Research Article
Classification of Hyperspectral Remote Sensing Images Based on Three-Dimensional Convolutional Neural Network Model
@INPROCEEDINGS{10.1007/978-3-031-50546-1_30, author={Pan Zhao and Xiaoling Yin and Shida Chen}, title={Classification of Hyperspectral Remote Sensing Images Based on Three-Dimensional Convolutional Neural Network Model}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part II}, proceedings_a={ADHIP PART 2}, year={2024}, month={3}, keywords={3D Convolutional Neural Network Model Normalization Processing Hyperspectral Remote Sensing Images Support Vector Machine}, doi={10.1007/978-3-031-50546-1_30} }- Pan Zhao
Xiaoling Yin
Shida Chen
Year: 2024
Classification of Hyperspectral Remote Sensing Images Based on Three-Dimensional Convolutional Neural Network Model
ADHIP PART 2
Springer
DOI: 10.1007/978-3-031-50546-1_30
Abstract
In response to the problems of low accuracy and long time consumption in traditional hyperspectral remote sensing image classification methods, this paper proposes a hyperspectral remote sensing image classification method based on a three-dimensional convolutional neural network model. Firstly, the image data is preprocessed and normalized. Based on this, a three-dimensional convolutional neural network is introduced into the learning of image data. On this basis, by optimizing the overall connectivity parameters of the convolutional kernel function, hyperspectral remote sensing image classification based on the convolutional kernel function was achieved. Experiments have shown that the algorithm proposed in this article can accurately classify hyperspectral images and achieve good results.
