Not, ACON) and integrating residuals block with channel-space and criss-cross attention module based on the U-Net model structure. The ACON activation function in the model allows each neuron to be activated or not activated adaptively, which helps improve the generalization ability and transmission performance of the model. The residual module is used to broaden the depth of the network, reduce the difficulty in training and learning, and obtain deep semantic feature information. The channel-spatial attention module is used to enhance the correlation between encoding and decoding information, suppress the influence of irrelevant background region, and improve the sensitivity of the model. The cross attention module aggregates the context information of all pixels on the cross path and captures the global context information by circular operation to improve the global correlation between pixels. The building extraction experiment using the Massachusetts dataset as samples shows that among all the 7 comparison models, the proposed RMA-UNET model is optimal in terms of intersection of union and F1-score, as well as indexes of precision and recall, and the overall performance of RMAU-Net is better than similar models. Each module is added step by step to further verify the validity of each module and the reliability of the proposed method. ©2022, Science Press. All right reserved.

Keyword:

Chemical activation Convolutional neural networks Deep learning Extraction Pixels Remote sensing Semantics Space optics

Community:

  • [ 1 ] [Wu, Xinhui]Academy of Digital China, Fuzhou University, Fuzhou; 350108, China
  • [ 2 ] [Wu, Xinhui]Key Laboratory of Spatial Data Mining a Information Sharing of Ministry of Education, Fuzhou University, Fuzhou; 350108, China
  • [ 3 ] [Mao, Zhengyuan]Academy of Digital China, Fuzhou University, Fuzhou; 350108, China
  • [ 4 ] [Mao, Zhengyuan]Key Laboratory of Spatial Data Mining a Information Sharing of Ministry of Education, Fuzhou University, Fuzhou; 350108, China
  • [ 5 ] [Weng, Qian]College of Computer and Data Science, Fuzhou University, Fuzhou; 350108, China
  • [ 6 ] [Weng, Qian]Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou; 350108, China
  • [ 7 ] [Shi, Wenzao]College of Opto-Electronic and Information Engineering, Fujian Normal University, Fuzhou; 350007, China
  • [ 8 ] [Shi, Wenzao]Fujian Engineering Technology Research Center of Photoelectric Sensing Application, Fujian Normal University, Fuzhou; 350007, China

Reprint 's Address:

Email:

Show more details

Related Keywords:

Source :

Journal of Geo-Information Science

ISSN: 1560-8999

CN: 11-5809/P

Year: 2022

Issue: 4

Volume: 24

Page: 792-801

Cited Count:

WoS CC Cited Count: 0

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 9

Online/Total:62/10009542
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1