MSFANet: Multi-Scale Strip Feature Attention Network for Cloud and Cloud Shadow Segmentation

被引:16
|
作者
Chen, Kai [1 ]
Dai, Xin [1 ]
Xia, Min [1 ]
Weng, Liguo [1 ]
Hu, Kai [1 ]
Lin, Haifeng [2 ]
机构
[1] Nanjing Univ Informat Sci & Technol, Collaborat Innovat Ctr Atmospher Environm & Equipm, Nanjing 210044, Peoples R China
[2] Nanjing Forestry Univ, Coll Informat Sci & Technol, Nanjing 210037, Peoples R China
关键词
cloud; cloud shadow; attention; image segmentation; MASK;
D O I
10.3390/rs15194853
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Cloud and cloud shadow segmentation is one of the most critical challenges in remote sensing image processing. Because of susceptibility to factors such as disturbance from terrain features and noise, as well as a poor capacity to generalize, conventional deep learning networks, when directly used to cloud and cloud shade detection and division, have a tendency to lose fine features and spatial data, leading to coarse segmentation of cloud and cloud shadow borders, false detections, and omissions of targets. To address the aforementioned issues, a multi-scale strip feature attention network (MSFANet) is proposed. This approach uses Resnet18 as the backbone for obtaining semantic data at multiple levels. It incorporates a particular attention module that we name the deep-layer multi-scale pooling attention module (DMPA), aimed at extracting multi-scale contextual semantic data, deep channel feature information, and deep spatial feature information. Furthermore, a skip connection module named the boundary detail feature perception module (BDFP) is introduced to promote information interaction and fusion between adjacent layers of the backbone network. This module performs feature exploration on both the height and width dimensions of the characteristic pattern to enhance the recovery of boundary detail intelligence of the detection targets. Finally, during the decoding phase, a self-attention module named the cross-layer self-attention feature fusion module (CSFF) is employed to direct the aggregation of deeplayer semantic feature and shallow detail feature. This approach facilitates the extraction of feature information to the maximum extent while conducting image restoration. The experimental outcomes unequivocally prove the efficacy of our network in effectively addressing complex cloud-covered scenes, showcasing good performance across the cloud and cloud shadow datasets, the HRC_WHU dataset, and the SPARCS dataset. Our model outperforms existing methods in terms of segmentation accuracy, underscoring its paramount importance in the field of cloud recognition research.
引用
收藏
页数:25
相关论文
共 50 条
  • [1] Multi-scale strip pooling feature aggregation network for cloud and cloud shadow segmentation
    Chen Lu
    Min Xia
    Haifeng Lin
    [J]. Neural Computing and Applications, 2022, 34 : 6149 - 6162
  • [2] Multi-scale strip pooling feature aggregation network for cloud and cloud shadow segmentation
    Lu, Chen
    Xia, Min
    Lin, Haifeng
    [J]. NEURAL COMPUTING & APPLICATIONS, 2022, 34 (08): : 6149 - 6162
  • [3] LPMSNet: Location Pooling Multi-Scale Network for Cloud and Cloud Shadow Segmentation
    Dai, Xin
    Chen, Kai
    Xia, Min
    Weng, Liguo
    Lin, Haifeng
    [J]. REMOTE SENSING, 2023, 15 (16)
  • [4] Multiscale Attention Feature Aggregation Network for Cloud and Cloud Shadow Segmentation
    Chen, Kai
    Xia, Min
    Lin, Haifeng
    Qian, Ming
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [5] Strip pooling channel spatial attention network for the segmentation of cloud and cloud shadow
    Qu, Yi
    Xia, Min
    Zhang, Yonghong
    [J]. COMPUTERS & GEOSCIENCES, 2021, 157
  • [6] Strip pooling channel spatial attention network for the segmentation of cloud and cloud shadow
    Qu, Yi
    Xia, Min
    Zhang, Yonghong
    [J]. Computers and Geosciences, 2021, 157
  • [7] Shadow Detection with Attention Feature Block and Multi-scale Weight Segmentation Network
    Xu, Di
    Wang, Zhili
    [J]. 2020 6TH INTERNATIONAL CONFERENCE ON COMMUNICATION AND INFORMATION PROCESSING, ICCIP 2020, 2020, : 43 - 51
  • [8] Multi-Branch Attention Fusion Network for Cloud and Cloud Shadow Segmentation
    Gu, Hongde
    Gu, Guowei
    Liu, Yi
    Lin, Haifeng
    Xu, Yao
    [J]. REMOTE SENSING, 2024, 16 (13)
  • [9] Point Cloud Semantic Segmentation Network Based on Multi-Scale Feature Fusion
    Du, Jing
    Jiang, Zuning
    Huang, Shangfeng
    Wang, Zongyue
    Su, Jinhe
    Su, Songjian
    Wu, Yundong
    Cai, Guorong
    [J]. SENSORS, 2021, 21 (05) : 1 - 20
  • [10] Fusion of Geometric Attention and Multi-Scale Feature Network for Point Cloud Registration
    Du, Jiajin
    Bai, Zhengyao
    Liu, Xuheng
    Li, Zekai
    Xiao, Xiao
    You, Yilin
    [J]. Computer Engineering and Applications, 2024, 60 (12) : 234 - 244