FCAE-AD: Full Convolutional Autoencoder Based on Attention Gate for Hyperspectral Anomaly Detection

被引:2
|
作者
Wang, Xianghai [1 ,2 ]
Wang, Yihan [2 ]
Mu, Zhenhua [1 ]
Wang, Ming [2 ]
机构
[1] Liaoning Normal Univ, Sch Geog Sci, Dalian 116029, Peoples R China
[2] Liaoning Normal Univ, Sch Comp Sci & Artificial Intelligence, Dalian 116029, Peoples R China
关键词
hyperspectral image; anomaly detection; autoencoder; guided filtering; attention gate;
D O I
10.3390/rs15174263
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Recently, the methods based on the autoencoder reconstruction background have been applied to the area of hyperspectral image (HSI) anomaly detection (HSI-AD). However, the encoding mechanism of the autoencoder (AE) makes it possible to treat the anomaly and the background indistinguishably during reconstruction, which can result in a small number of anomalous pixels still being included in the acquired reconstruction background. In addition, the problem of redundant information in HSIs also exists in reconstruction errors. To this end, a fully convolutional AE hyperspectral anomaly detection (AD) network with an attention gate (AG) connection is proposed. First, the low-dimensional feature map as a product of the encoder and the fine feature map as a product of the corresponding decoding stage are simultaneously input into the AG module. The network context information is used to suppress the irrelevant regions in the input image and obtain the significant feature map. Then, the features from the AG and the deep features from upsampling are efficiently combined in the decoder stage based on the skip connection to gradually estimate the reconstructed background image. Finally, post-processing optimization based on guided filtering (GF) is carried out on the reconstruction error to eliminate the wrong anomalous pixels in the reconstruction error image and amplify the contrast between the anomaly and the background.
引用
收藏
页数:18
相关论文
共 50 条
  • [31] Pixel-associated autoencoder for hyperspectral anomaly detection
    Xiang, Pei
    Ali, Shahzad
    Zhang, Jiajia
    Jung, Soon Ki
    Zhou, Huixin
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2024, 129
  • [32] Integration of an autoencoder and background suppression for hyperspectral anomaly detection
    Hu, Xing
    Chen, Tingting
    Zhang, Dawei
    REMOTE SENSING LETTERS, 2024, 15 (09) : 977 - 987
  • [33] A cascaded autoencoder unmixing network for Hyperspectral anomaly detection
    Li, Kun
    Wang, Yingqian
    Ling, Qiang
    Cai, Yaoming
    Qin, Yao
    INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION, 2025, 136
  • [34] Dynamic Negative Sampling Autoencoder for Hyperspectral Anomaly Detection
    Wang, Jingxuan
    Sun, Jinqiu
    Xia, Yong
    Zhang, Yanning
    IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15 : 9829 - 9841
  • [35] Graph Attention Convolutional Autoencoder-Based Unsupervised Nonlinear Unmixing for Hyperspectral Images
    Jin, Danni
    Yang, Bin
    IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 7896 - 7906
  • [36] LogAttn: Unsupervised Log Anomaly Detection with an AutoEncoder Based Attention Mechanism
    Zhang, Linming
    Li, Wenzhong
    Zhang, Zhijie
    Lu, Qingning
    Hou, Ce
    Hu, Peng
    Gui, Tong
    Lu, Sanglu
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT III, 2021, 12817 : 222 - 235
  • [37] Anomaly detection of defects on concrete structures with the convolutional autoencoder
    Chow, J. K.
    Su, Z.
    Wu, J.
    Tan, P. S.
    Mao, X.
    Wang, Y. H.
    ADVANCED ENGINEERING INFORMATICS, 2020, 45 (45)
  • [38] SDN traffic anomaly detection method based on convolutional autoencoder and federated learning
    Wang, ZiXuan
    Wang, Pan
    Sun, ZhiXin
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 4154 - 4160
  • [39] Attention boosted autoencoder for building energy anomaly detection
    Pydi, Durga Prasad
    Advaith, S.
    ENERGY AND AI, 2023, 14
  • [40] Temporal autoencoder architectures with attention for ECG anomaly detection
    Varghese A.
    Midhun M.S.
    Kurian J.
    International Journal of Business Intelligence and Data Mining, 2024, 24 (02) : 146 - 159