SAR image flood detection and prevention method based on SAE-CNN

A prevention method and image technology, applied in neural learning methods, character and pattern recognition, instruments, etc., can solve problems such as rotation sensitivity and noise interference, and achieve the effect of improving accuracy and efficiency, reducing noise, and eliminating translation sensitivity.

Pending Publication Date: 2020-11-17
JINLING INST OF TECH
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, SAR images have disadvantages such as noise interference, translation sensitivity, and rotation sensitivity.

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
  • SAR image flood detection and prevention method based on SAE-CNN
  • SAR image flood detection and prevention method based on SAE-CNN
  • SAR image flood detection and prevention method based on SAE-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0050] The invention provides a SAE-CNN-based SAR image flood detection and prevention method, utilizes the reconstruction ability of the SAE algorithm, reconstructs the river SAR image, eliminates image noise, and extracts the output of the hidden layer of the SAE model as a sparse feature, combined with CNN The model removes the translation sensitivity and rotation sensitivity of the SAR image, and outputs the water level information of the river to realize flood detection and prevention. The overall algorithm principle flow process of the present invention is as figure 1 As shown, the specific steps are as follows:

[0051] Step 1: Use the spaceborne SAR map image radar photogrammetry SAR image of the river;

[0052] Step 2: In order to remove the noise of the river SAR image and extract the features of the river SAR image, the image data is ...

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 relates to an SAR image flood detection and prevention method based on SAE-CNN, and the method comprises the steps: firstly removing the noise of a river SAR image, extracting the features of the river SAR image, taking image data as the input data, reconstructing the SAR image data, and training a sparse auto-encoder model; in order to remove translation sensitivity and rotation sensitivity of the SAR image, combining a CNN model, taking SAR image data sparse features as input of the CNN model, taking water level information corresponding to the image as output of the CNN model,training a CNN network, and constructing an SAE-CNN model; inputting the image data sparse features to be detected into the trained CNN network, and outputting a river water level information monitoring result; and finally, sending the river water level information monitoring result to a monitoring platform through a Beidou satellite to realize real-time monitoring of river water level information.

Description

technical field [0001] The invention relates to the field of flood detection, and particularly designs a SAE-CNN-based SAR image flood detection and prevention method. Background technique [0002] Flood disasters are generally characterized by strong suddenness, great harm, and wide spatial and temporal distribution. If timely monitoring, assessment and disaster relief can be carried out on flood disasters, it will have an extremely important impact on saving people's lives, saving major economic losses and saving manpower. . To carry out flood monitoring, assessment, disaster relief and arrange post-disaster reconstruction, timely, accurate and reliable collection and feedback of flood disaster-related information is required. The traditional basic ways of collecting hydrological information can be divided into: stationary survey, patrol survey and intermittent survey, etc. Among them, stationary survey refers to the observation of hydrological elements at fixed points in...

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 Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/182G06N3/045
Inventor 司海飞胡兴柳史震沈浩方挺
Owner JINLING INST OF 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