Optical remote sensing image change detection method, storage medium and computing device
An optical remote sensing image and change detection technology, which is applied in the field of optical remote sensing image change detection, can solve the problem that the model is easily affected by noise, and achieve the effect of fast convergence and good predictive ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0052] The present invention provides an optical remote sensing image change detection method based on the TernausNet twin neural network. Combining with the idea of TernausNet, the convolution layer in the encoder uses the pre-trained convolution layer of vgg11, which greatly improves the prediction accuracy. Considering the differences in spectral features and target structures between the data set used by the pre-trained vgg11 model and the change detection data set, the present invention adds a branch network at the end of the encoder, and the branch network consists of a randomly initialized convolutional layer, batch normalization The normalization layer and activation function are composed, which can effectively assist the training of the network, so that the difference image obtained from the sub-network of the encoder is closer to the real change of the input image and converges quickly. Compared with the manually designed feature extraction scheme of the traditional...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com