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

Pending Publication Date: 2019-06-25
NANJING UNIV OF INFORMATION SCI & TECH
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a method for cloud detection of RGB color remote sensing images based on improved M-Net, w

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Improved M-Net-based RGB color remote sensing image cloud detection method and system
  • Improved M-Net-based RGB color remote sensing image cloud detection method and system
  • Improved M-Net-based RGB color remote sensing image cloud detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0038] Example 1

[0039] The present invention provides a RGB color remote sensing image cloud detection method based on improved M-Net, including:

[0040] Training stage: Step 1. Preprocess the image;

[0041] Since the training data set is small and the size is too large, taking into account the limitations 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] Taking into account the computer's video memory and calculation speed, the picture is cropped to 256×256 pixels. Calculate the average value of each image to be detected in the training set in the three dimensions of RGB, and subtract the average value, which can improve the speed and accuracy of training;

[0043] The label production process uses 2, 1 and 0 to indicate whether each pixel is "cloud", "c...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an improved M-Net-based RGB color remote sensing image cloud detection method and system, and belongs to the field of artificial intelligence and image recognition, RM-Net deepsemantic segmentation network is designed combining advantages of a residual error network and M-Net. The method comprises the following steps: firstly, enhancing an original data set, and labeling acorresponding pixel-level tag; multi-scale features of the image are extracted on the premise that information is not lost through pooling of the hollow space pyramid, and the network is not prone todegeneration by combining with a residual unit; and finally, extracting global context information of the image by using an encoder module and a left path, recovering the spatial resolution of the image by using a decoder module and a right path, judging the category probability of each pixel according to the fused characteristics, and inputting the category probability into a classifier for pixel-level cloud and non-cloud segmentation. According to the method, the color image is trained and tested, experimental results show that the cloud edge details can be well detected under different conditions, high-precision cloud shadow detection is obtained, and it is proved that the method has good generalization and robustness.

Description

technical field [0001] The invention relates to the fields of deep learning and image recognition, in particular to a method and system for detecting cloud of RGB color remote sensing images based on improved M-Net. Background technique [0002] With the development of remote sensing technology, remote sensing images have been widely used in meteorological detection, resource utilization and environmental detection and other work fields. The global cloud coverage area accounts for about 68% of the earth's land surface, and cloud detection is also an important part of remote sensing data processing. Correctly separating cloudy pixels and cloudless pixels in remote sensing images has become an important basic work for weather forecasting and natural disaster prediction. Therefore, effective cloud detection is a prerequisite for subsequent analysis and utilization of remote sensing images. [0003] At present, a variety of cloud detection methods have been proposed, including...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06K9/46G06K9/62
CPCY02A90/10
Inventor 张秀再胡敬锋沈嘉程刘思成蒋闯
Owner NANJING UNIV OF INFORMATION SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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