Identification of Earth’s surface objects using ensembles of convolutional neural networks.

Журнал Белорусского государственного университета: Математика, информатика

Xiangtao Zheng¹  Evgenii E. Marushko²  Alexander A. Doudkin² 

[1] Xiʼan Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Shaanxi, Xiʼan 710119, China;United Institute of Informatics Problems, National Academy of Sciences of Belarus,6 Surhanava Street, Minsk 220012, Belarus;

关键词: convolutional neural network;    support vector machine;    neural network ensemble;    earth’s surface image;    remote sensing;    identification;    synthetic aperture radar;   

DOI  :  10.33581/2520-6508-2021-2-114-123

来源: DOAJ

【 摘 要 】

The paper proposes an identification technique of objects on the Earth’s surface images based on combination of machine learning methods. Different variants of multi-layer convolutional neural networks and support vector machines are considered as original models. A hybrid convolutional neural network that combines features extracted by the neural network and experts is proposed. Optimal values of hyperparameters of the models are calculated by grid search methods using k-fold cross-validation. The possibility of improving the accuracy of identification based on the ensembles of these models is shown. Effectiveness of the proposed technique is demonstrated by the example of images obtained by synthetic aperture radar.

【 授权许可】

Unknown