Improved M-Net-based RGB color remote sensing image cloud detection method and system
A remote sensing image and cloud detection technology, applied in the field of deep learning and image recognition, can solve the problems of poor versatility and low accuracy of cloud detection, and achieve easy training, promotion of forward propagation and back propagation, good generalization and The effect of robustness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] The present invention provides a kind of RGB color remote sensing image cloud detection method based on improved M-Net, comprising:
[0040] Training stage: step 1, preprocessing the image;
[0041] Because the training data set is small and the size is too large, considering the limitation of GPU memory, calculation speed and ensuring the timeliness of the segmentation method, the present invention enhances the training data set, mainly through flipping, saturation adjustment, Operations such as brightness adjustment, color adjustment and noise addition;
[0042] Considering the computer memory and calculation speed, the picture is cropped to 256×256 pixels. Calculate the mean value of each image to be detected in the training set in the three dimensions of RGB, and subtract the mean value, which can improve the speed and accuracy of training;
[0043] In the process of making labels, whether each pixel is "cloud", "cloud shadow" or "non-cloud" is represented by 2, 1...
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