Autonomous Learning Interactive Features for Hyperspectral Remotely Sensed Data

被引:2
|
作者
Dai, Ling [1 ]
Zhang, Guangyun [1 ]
Gong, Jinqi [1 ]
Zhang, Rongting [1 ]
机构
[1] Nanjing Tech Univ, Sch Geomat Sci & Technol, Nanjing 211816, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 21期
关键词
hyperspectral image; feature extraction; interactive features; sparse multiclass logistic regression; autonomous learning; CLASSIFICATION; INDEX; DELINEATION;
D O I
10.3390/app112110502
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In the field of remote sensing, most of the feature indexes are obtained based on expert knowledge or domain analysis. With the rapid development of machine learning and artificial intelligence, this method is time-consuming and lacks flexibility, and the indexes obtained cannot be applied to all areas. In order to not rely on expert knowledge and find the effective feature index with regard to a certain material automatically, this paper proposes a data-driven method to learn interactive features for hyperspectral remotely sensed data based on a sparse multiclass logistic regression model. The key point explicitly expresses the interaction relationship between original features as new features by multiplication or division operation in the logistic regression. Through the strong constraint of the L1 norm, the learned features are sparse. The coefficient value of the corresponding features after sparse represents the basis for judging the importance of the features, and the optimal interactive features among the original features. This expression is inspired by the phenomenon that usually the famous indexes we used in remote sensing, like NDVI, NDWI, are the ratio between different spectral bands, and also in statistical regression, the relationship between features is captured by feature value multiplication. Experiments were conducted on three hyperspectral data sets of Pavia Center, Washington DC Mall, and Pavia University. The results for binary classification show that the method can extract the NDVI and NDWI autonomously, and a new type of metal index is proposed in the Pavia University data set. This framework is more flexible and creative than the traditional method based on laboratory research to obtain the key feature and feature interaction index for hyperspectral remotely sensed data.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] Probabilistic anomaly detector for remotely sensed hyperspectral data
    Gao, Lianru
    Guo, Qiandong
    Plaza, Antonio
    Li, Jun
    Zhang, Bing
    [J]. JOURNAL OF APPLIED REMOTE SENSING, 2014, 8
  • [2] Deep learning for remotely sensed data
    Mountrakis, Giorgos
    Li, Jun
    Lu, Xiaoqiang
    Hellwich, Olaf
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 145 : 1 - 2
  • [3] Solar spectral irradiometer for validation of remotely sensed hyperspectral data
    Barducci, A
    Castagnoli, F
    Guzzi, D
    Marcoionni, P
    Pippi, I
    Poggesi, M
    [J]. APPLIED OPTICS, 2004, 43 (01) : 183 - 195
  • [4] Remotely Sensed Hyperspectral Data to Determine Chlorophyll-a in RiverWater
    Pandey, Ayushi
    Pandey, Pramod
    Garg, Vaibhav
    Dikshit, Anant
    Pandey, Prachi
    Pandey, Aditya
    Rai, Navneet
    Singh, Vikrant
    Stillway, Marie
    Singh, Vijay
    [J]. TOWARDS WATER CIRCULAR ECONOMY, RWC 2024, 2024, : 176 - 187
  • [5] Experiments on feature extraction in remotely sensed hyperspectral image data
    Zortea, M
    Haertel, V
    [J]. IGARSS 2004: IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM PROCEEDINGS, VOLS 1-7: SCIENCE FOR SOCIETY: EXPLORING AND MANAGING A CHANGING PLANET, 2004, : 964 - 967
  • [6] Active-Metric Learning for Classification of Remotely Sensed Hyperspectral Images
    Pasolli, Edoardo
    Yang, Hsiuhan Lexie
    Crawford, Melba M.
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2016, 54 (04): : 1925 - 1939
  • [7] AN ATMOSPHERIC CORRECTION METHOD FOR REMOTELY SENSED HYPERSPECTRAL THERMAL INFRARED DATA
    Wang, Xinghong
    OuYang, Xiaoying
    Li, Zhao-Liang
    Jiang, Xiaoguang
    Ma, Lingling
    [J]. 2009 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, VOLS 1-5, 2009, : 1979 - +
  • [8] A Deep Belief Network for Classifying Remotely-Sensed Hyperspectral Data
    Le, Justin H.
    Yazdanpanah, Ali Pour
    Regentova, Emma E.
    Muthukumar, Venkatesan
    [J]. ADVANCES IN VISUAL COMPUTING, PT I (ISVC 2015), 2015, 9474 : 682 - 692
  • [9] Measuring trace gases in plumes from hyperspectral remotely sensed data
    Marion, R
    Michel, W
    Faye, C
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2004, 42 (04): : 854 - 864
  • [10] Acquiring hyperspectral remotely sensed images classification rules using inductive learning
    Sun, LX
    Zhang, YM
    [J]. HYPERSPECTRAL REMOTE SENSING AND APPLICATIONS, 1998, 3502 : 164 - 168