Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A kind of remote sensing image cloud removal residual neural network system, method, device and storage medium based on multi-scale convolution and attention

A remote sensing image and neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as long computing time, large computing resource consumption, poor recovery effect, etc., to achieve strong learning ability and enhance adaptation. Effects of Sex and Robustness

Active Publication Date: 2022-07-08
NORTHEAST FORESTRY UNIVERSITY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of poor recovery effect, huge consumption of computing resources and long computing time of the existing cloud removal algorithm, the present invention proposes a remote sensing image cloud removal residual neural network system based on multi-scale convolution and attention , method, equipment and storage medium, the concrete scheme of the present invention is as follows:

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
  • A kind of remote sensing image cloud removal residual neural network system, method, device and storage medium based on multi-scale convolution and attention
  • A kind of remote sensing image cloud removal residual neural network system, method, device and storage medium based on multi-scale convolution and attention
  • A kind of remote sensing image cloud removal residual neural network system, method, device and storage medium based on multi-scale convolution and attention

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0033] Embodiment 1: A high-resolution remote sensing image cloud removal residual neural network system based on multi-scale convolution and channel attention mechanism, the system includes an input module, a data enhancement module, a dimension enhancement module, a delicate feature module, a multi-dimensional A scale convolution module, a dimensionality reduction module and an output module; the above modules complete the logical link for a progressive relationship; the input module is responsible for collecting remote sensing image data; the data enhancement module is used to enhance the richness of the remote sensing image data enhancement operation obtained by the input module; The dimension increase module is responsible for increasing the dimension of the remote sensing image data; the delicate feature module is responsible for cropping the remote sensing image; the multi-scale convolution module is responsible for removing noise from the remote sensing image; the dimens...

specific Embodiment approach 2

[0034]Embodiment 2: In addition to the system flow of Embodiment 1, this embodiment proposes a method (MSAR_DefogNet) based on multi-scale convolution and attention to remove cloud residuals from remote sensing images. The richer dataset PRSC for the image de-cloud task. The multi-scale convolution block in the MSAR_DefogNet model can extract features of different scales and fuse these features to achieve efficient cloud removal. The residual block with channel attention mechanism can extract detailed features and realize the function of mining detailed information. Using the PRSC dataset can enhance the adaptability and robustness of the model, which helps to transfer the model to real-world scenarios. Compared with the existing algorithms, this method does not require explicit estimation of the transmission rate, etc., has a stronger learning ability, can adapt to a variety of scene changes, has better image restoration effect and faster processing speed, and has a high imp...

specific Embodiment approach 3

[0073] Specific embodiment three: the above method examples can be attached according to the description figure 1 The block diagram shown is for the division of functional modules. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module; the above-mentioned integrated modules can be implemented in the form of hardware, It can also be implemented in the form of software function modules. It should be noted that, the division of modules in the embodiment of the present invention is schematic, and is only a logical function division, and there may be other division manners in actual implementation.

[0074] Specifically, the system is carried on a computer, including a processor, a memory, a bus and a communication device;

[0075] The memory is used to store computer-executed instructions, the processor is connected to the memory through the bus, the processor executes the computer-exec...

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 proposes a remote sensing image cloud removal residual neural network system, method, equipment and storage medium based on multi-scale convolution and attention, belonging to the field of remote sensing image processing, in order to solve the problem that traditional algorithms have poor robustness and recovery effects do not conform to remote sensing The problem of visual characteristics of images. The deep neural network method achieves a balance between the speed of the high-resolution remote sensing image cloud removal task and the restoration effect; the use of multi-scale context convolution with a larger range of convolution kernel size reduces the memory required by the model and the algorithmic complexity. processing time; and before multi-scale convolution, fine-grained convolution with channel attention module is spliced ​​in the form of residual connection to increase the feature extraction capability of the network; the present invention is more realistic and more in line with the actual scene dedicated to high resolution For the dataset of remote sensing image cloud removal task, no matter what kind of network model, the network weights trained on this dataset have higher adaptability and stronger robustness.

Description

technical field [0001] The invention relates to a remote sensing image cloud removal residual neural network system and method based on multi-scale convolution and attention, and belongs to the field of remote sensing image processing. Background technique [0002] There is a lot of cloud noise in remote sensing images. The existence of clouds greatly reduces the utilization rate of remote sensing images and increases the cost of remote sensing technology. The brightening effect of clouds and the darkening effect of cloud shadows affect a variety of data analysis and cause problems with many remote sensing activities, including inaccurate atmospheric corrections, biased estimates of normalized difference vegetation index values, land cover misclassification, and land cover Changed error detection. In most application tasks, reducing the resources required for model computation is quite friendly to many individuals training. Especially in application scenarios such as milit...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V10/80G06V20/10G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06N3/045G06F18/253
Inventor 景维鹏陈广胜周莹李林辉徐达丽
Owner NORTHEAST FORESTRY UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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