Remote-sensing image semi-supervision classification method based on customized step-size learning
A technology of remote sensing image and self-determined step size, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of high subjectivity, error accumulation and propagation, and low work efficiency, and achieve strong anti-noise ability and demand The effect of small volume and strong anti-noise ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0047] Such as figure 1 As shown, the present invention provides a semi-supervised classification method for remote sensing images with self-determined step size learning, which is characterized in that it comprises the following steps:
[0048] Step S1: Preprocessing the remote sensing images to obtain a small number of qualified marked (category information) samples of various types of ground features, the specific contents include:
[0049] Step S11: Perform preprocessing on the acquired remote sensing image according to the image quality of the acquired remote sensing image data source, the preprocessing includes geometric and radiometric correction, image splicing and cropping, image fusion enhancement and feature extraction;
[0050] Step S12: Obtain a few marked samples of each type of ground object in the remote sensing image according to the a...
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