Hyperspectral image classification method based on three-dimensional convolutional neural network
A hyperspectral image and three-dimensional convolution technology, applied in the field of hyperspectral image classification, can solve the problems of destroying the spatial information and spectral information of three-dimensional hyperspectral images, rearranging rough three-dimensional signals, and being unable to fully utilize the spatial information of hyperspectral images, etc. Achieving a good classification effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0029] Specific implementation mode 1: Combination figure 1 To explain this embodiment, the specific process of the hyperspectral image classification method based on the three-dimensional convolutional neural network in this embodiment is as follows:
[0030] Step 1: Import the hyperspectral image data set into the MATLAB platform, and normalize the three-dimensional data information in the hyperspectral image data set imported into the MATLAB platform layer by layer to obtain a processed data set;
[0031] Select the same amount of data (200 for soil, 200 for water and 200 for sky) of all categories (soil, water and sky) tags from the processed data set and record the space coordinates;
[0032] Use the processed data set as the test set;
[0033] The three-dimensional data information in the hyperspectral image data set includes spectral information and spatial information;
[0034] The hyperspectral image data set is in the form of a three-dimensional matrix;
[0035] Step 2: Take th...
Example Embodiment
[0044] Specific embodiment two: this embodiment is different from specific embodiment one in that in the first step, the hyperspectral image data set is imported into the MATLAB platform, and the three-dimensional data information in the hyperspectral image data set imported into the MATLAB platform is sorted layer by layer. One process to obtain a processed data set; the specific process is:
[0045] Import the hyperspectral image data set into the MATLAB platform used in the experiment, and perform layer-by-layer normalization on the three-dimensional data information of the hyperspectral image data set imported into the MATLAB platform. The formula is:
[0046]
[0047] In the formula, 1≤i≤W, 1≤j≤L, 1≤k≤H, Is the normalization function, Is the three-dimensional data of the hyperspectral image data set at positions i, j, and k, i, j represent the spatial position of the three-dimensional data information in the hyperspectral image data set, k represents the spectral band of the ...
Example Embodiment
[0051] Specific embodiment three: This embodiment is different from specific embodiments one or two in that in the third step, a three-dimensional convolutional neural network is built on the Keras platform according to a training set in the form of a three-dimensional matrix; the specific process is:
[0052] 1) The three-dimensional convolution layer performs sliding window convolution on the training set in the form of the three-dimensional matrix as the input of the three-dimensional convolutional neural network, and uses the three-dimensional convolutional layer as the first layer of the three-dimensional convolutional neural network;
[0053] When using a three-dimensional convolutional layer as the first layer of a three-dimensional convolutional neural network, input_shape (when the training set in the form of a three-dimensional matrix is used as input) parameters must be provided;
[0054] 2) The channel position of the training set data after sliding window convolution is...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap