A SAR image change detection method based on complex neural network
A technology of image change detection and neural network, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problem of low detection accuracy of SAR image change detection
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0072] The invention provides a SAR image change detection method based on a complex neural network. Two original SAR gray images are input, and a preliminary difference map is obtained by a traditional method as a preliminary label; according to the preliminary label, two original SAR images are screened out through confidence detection. Part of the pixel blocks in the image are used as candidate training samples; a complex network including 3 layers of complex fully connected layers and 2 layers of complex batch normalization layers is constructed; part of the candidate training samples is selected according to a random ratio method to construct complex training samples, In this way, the complex number network is trained; the test complex number samples directly constructed from two original SAR images are tested by using the trained complex number network, and the final change detection result is obtained. The invention has the advantages of accurately distinguishing changed...
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