Multispectral remote sensing image terrain classification method based on deep and semi-supervised transfer learning
A transfer learning and remote sensing image technology, applied in the field of remote sensing image processing, can solve the problems of inconsistent distribution of training and testing samples, insufficient training samples, etc., and achieve the effect of improving classification accuracy, good classification effect, and preventing deviation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0057] The present invention provides a multi-spectral remote sensing image feature classification method based on deep semi-supervised migration learning. When training samples are insufficient, a source domain similar to the target domain and unlabeled samples of the target domain are used to assist the classification of target domain data. Specifically: input the multispectral remote sensing image of the training sample, take out the training data set D and kNN data K1 and K2 according to the ground truth; divide the training data set D into two parts, and train two different CNN models CNN1 and CNN2; For classified multi-spectral images, two classification result maps F1 and F2 are obtained in two CNN models; two kNN neighboring algorithm maps are constructed according to training samples K1 and K2, kNN1 and kNN2; F1 and F2 are used to take out the test data A1 and A2, use the kNN proximity algorithm to classify the data; update the classification result graph; update the tr...
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