Remote sensing image classification method based on capsule network
A remote sensing image and classification method technology, applied in the field of remote sensing image processing, can solve the problems of inability to effectively capture remote sensing images, inability to effectively extract advanced features, poor classification effect, etc., and achieve good classification effect, simple structure, and easy to reproduce effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0099] Example
[0100] In this embodiment, the above-mentioned classification method is described by using a remote sensing image with 256*256 pixels.
[0101] like figure 2As shown, obtain the original remote sensing image, each original remote sensing image has a corresponding category label; by cutting the main area of the original remote sensing image and adjusting the image size, the remote sensing image with the pixel of 256*256 is obtained as the sample set; the The image sample set with a pixel of 256*256 is divided into training set and test set; a VGG16-capsule network model is built, and each remote sensing image in the divided training set is input into the VGG16-capsule network model for learning; the loss function formula is used to calculate The loss value between the output value of the VGG16-capsule network model (ie the predicted value) and the actual class label (ie the true value) of each remote sensing image in the training set, adjust the VGG16-capsu...
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