Foundation cloud classification method based on self-adaptive extreme learning machine
An extreme learning machine and self-adaptive technology, applied in the field of image analysis and meteorology, can solve the problems of slow learning speed, lack of systematic modeling of neural network, difference error between input data and learning data, etc., to achieve accurate classification performance, good Generalization performance, the effect of improving the learning speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0026] The present invention will be described in detail below in conjunction with the accompanying drawings. The described examples of implementation are for the purpose of illustration only and are not intended to limit the scope of the invention.
[0027] The present invention proposes a cloud classification method for ground-based cloud images based on an adaptive extreme learning machine. Category identification. Setting cloud class type is 4 kinds of typical cloud shapes in the implementation of the present invention, comprises cumuliform cloud, cirrus cloud, stratiform cloud and clear sky.
[0028] figure 1 is a flowchart of the present invention. refer to figure 1 , the present invention realizes steps as follows:
[0029] Step 1. Extract the texture features, shape features and color features of the cloud image to form a 21-dimensional feature vector.
[0030] (1.1) Extracting the gray level co-occurrence matrix texture P(i, j, δ, φ) represents the probability o...
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